Empyre turns a plain-language description of a business into a published software company operated by eight specialised AI agents.
This page describes what actually happens, in order, and what you get at the end.
What happens when you launch
- Describe the businessPlain words. What it does, who it is for. Naming a stack is optional. Go, FastAPI, Django, Rails, or another runtime is built as named, including for a new company. Silence means a web application.
- Infrastructure is provisionedA repository, a release target, an encrypted environment vault, and internal authentication keys so the product's own sign-up works.
- The CTO buildsThe first CTO cycle produces the application: the interface, the architecture and the core product. This is the run that decides the shape of everything after it.
- The product is marked readyRelease is gated until the core product actually works. The CTO flips that flag; agents cannot publish an unbuilt product.
- It publishes to a live addressEvery business gets a one-word address of the form yourword.empyre.site, free on every plan, with HTTPS and no DNS for you to configure.
- The other agents take overThe CMO writes positioning and launch content, the CLO produces terms and privacy, the Tester exercises the product and reports what broke, the CFO watches spend.
- Weekly cycles continueWhile the plan is active, agents keep maintaining, fixing and hardening the product. This is the part that distinguishes Empyre from an app builder.
The eight agents
| Agent | Responsibility |
|---|---|
| CEO | Sets direction, turns your instructions into work for the other agents, commits the company to goals set against numbers the platform measured, and reports back. You can also text it on iMessage, typed or as a voice note, and it sends you the reports you ask for, when you ask for them. |
| CTO | Writes the code, commits it, and publishes the product. Runs security scans and SEO audits against what it shipped. Owns the technical build. |
| CMO | Works from your marketing plan: the channels you want, the ones you rule out and your goals, on top of a playbook for your kind of business (a restaurant starts with its Google listing, reviews and photos; a software product with articles). Where articles are part of the plan it publishes at least one a day to the product's built-in server-rendered blog, and more when it judges the topics deserve it (up to two a day on Starter, four on Growth, eight on Empyre and pay as you go); decides the positioning every other channel then delivers; works SEO from the company's own Google data (Search Console and Analytics once you connect them, Keyword Planner demand either way), keeping a backlog where every item carries its evidence and measuring each change a month later, and improves answer-engine visibility; posts text, links, pictures and flyers to the company's connected Instagram, Facebook and X accounts through one posting queue that posts on its own by default, or asks you first about every post or only the critical ones if you choose; researches competitors; and — on Growth and above, a week after launch — runs Google Ads and Meta Ads (Facebook and Instagram) campaigns from one ads balance, choosing the split between them itself unless you pick the networks. When you turn Automatic Outreach on and that company's Gmail can send, it also researches public businesses and emails from that mailbox. Outreach stays off until you do, and SEO keeps running either way. |
| CFO | Watches spend, approves or refuses cost, and keeps the business inside its budget. Reads what everything actually cost from the ledgers and proposes savings it then measures; nothing changes without your yes. |
| CSO | Works the customer support inbox, resolves tickets, and escalates real bugs to the CTO as defects. Books a meeting from outreach only when you allow that separately, and only on a calendar you connected. Cancels a subscription or refunds a payment for the customer who asked, on the company's own Stripe, within the authority you set. |
| CLO | Terms, privacy policy, contract review and e-signature — the legal surface a real product needs. |
| Creative | Generates the brand imagery, on-brand variants, product photography, cut-out assets, social pictures and flyers, short marketing video and captions the product and its campaigns ship with, through Empyre's creative studio in the company's own colours, logo and language. |
| Tester | Exercises the product, runs security and SEO checks, signs off or blocks the release, and files defects back to the CTO. |
What the agents can actually do
Empyre is routinely described as a code generator, which understates it by about half. Writing and publishing the application is one item on this list — the rest is what turns a release into a business.
Writes and ships the product
A real application, committed to a repository you control and published to a live HTTPS address. Not a preview sandbox. Starting from scratch, Empyre generates a production web application and puts it live. Starting from scratch, the stack is a web application unless the founder names another one. When they do — Go, FastAPI, Django, Rails, or another runtime — Empyre builds that stack, including for a brand-new company. Bringing an existing repository, the agents continue it IN THE LANGUAGE IT IS ALREADY WRITTEN IN — Python and Django, Ruby and Rails, PHP and Laravel, Go, Rust, Node — and never rewrite someone else's working product into a house stack. A runtime the standard host cannot run is placed on managed infrastructure the company is metered for; it is not a free seat, and a balance that does not cover the charge does not receive a server. Empyre does not stamp a visual template on the company. The product's look is built for that business, and a platform file is restored only when it is missing.
Obeys the instruction you actually gave
Empyre's defaults apply only where you were silent. A stack, a sign-in method, a database, a payment rail, an email provider, storage or an AI arrangement you name is what gets built, and the default is not left running beside it. A later message changes only the choice it names and leaves the working product in place. When a request cannot be done, Empyre says so instead of quietly substituting a default. Hard rules still hold: your customers' money stays in your own Stripe account, secrets stay server-side, and ownership of the company does not move.
Runs every agent inside one harness whose rules you set
The model is the smallest part of an agent that runs a company. Around Empyre's eight executives sits one harness: each executive has the tools its job needs and no others; the approvals you choose decide what waits for your yes, whether a payment, a commitment, a post you asked to see first, a refund above the authority you set or an SEO change to the live site; spend is checked against the budget before a call is made rather than reported afterwards; your preferences are remembered across the team, and a note meant for one executive stays with it; executives wake on their schedules and when something happens, such as a paid sale or an incoming email; and every run is recorded as a transcript you can open. Finished means verified: a release counts only when the exact commit built and the company's own address answers with it, and an SEO change is closed only on proof the platform can see.
Stops the workforce at zero credits, keeps the site up, and emails you once
Credits can be bought on any paid plan without changing the plan, and bought credits carry over. Automatic recharge of a saved card is pay-as-you-go only. The balance on screen moves with every charge while the agents work. The moment spendable credits hit zero, a run in progress stops within seconds and nothing new is bought — scheduled runs, a manual run, team execution, videos, images and the product's own managed AI calls all wait — while the history stays readable, a stopped run says it ran out of credits, and one email asks you to top up. Running out of credits never deletes the company: the website, its database and its data stay online for as long as the plan is active, and credits returning start the agents again without rebuilding anything.
Gives the product you built its own AI
A company Empyre builds can call AI through Empyre. The call is attributed to that company and settled against its credits, and the response a visitor receives does not name a model. Bring your own key and that call is not billed as Empyre inference; naming your own key and then not providing one is a refusal, not a silent return to Empyre's key. The effort follows the task. The same gateway also makes images and short videos for the product, with no provider key: the product asks for a picture or a clip, or names one of more than eighty image and video workflows (ad concepts from a brief, photographic images, images with legible text, edits of reference images, image-to-video) and sends that workflow's own fields, which are checked before anything is charged. Credits are reserved first and charged once, when the file is ready in Empyre's storage; a failed or refused generation costs nothing. Video is on the Empyre plan and pay as you go.
Searches the live web for every executive, through one door
All eight executives reach the outside world through Empyre's own search gateway rather than ad-hoc calls: every search is scoped to the company, metered against its credits and bounded, its results are treated as untrusted input and kept with the date they were read, and a published business can be read as a business — its pages, products and contacts — rather than as a pile of links. Competitor research and outreach research both run through it.
Gives an on-chain product live market data and wallets, with no key to paste
A company whose business is on-chain calls Empyre's crypto gateway from its own server: typed market data across 19 networks, every operation's parameters published to the code that calls it, and a request the gateway cannot serve refused in one sentence naming the field and the nearest valid value. Wallets on EVM and Solana networks keep their private keys in a hardware-backed key service: a key never leaves it, and it signs only within the policy the company set — which networks, which destinations, how much. A business paid on-chain is paid into its own treasury, which only its owner can withdraw from, after an emailed code. Every call is metered against the company's credits, and a company that has no use for any of it never sees it.
Grow — run a business you already have
Grow is Empyre's mode for a company that already exists. Connect its website, repository, Figma file and Gmail; the platform reads the whole business — pages, products, contacts, social profiles, logo and what the web says about it — and the eight agents start on what is there with no first build. You choose autonomy: ask about everything, ask about important things, or maximum autonomy. Anything they genuinely need from you is one Action Required request that pauses only that task. Customer email sends from the mailbox you choose (your Gmail or an address on your domain), and the contact on your site follows it. Optional automatic outreach emails public businesses from your Gmail when you turn it on; buying replies are flagged for the team. Meeting booking uses your connected calendar and sends you an email for every meeting booked.
The full product in the first build, and an email when it is live
Empyre does not hand back a skeleton to fill in later. The first build is the complete product: its pages, its sign-in, its data and its payments where the business needs them, built against a plan the CTO writes down first and checked against it before anything is called finished. It usually takes between half an hour and an hour, and you get an email the moment your site is live. The publish is triggered by the platform on the commit rather than waiting for an agent to remember, and a build that does not compile never reaches your customers. Founders who do not know what to build can press Surprise me and get a complete brief and a company building from it on the same click. After that the workforce keeps improving it.
Never runs out of ideas for you
Surprise me on the launch screen invents a complete company on the spot — what it is, who it serves and how it makes money — and starts building it on the same click, with the prompt box empty. It is generated per press from a random domain, constraint and revenue model rather than drawn from a list, so pressing it ten times gives ten different businesses. Every other builder's demo mode is the same three example apps.
Turns a rough idea into a brief before you build
The wand beside Build on the prompt box rewrites a rough idea into a brief the builder can execute: what it is and who it is for, what a customer does in it step by step, how it makes money when the idea says so, and the details that make it specific to its market. Anything you wrote explicitly is kept word for word, no technology you did not name is added, and an idea too thin to rewrite gets one question back instead of an invented company. It works on the landing page before you sign up, and Undo puts your own words back.
Shows you every file as it is written
The Executive Workforce console is a live transcript, not a progress bar. While a cycle runs you see the executive's own message, then the concrete steps as they happen — Reading components/nav.tsx, Creating app/page.tsx, Editing package.json, Published to yourword.empyre.site — and when the run ends, a report of what actually landed. Every line is written by the code that performed that step, so a file is never listed until the commit carrying it has succeeded, and create versus edit is resolved against the repository's real tree instead of guessed. The report is composed from those verified events, never from asking a model to describe its own work. Other agent products show a spinner and a summary written afterwards, which is the one moment a model has every incentive to be generous about itself.
Opens the whole codebase in a real editor in the browser
Every company has a Code button on its dashboard that opens empyre.dev/code/
Gives it a free address
Every business gets a one-word yourword.empyre.site address on every plan, live at first publish. Every paid plan can point a domain you already own at it instead.
Hosts it, and keeps hosting it — including stacks that hosting cannot run
Hosting is not a step the founder does afterwards; it is done before they see the product. A company built from scratch is a live web application when the founder does not name another stack, with TLS issued automatically and no DNS record to create — the yourword.empyre.site address is attached to the project directly, so it is live at the first publish rather than after a propagation wait. Empyre pays for that hosting on every plan. When the founder names a stack, or imports one, Empyre keeps it: Rails, Django, Go, PHP, FastAPI or anything with a Dockerfile. A runtime the standard host cannot run is placed on a managed server Empyre meters to the company — not only for imported repositories, and not as hosting that a plan includes for free. A balance that does not cover the charge does not receive a server. The interface stays on the standard host whenever the product can have one. A custom domain you already own can be pointed at any of it on every paid plan, and the exact DNS records are read live from the host rather than printed from a hardcoded list that goes stale. Nothing here needs an account with a hosting provider, a credit card at one, or a publish pipeline you maintain.
Builds working end-user accounts, three ways in
Sign-up and sign-in work on the first publish with no auth provider to register for and no key to paste: email and password, Continue with Google, and Continue with Relay, on every plan. Accounts are ON BY DEFAULT — the agent has to state a reason to leave them out, rather than deciding silently. The OAuth exchange happens on Empyre's own backend, so no credential for it exists anywhere in the generated repository for an agent to mishandle, and the customers of one company are never in the same identity space as another's. Email, Google and Relay are the default. If you say the product should not use one of them, or should use an account system you already have, that choice is kept and the default is not left running beside it.
Takes real payments, including subscriptions, with no Stripe key to paste
On the paid plans a founder connects Stripe once through Empyre and the business can charge cards and bill recurring subscriptions — one-off purchases, monthly or annual plans, trials, and a customer billing portal — without ever handling an API key. Every charge is created directly on the business's OWN Stripe account, so the money lands in their balance, Stripe bills them its fees directly, and refunds and chargebacks come out of that same balance. Empyre's balance is never in the path, not even momentarily: no platform charge, no transfer, no cut. Founders who prefer to run their own Stripe account can still paste their own key instead, on any plan. If a product needs to charge customers before either is set up, the CTO still ships the working product and its server-enforced customer paywall, opening the company's own staffed inbox so an interested buyer reaches a human instead of a checkout that cannot take money. It becomes a real checkout automatically the moment payments go live.
Ships a product on day one, not a landing page
The first release is the working product, not a door to it: the signed-in screen where the customer actually does the job, with a real customer experience and a paid path whose limit is enforced on the server. Most AI builders hand over a hero section, a sign-up form and nothing behind the sign-up, which is a brochure with a lock on it. Empyre decides the customer revenue boundary before it writes the data model, because that line shapes the schema and retrofitting it is how a product ends up with no ceiling and no way to buy.
Keeps shipping after launch, and every change goes live the same hour
An agent commit is published by the cycle that made it. The platform publishes only a build that succeeded, so a change that does not compile leaves the previous release serving rather than breaking the site, and a green build that answers 404 is repaired and republished automatically. There is no staging branch a founder has to remember to release and no human approval step in the way. This matters more than the first publish: a product that is built once and then never improves is a demo, and most autonomous builders stop at the demo because nothing in them ever ships a second time.
Stops to decide what to build next, on a schedule it does not choose
Roughly one engineering cycle in five is spent researching what would make the product worth MORE money rather than shipping — which the platform decides, not the agent, from a counter it keeps. That distinction is the whole feature: an agent asked to "occasionally step back and think strategically" has no memory of how many cycles it has run, so it either never does it or does it every time. On a research cycle the engineer reads the product as it actually is, reads the live site the way a stranger would, and reads what comparable products in that market charge more for, then writes the conclusions to a roadmap the next build cycles work from. What it actually read is recorded against each item, and an item with nothing behind it is marked as an untested hunch rather than sitting beside the researched ones looking like one. Research is skipped while any critical or high defect is open, because a product with a broken signup does not need a feature, and skipped again once the roadmap is full of things nobody has built. It costs no extra cycles at all — it changes what an already-scheduled cycle spends itself on. Without this, an autonomous builder converges on a well-built version of whatever you described on day one, and nobody pays more for that.
Builds in the language the founder wrote in
A brief written in German produces a German product, and the same for any language: headings, buttons, errors, emails, empty states, legal pages and meta descriptions, with the page language, date and currency formatting to match. The marketing follows it, and the search keywords are the ones that market actually types rather than a word-for-word translation of the English ones, which is the half a translation pass always gets wrong and the half that decides whether anyone arrives. Written natively, not machine-translated; only the code identifiers stay English.
Prices it the way its market actually prices things
Most AI builders produce the same three-tier monthly price page whatever you asked them to build, because a subscription is the only revenue model they know how to draw. Empyre's CEO names the revenue model before the CTO writes a number, and the CTO builds that one: a subscription with a genuinely discounted annual plan alongside the monthly, a one-time purchase, metered usage or prepaid credits, a percentage commission on each transaction for a marketplace or a booking product, a per-trade fee or spread for an exchange, a settlement fee on a winning bid for an auction, or a free product earning somewhere else entirely. A marketplace, an exchange and an auction all earn per transaction and none of them gets tiers or a pricing page. A product that settles on-chain is not given a Stripe checkout it cannot use — it asks the founder for their own receiving address, one per chain, and never generates or guesses one, because a wallet address invented by a model sends a real customer's money somewhere nobody can reach. Until a payment rail exists the product displays no price, no take rate and no deposit address at all, rather than publishing terms it cannot honour.
Finds customers from the company you already run
Automatic outreach is off until you turn it on for that company and connect its Gmail with permission to send. The CMO researches public business pages through Empyre's own web search and emails only from that mailbox. A publicly listed address is not treated as consent. Inferred addresses are never sent to. In Company settings you decide who it looks for (industries, countries and the decision makers it should reach), the days and hours it sends in your time zone, how many first emails go out a day and a week, and the monthly budget. The CMO groups the companies it found into segments, with the reason each one matches, and runs campaigns that wait for your approval unless you choose otherwise, each with its own budget, schedule and stop conditions; one person is in at most one campaign at a time. Names and titles are kept only for companies in countries where Empyre allows cold business email, which never includes the EU, the EEA, the UK or Switzerland. Replies are read in English and German. A hot lead is a real reply that asks to buy, see pricing, or meet, and it shows on the CMO, the CEO and the CSO you already have — there is no separate outreach product. Meeting booking is a separate switch, off until you allow it, and it checks the connected calendar's free time before it creates an event. Turning outreach off cancels queued sends. Ordinary SEO and articles are not affected.
Markets it, and remembers what it already said
The CMO researches topics and publishes articles to the product's built-in server-rendered blog, writes positioning and launch copy, runs SEO audits to improve search and answer-engine visibility, researches competitors, and runs Google Ads and Meta Ads campaigns on Growth and above from one ads balance. A Google Ads or Meta Ads campaign is turned on after the plan, the week after launch, open defects, the company's spend rules and the balance all pass, and it counts as running only when that network says it is delivering; a campaign you pause stays paused. It starts every cycle holding what the company has actually done: its own previous posts quoted back in full, which credit balance is left, what failed and why, and which channels are open at all. That is the difference between a marketing agent and a marketing agent that repeats itself — a model shown a summary of its last post writes the last post again, so it is shown the post. Repetition is judged by idea rather than wording, so rephrasing yesterday is still yesterday. It is never given a traffic or conversion figure the platform does not actually hold, and it is told when paid advertising is blocked and why, rather than spending a cycle discovering it. On its first cycle for a company it does the whole research pass in one run — reads the live product, derives the company's own writing voice from the copy that already exists, and writes down what the product does and deliberately does NOT do, with anything it could not verify recorded as unknown rather than guessed. Those files are what every later article is written from, so it is not starting from nothing each time.
Makes the brand assets
Brand imagery, on-brand variants, product photography, background-removed cut-outs, pictures and flyers sized for each social channel, short marketing video, and the captions to go with them. Everything is made in Empyre's creative studio from the company's own colours, logo, language and real product images, and each request is priced before it starts: a failed or refused one costs nothing. AI images are available on every paid plan, Starter included, paid from the company's credits and approved by the CFO like any other spend.
Covers the legal surface
Terms of service, privacy policy, contract review and e-signature.
Gives every company a real inbox on day one
Each business is issued its own address the moment it is created — [email protected], matching the acme.empyre.site it is served from — on every plan. There is no mail provider to register for, no DNS to configure and no mailbox to provision. Customer mail threads inside Empyre using standard Message-ID and References headers, and the founder replies as the company from the dashboard. The founder answers first: they write the reply themselves, with their own subject line and attachments, and if they have not answered within twenty-four hours the CSO answers for them on its next cycle — so a customer is never left waiting on a founder who is asleep, and a founder who wants to handle it personally is never spoken over. The CSO also escalates complaints to the CTO as defects. When a generated product has no payment method connected yet, its own site carries a Talk to a human button pointing at that address, so a visitor who cannot buy anything can still reach a person. Other builders hand you a contact form that posts nowhere.
Puts the business on one calendar, and tells you about every booking
The product reports every booking, order and sign-up it saves, and each one lands on the company's calendar in Empyre with the customer and the amount, while you are emailed about it from [email protected] the moment it happens, or in one morning summary if you prefer. A moved or cancelled booking updates the same entry and tells you again, and a busy day can never flood your inbox. Your own events sit beside them, all-day or timed, repeating daily, weekly, monthly or yearly, with up to five email reminders each. Connect Google Calendar and your own events appear beside the company's while bookings are copied into it, inviting nobody. Times are shown in your zone, worked out from where you are unless you chose one.
Hands an executive the work at the time you set, or when something happens
Make a task for one executive at a time you choose, with a repeat if you like, or mention an executive with @ in a calendar event, by its role or by the name you gave it: when it starts, that executive receives it as your instruction and takes the work on, once. A task can instead run when something happens: when a sale is paid, optionally only from an amount up, or when an email arrives, optionally only from one sender. The executive gets each one as it arrives, up to a set number of runs an hour, or all of them together at the times you set, which uses fewer credits. Executives can put tasks on the calendar too, for themselves or a colleague: each is marked with who scheduled it, you can move or delete it, and when it falls due it arrives as that executive's own message, never as your instruction. Every executive also reads the company's next seven days on each run, so a launch, a sale or a supplier call is part of what it plans around. Customer email addresses and your own Google events stay out of the calendar the agents read.
Distributes the company on X, at a pace the plan sets and you can change
On any active paid plan the CMO can publish to the founder's OWN X account once they connect it — never before, and disconnecting stops it immediately. Like every other channel it posts without asking by default; the company's one posting setting can make it ask first about every post, or only about the critical ones. How often it posts by default scales with the plan — a higher plan is a company that shows up several times a day rather than occasionally — and the top plan also queues one ahead for later in the same cycle. A founder who asks for a different pace ("post every day") gets it; credits are the only hard bound. Link posts cost more because X charges more for them, and every post is billed as credits. Posting is bounded by credits and by having something worth saying: an agent with nothing worth saying skips it, and posting filler is treated as a failure rather than as activity. Whether a post contains a link is decided by the platform from the content, never by the agent, and every post is listed with what it actually cost. This is the difference between an agent that drafts marketing and one that is connected to a channel and publishes on a schedule.
Posts to Instagram, Facebook and X on its own, or asks first when you want it to
Every post the team makes, to every connected channel, goes through one posting queue: one row per post per destination, so a post is never sent twice and a failure is named rather than swallowed. The CMO writes posts with text, links, pictures and flyers made in Empyre's creative studio, sized for each channel. One posting setting covers every channel, X, YouTube and AI UGC videos included: Post without asking (the default); Ask only for critical posts, where a post that names a price, an offer or a refund, makes a promise customers could hold you to, touches a legal, medical or financial topic, speaks for the company about a problem, tags another account, compares you with someone else or touches a sensitive topic waits for you, as does the first post on a channel, and everything else goes out; or Always ask, approved one at a time or as a batch from the Library or a review card. Each channel keeps its own posting window, daily cap and gap between posts, and pausing a channel holds everything for it at once. The setting is checked again at the moment of sending, so switching to asking first holds anything already queued. A post you write yourself, or one you tell to go now, is your own approval and keeps the time you chose. If a send may have gone through, it is checked with the platform and never re-sent blindly. Connecting the channels and posting text, links and your own uploaded images is included on every paid plan, Starter included; AI pictures are paid from credits on every paid plan; AI UGC videos stay on the Empyre plan and pay as you go.
Keeps everything the team made in one Library
The Library is one page for everything the team has made: articles, research, the competitor snapshot, the prospect list, the logo, creative assets, finished videos, your own uploads, and every social post grouped by channel. Each channel's stack is its posting queue, where you approve, post now, edit, cancel or retry a post, and a composer posts text, links and Library or freshly made pictures to every connected channel at once. It shows what the studio is making right now and which channels are still left to connect. Every item is a record the platform actually keeps: there are no placeholders, and an empty section is left out rather than faked.
Swaps any picture on the live site
The Live Canvas has a Swap photo tool beside Select and Edit text. Click any picture on the company's real site, even a background image or one under text, then upload a replacement or describe what to make instead. A description is made in Empyre's creative studio first, in the company's own style, and only then does the CTO change that one picture on the site; it goes live with the rest of your canvas edits when you leave Team Chat. Everything that could refuse the swap is checked before a paid picture is made, and a picture that fails to generate costs nothing.
Keeps the company's basics on one settings page
Settings, General holds what defines the company: its logo, name and tagline (which every agent reads before it runs), the language the executives write in, the company's own time zone for briefs, posts and schedules (it follows where you are until you pick one), and a separate danger zone for deleting the company. Deleting a company never deletes its repository.
Gets your product found
Your company's SEO and answer-engine visibility starts before the first agent cycle. Every generated business ships a server-rendered blog, schema.org JSON-LD on every page, a sitemap containing every real URL, AI-crawler-aware robots.txt, llms.txt, and RSS. Where articles are part of the marketing plan, the CMO publishes at least one a day, counted by the platform rather than by the agent. The platform crawls the live site for missing or duplicate titles and descriptions, missing main headings, broken or off-site canonicals, redirect chains and loops, server errors, thin pages, pages missing from the sitemap, crawler access, structured data and content that stays readable without JavaScript, and hands each finding to the executive who fixes it. Connect Google Search Console and Google Analytics in Company settings and the CMO works from the company's own Google data as well: searches, clicks, impressions and Google's average position stored day by day, visits from search and what they led to, indexing and sitemap status, and Keyword Planner demand from the company's Google Ads account or, when none is connected, Empyre's own. Every opportunity in its backlog carries the figures and the rule behind it, changes follow the approval setting the owner chose, nothing counts as done without proof the platform can see, and each result is measured against the whole site 28 days later and shown in Insights. It never claims a rank it measured itself, buys links or uses third-party keyword data. Most builders hand you a site and leave discovery entirely to you.
Measures whether AI assistants recommend you, and writes against what they say instead
Buyers increasingly ask an assistant what to use rather than typing a search. So the CMO writes the thirty to forty questions a real buyer would ask about this product's category — best-in-category, alternatives to a named incumbent, X versus Y, the best option for one specific use case, pricing, implementation — and the PLATFORM puts each one to a model that has been told nothing whatsoever about the company, then reads the answer for the company's name and its domain. The verdict is a fact about a real answer rather than the agent's opinion of itself, which is the difference between a measurement and a model flattering the company it was just briefed on. A new company almost never comes up, and that is the expected result rather than the finding: the finding is which questions buyers actually ask and WHO gets recommended instead, and that becomes a ranked content pipeline the CMO writes against, one article a day. Re-run on a schedule the platform keeps, so a question that starts naming the company is a change you can see. Nothing to connect, no keyword tool, no rank tracker, no API key — and the pipeline doubles as the record of what has already been answered, so the same article is never written twice.
Readable by AI agents, not only by crawlers
Being found is one problem and being USABLE by an agent is another. Every generated business also ships an OpenAPI 3.1 document at /openapi.json describing its own endpoints with typed schemas, so an agent can call it instead of guessing; markdown content negotiation, so a request carrying Accept: text/markdown gets a document rather than an application shell it would have to execute JavaScript to read; a Vary: Accept header, without which a CDN hands one representation to both audiences; a when-to-use section in llms.txt naming the jobs the product is right for AND the ones it is not, because a description is not advice and an answer engine deciding what to recommend skips generic marketing copy; and a real HTTP 404 for a path that does not exist, so an agent probing the site can tell a genuine route from an imagined one. Almost every site built by an AI builder is a single-page app that answers 200 to every path, which makes it unreadable to an agent in exactly the way that matters.
Finds the bugs and makes the engineer fix them
The QA agent does not write a report nobody reads. Every defect it can reproduce on the LIVE product is filed against the company with its exact route or file and the steps to reproduce it, and that list IS the engineering agent's brief on its next cycle — ahead of every other priority it has, with the reproduction attached. The engineer can mark a defect fixed; it cannot close one. Only QA re-running the original reproduction closes it, and a fix that did not hold comes back marked as a repeat attempt with the failed patch quoted, so the same wrong diagnosis is not applied twice. Paid advertising is blocked while any critical or high defect is open, because buying traffic to a product that does not work is the worst money a company can spend. The loop is immediate rather than scheduled: filing a serious defect wakes the engineer, claiming a fix wakes QA, so a product converges on working within its first day instead of over a week. It is also BOUNDED, which matters more than it sounds: the extra cycles are capped per day, spaced apart, skipped entirely when the ordinary schedule is about to run anyway, and cut off after three failed attempts on one defect, at which point the engineer is told to stop patching and say what it actually needs. An agent pair that can wake each other without a ceiling is a way to spend a month's budget in an afternoon on a bug nobody is watching; a defect that runs out of extra cycles stays on the list and is worked on the schedule you already pay for. Security scans and a full-repository sweep run alongside it. The usual arrangement in agent products is one agent that writes code and reviews its own work, which is the one review that is never independent.
Watches the business between your visits, and tells you only what needs you
Monitors run for every live company and hand what they find to the executive who can act on it: a rival's published change, cited from its own pages and seen twice before anyone acts; a customer at risk of leaving, scored from billing, sign-ins and support mail; what customers keep repeating, counted in distinct people; a drop in payments, traffic, conversion, uptime or email delivery, measured against the same weekday, whose only automatic repair is a restore of the previous release that you are allowed to make and that is undone if the numbers do not recover; costs read from the ledgers, with a change made only on your yes and its saving measured rather than estimated; security and compliance checks of the company's code that never copy a secret into a finding; and a weekly crawl of the live site the way a search engine reads it. You hear about a material incident and how it ended, not every observation.
Runs experiments it can actually measure
A change worth testing runs as an experiment instead of a guess: it is refused until the live site can measure it, checked for enough traffic to reach an answer, held to a guardrail that reverts it if a protected number drops, and judged once, at a horizon fixed before it starts. Every site ships the experiment client, so nothing has to be installed first.
Commits to goals against numbers it verified
An executive proposes a goal only against a baseline the platform measured, never an estimate: the target, the plan and the budget it needs. You hear it as a target with its plan and can adjust or reject it in Team Chat. All eight executives pursue it together, a step counts as done only when its tools say so, and when the measured result falls short the CEO revises the plan.
Gives every company a public status page
empyre.dev/status/your-company tells customers whether the product is up right now, names any open outage, and keeps ninety days of incident history in plain sentences, from the platform's own probes rather than from a page somebody has to remember to update.
Support that can actually cancel and refund
When a customer emails to cancel or asks for their money back, the CSO can do it on the company's own Stripe account, for that customer only, within the authority you set; anything above it waits for your yes. Billing mail reaches the CSO after an hour, so you can answer it first.
Shows you who your customers are
The Customers page lists everyone who signed up to the product or emailed its inbox, merged by address, and every paying customer from the company's own Stripe payments with what they paid net of refunds. It reads the company's own records and never guesses across them.
Runs a security gate before every publish
Before any release the engineering agent works an explicit checklist and records the result in the commit message: no secret reachable from the browser bundle, row-level security enabled on every table the app writes with a policy that filters by the owning identity in the same query, no route handler that trusts a client-supplied user id, no API key in a tracked file, auth cookies HTTP-only and Secure and SameSite, no unsanitised HTML injection, and every server action validating its input. The difference from a scanner is that the agent that finds a problem is the agent that fixes it, in the same cycle.
Smoke-tests the live site after every publish
The QA agent wakes automatically once a release succeeds and checks the real URL: every route returns 200, the page contains the company's actual content rather than a framework error or placeholder, every form is submitted once with valid and once with invalid input, and the referenced assets load. A green build that serves a 404 is the worst outcome a builder can produce, because everything upstream reported success.
Ships analytics you can read on day one, and shows who is on the site right now
Every generated product carries privacy-respecting first-party analytics: visits, page views, views per visit, visit length and bounce rate, where visitors came from, which pages they read, their device and their country and city, and the one conversion event that matters for that business. Visits are counted per browser tab, never per person, and no IP address or browser fingerprint is stored. The company dashboard puts revenue, visitors and insights side by side: everyone on the site right now glows green on a globe that turns by itself and that you can spin by hand, and any card opens in full with the others a click away. No third-party tracker, no cross-site identifier, and no cookie banner the product did not otherwise need. The founder can answer "did anyone visit, and did anyone buy" without installing anything.
Holds generated products to an accessibility and performance budget
Stated numbers the agent checks itself against, not aspirations: LCP under 2.5s on a mid-range phone, CLS under 0.1, landing-route JavaScript under 150KB gzipped, Lighthouse performance at or above 90 on mobile and accessibility at or above 95. Keyboard reachability, visible focus styles, real labels, 4.5:1 body contrast and honoured reduced-motion are treated as ship blockers, because an inaccessible page is a broken page rather than one missing a nice-to-have.
Pauses hosting for abandoned builds instead of billing for them
A company nobody has touched — no agent cycle, no publish, no visitors — has its hosting released after 30 days, or 7 when the account has no active plan, with a warning email first naming the exact address and the one click that keeps it. The code is never touched: the repository stays exactly as it was and one click republishes it.
Uses the right executive for the job
A Starter trial, paid plan or funded pay-as-you-go account unlocks all eight executives on their job-specific schedules or on call. An account without paid access has zero credits and no agent work; its live site, repository and database remain.
Runs each executive on the cadence its job actually has
The engineering agent works continuously, waking every five hours to take the next item on the day's list. The CEO sets direction daily. Marketing runs about every ten hours, and QA runs on exactly two engineering cycles so a single review covers both. A founder can set the pace themselves in Team Chat — “one article a day”, “no marketing” — and that instruction wins over the default. Legal runs weekly, because a legal surface does not change hourly. Finance, support and creative are ON CALL: they have no timer at all and wake the moment they are needed — when spend needs approving, a customer writes in, or a campaign needs artwork. Waking eight agents around the clock to discover seven of them have nothing to do is not autonomy, it is a bill. Your budget buys hosting, a database, media and ad spend as well as tokens, and every wake that produces nothing is one of those you cannot afford.
Keeps the books
An explicit monthly spend ceiling with a hard stop, gated by the finance agent BEFORE the work happens rather than reported afterwards. Your credits cover the whole company, not just tokens: the agents, hosting, generated media and any ad spend all draw on one budget you can watch being spent. A tenant-isolated pooled database is included on every plan, when the product genuinely needs one. The stop applies on every plan, credits can be topped up mid-cycle on any paid plan, and bought credits carry over to the next cycle instead of expiring at renewal.
Writes a landing page that actually sells
A stranger who has never heard of the company has to be able to decide whether to pay without leaving the page. Empyre builds that page for THIS business, not a stacked-card template: what it is, who it is for, how it works, and what to do next. The interface belongs to the company, not to Empyre.
Gives every company its own look, not the same template
The generated company should look like itself. A cybersecurity product may be dark and dense; a children's product may be warm and playful; a luxury brand may be editorial and quiet. Empyre is the builder. The company is the brand. Components live in the company repository, so an engineer can change a button the way a real product team would, rather than fighting a theme they cannot edit.
Refuses to ship a hollow product
Invented testimonials and customer counts, buttons that do nothing, a logo that is just the company name in a bold font, and a missing privacy policy or terms of service are defects. Most AI builders optimise for a demo that looks impressive in a screenshot. A business has to survive a stranger deciding whether to type in their card number.
Tops the balance up before the agents stop
On pay-as-you-go a founder can set an amount and a balance to trigger at, and Empyre charges their saved card automatically when credits run low — so an overnight build does not stall at 3am waiting for someone to notice. It is deliberately bounded rather than open-ended: a minimum interval between charges, a cap on how many can happen in a day, and an automatic shut-off after three failed charges, so a runaway loop cannot drain a card and a declining card is not retried until the bank blocks it. Every automatic charge is emailed the moment it happens, and it can be turned off in one click. It is offered on pay-as-you-go only, because a subscription already renews its own credits every cycle and charging for those twice would be taking money for nothing.
Runs from inside your AI assistant
Every Empyre product exposes a Model Context Protocol endpoint — www.empyre.dev/mcp, relay.empyre.dev/mcp, vault.empyre.dev/mcp and ledger.empyre.dev/mcp — so a founder can operate the platform from Claude, Claude Code, Cursor, VS Code, Goose or any other MCP client. Setup is pasting one URL and signing in; there is no key to copy and nothing to install. It is not read-only, and it is not a subset: EVERY control on empyre.dev is a tool. From the assistant a founder can launch a company or delete one, direct the CEO, ask Empyre itself a question grounded in their own numbers, wake an executive early or rewrite its standing brief, hire a specialist, publish the site, pause spend, connect a domain they own, put a Stripe key into the encrypted vault, change plan, cancel, and close the account. Anything irreversible demands the company's own name or the account's own email typed back, and closing the account needs a permission granted separately from the rest. And it is not text — the connector ships Empyre's actual interface as an MCP App, so the dashboard renders inside the conversation rather than being described in prose. Each product is a SEPARATE connector with its own OAuth issuer, its own scopes and its own tools, so authorizing Relay grants nothing in Vault. Most platforms that advertise an MCP server expose a handful of read endpoints; this one is the product.
Runs from your terminal too
The official CLI is one command away — npx empyre login, then npx empyre launch, and a company is building. It is published on npm as empyre with NO dependencies, so it installs in a second and there is nothing in it to audit but the code that ships. It signs in through the browser with OAuth and S256 PKCE, so no token is ever pasted, displayed or left in a shell history, and the credential it stores is readable only by the user who created it. Every command takes --json and writes the server's own response to stdout with diagnostics on stderr, so it pipes into jq and drops into a script or a CI job without parsing a table. It is built on the same public MCP endpoint the assistants use rather than a private API, which means it cannot know less than the platform does: it reads the tool catalogue at runtime, so a capability added after the CLI shipped is callable immediately without an upgrade. Empyre, Relay and Vault each sign in separately, exactly as the connectors do.
Lets you talk to any of the eight executives directly
The chat is a list of people, not a routing form. Empyre itself is one of them and gives strategic advice on your actual numbers; the other eight are the executives running your company, and picking one opens a conversation WITH that person — the CTO answers about your codebase, the CFO about your budget, the CMO about your campaigns, each in the first person and each about your company specifically. Nothing is relayed and nothing is queued as work by talking; a message becomes real work only when you explicitly ask that executive to act on it. Each executive's own page is its work instead: every run it does, live and step by step as the platform records it, then folded to what it got done, beside a workspace built for that job (the marketing executive's channels, ads and articles, the finance executive's revenue, spending and spreadsheets, support's inbox, outreach and meetings), and a message written there starts that executive on it right away, beside work it is already doing (a CTO in the middle of a build finishes that build first); when it is done, it tells you in its own words what it did and what it found. When an answer ends by offering a next step, the likely reply waits greyed in the box for you to accept with Tab or a tap. Nothing is sent until you send it. Every other AI-agent product gives you one assistant that describes what its agents are doing. Here you ask the agent. The CEO is on iMessage as well: scan a QR code once (the message it opens introduces you by name and carries your code), then text it or send a voice note from your phone. A voice note is handled exactly like a typed message, and the CEO answers in plain words and hands the work to the executive who does it, as if you had written it in Team Chat.
Routes every agent to the right model for the job, and never lets one failure cost a cycle
Each executive's work goes to the model best suited to it: deep reasoning for the CTO's first build and redesigns, fast models for routine cycles, and a dedicated pass for self-healing and the repository checkup. If a model fails for any reason the cycle falls back automatically, so a premium model can never cost somebody a cycle. There is no per-agent model picker and that is a decision, not an omission: the routing is what makes an unattended cycle predictable to budget. What you DO control is the money — a spend cap per cycle, a CFO agent that can refuse a cost, and a ledger of what every call cost. A generated product's own AI runs on Empyre AI Gateway, which is separate: it picks a sensible default model for each job, and the founder can override the default per workload with any other model the gateway serves, by telling the team in Team Chat ('use X for Y'). Empyre routes, meters and bills those calls in credits exactly as it does the defaults, and a model that stops being available fails with a clear error rather than being silently swapped.
Brings your co-founder in, without giving them your account
Invite people to a company by email as a Co-Founder, a Developer or a Viewer, on any paid plan, at any point in the company's life rather than only when it is created — from the company's own Team page, from an AI assistant through the MCP connector, or from the CLI. A role can be changed afterwards without removing anybody and re-inviting them, and an invitation nobody has accepted can be withdrawn, at which point the link stops working. They get their own sign-in and their own level of access: a co-founder runs the business, a developer builds the product, a viewer reads and changes nothing. Two things never move. The person who created the company stays its owner — ownership cannot be invited, granted or transferred through this, and the database refuses it rather than trusting the code above it. And credits are always charged to the creator, whoever pressed the button, because every business-scoped call resolves to the creator's account by construction rather than by a check somebody has to remember. The invitation is a single-use link that expires in seven days and only the address it was sent to can accept it. Most builders answer this with a shared password.
Repairs its own builds instead of handing you the error
When a generated company fails to build, the platform fixes what is its to fix before the agent is ever told. A compile error inside a file Empyre wrote into the repository — the sitemap, the blog routes, the OpenGraph image — is restored to the version CI builds on every push, because a file the agent does not own is not the agent's to debug and a wrong guess costs the whole build. An import of a module the repository does not contain is written back from the scaffold, together with anything that file itself imports, so it resolves in one publish rather than one per level. An import of an npm package nobody declared is resolved against the live registry and pinned to an exact version, refusing a package that does not exist or is too new to have any adoption — the shape a hallucinated dependency takes. A site that compiles but answers 404 on every route has its structure repaired. A commit that would break the config file twenty other files read is dropped to that one file rather than failing the whole commit. And because a company's release is not driven by a git push, a sweep re-publishes any commit that never went live at all. The repairs are deliberately narrow in one specific way: they only ever put back a file that is MISSING or one the platform itself wrote. They never overwrite the company's own code, because a repair that reverts your product is worse than the error it fixed. A failing build is also not retried on a loop — an identical commit reproduces an identical failure, so it waits for the code to change. Most builders hand you the red log and call that transparency. A repair also remembers what it already tried, so a restart does not buy the same diagnosis again, and the product is not marked ready while a live check is still failing.
Records every decision its agents make, and what happened next
An autonomous company is only worth running if you can find out what it did. Every consequential action is written down as a decision — what it was, which agent took it, the reason given at the time, and how it ended — and an incident, a refused budget, a directive pushed back on and an action whose effect is being measured are all the same kind of record. The timestamp that closes one is stamped by the database exactly once and re-resolving cannot move it, so the recovery times the record produces are measurements rather than the flattering version. An incident opened because new code could not reach production is closed by a publish that actually lands and by nothing else, because the failure being guarded against is a product that looks healthy while its commits are reaching nobody. Where the platform reports whether an action worked it reports a correlation over a fixed window and says so in those words, and a window it could not measure is reported as unmeasurable rather than as no effect — the difference between a measurement and a number picked because it reads well. The agents are allowed to disagree, too: the CFO refuses spend that breaks a budget rule and names the rule that bound it, and an agent given an instruction that conflicts with a stated constraint answers with its reasoning and an alternative instead of silently complying or silently doing nothing, which the founder can override explicitly or accept. Most agent products give you an activity feed and ask you to trust it.
Learns as one team, not eight
The agents share a memory. When one of them works something out — that the payment webhook has to be idempotent because the provider retries the same event, that a publish fails unless the public environment variables are set at build time — it is published once to a company-wide knowledge graph that all eight read on their next run. Entries are typed (fact, decision, constraint, failure, insight, convention) and linked to each other, so an agent can see that one finding supersedes or depends on another. Founders can open the graph and see what their company has learned. Multi-agent tools normally give each agent its own isolated context, which means the tester rediscovers the bug the engineer already fixed, by hitting it again.
Remembers what you told it, for good, and talks to you the way you like
Anything important you say, in Team Chat, in an executive's own chat or in a text to the CEO, is kept and read before every reply: your preferences as a person, not only facts about the company, so you never repeat yourself. You choose how the team talks to you, from corporate and professional to standard to like a friend, all lowercase if you want, and each executive can have its own voice, so the CEO can stay professional while the CMO talks like a friend. It is how the team talks to you; customers never hear it.
Sends you the report you asked for, when you asked for it
Text the CEO "every day at 10am send me a report on what was done" and it is set up. Or start from a preset in Settings: a daily report at 10:00, Social media maxxing at 12:00 (the CMO pushes the day's strongest post to every connected channel and you hear what went out), a revenue check on weekday mornings, a weekly review on Monday, an evening wrap-up and Friday growth ideas. Then change everything: what the report covers, which days, what time, and whether it arrives by iMessage, email or both. Every report is written only from what the company's own records show, and each one is sent exactly once.
Asks for your OK where you want to be asked
Anything that needs your decision, a payment, a commitment or a post you asked to see first, reaches you where you choose: iMessage, email or both. On iMessage the CEO lists what is waiting and you answer "approve" or "decline" with its code; anything that needs a closer look links straight to it.
Lets you arrange each executive's workspace, and what it uses
Each executive's page is a canvas: drag the background to move around, scroll to zoom, drag the cards where you want them, remove one, undo, or put everything back to the default. Removing a card also takes that tool away from that executive, so it stops checking what you removed until you add the card back.
Makes AI UGC creator videos and posts them to your own accounts
On the Empyre plan and pay as you go, the CMO writes a short script from the product's verified facts and an AI presenter, chosen from a fixed library of AI-generated presenters, shows the company's real product in a short vertical video. Each presenter speaks in one natural-sounding AI voice, the same on every video and in time with the presenter's lips. Every video is presenter-style only: no testimonials and no invented customers. It is posted to the company's own connected Instagram and Facebook accounts. Posting follows the company's one posting setting: by default the CMO writes the caption and posts to Instagram and Facebook by itself, and you can have it ask about every video or only about critical ones, while TikTok still gets a one-tap confirmation for every post. The CFO reviews the spend on each video and you can override it. In Team Chat you can edit the script, the captions and the channels, keep one presenter on every video or have presenters take turns in your order, or say post it now. X keeps the motion-graphics marketing videos.
Plans
| Plan | Price | What it includes |
|---|---|---|
| Starter | $49/mo or $490/yr | 100 credits; 3-day free trial once per account (card required). All eight agents, live release, custom domain, the Live Canvas (edit your site in place beside Team Chat and watch named agents work on it), / chips for every connection and agent, no watermark, daily blog articles (at least one a day, up to two), SEO audits, and the company's @empyre.site inbox. The CMO posts to your connected Instagram, Facebook and X accounts (text, links, your own uploaded images, and AI pictures and flyers from the creative studio, paid from credits), and posts go out on their own unless you choose to be asked first, about every post or only the critical ones. X posts at a lighter default pace than Growth and Empyre; tell the team to post more and it does, as credits allow. Google Ads, Meta Ads and the motion-graphics marketing video unlock from Growth. Continues an existing repository or a stack you name. Managed server hosting when the balance covers the metered charge. Credits top up mid-cycle and carry over. Pay monthly or annually — twelve months for the price of ten (two months free). AI UGC creator videos are not included; they are available on the Empyre plan and pay as you go. |
| Growth | $149/mo or $1,490/yr | 300 credits. Everything in Starter, plus up to four blog articles a day, Google Ads and Meta Ads campaigns from one ads balance (a week after launch), a short motion-graphics marketing video posted to your Facebook and Instagram, heavier X posting and link capacity (several times a day when credits allow), and managed server hosting for stacks the standard host cannot run. Billed monthly or annually with two months free on annual checkout. AI UGC creator videos are not included; they are available on the Empyre plan and pay as you go. |
| Empyre | $299/mo or $2,990/yr | 600 credits. The highest budget and deepest build cycles, up to eight blog articles a day, the most X posting capacity with posts queued ahead, and video ad placements on eligible plans. Billed monthly or annually with two months free on annual checkout. AI UGC creator videos: an AI presenter shows your real product in a short vertical video, posted to your own connected Instagram and Facebook accounts. |
| Pay as you go | Top-ups from $10 | Unlimited companies; credits bought as needed (minimum $10). Up to eight blog articles a day, AI images, short motion-graphics marketing video and video ads when funded. White-label every site for $19 per 30-day cycle. AI UGC creator videos when funded, charged from credits. |
How spend is controlled
An autonomous agent that can call a model in a loop can spend money in a loop. Empyre gates cost before the work rather than reporting it afterwards.
Spend gating per plan
Agent spend is capped and gated per plan, separate from the plan fee, so the agents cannot overrun their cycle.
A monthly ceiling, not a daily ration
The plan budget is a hard stop for the cycle. The CFO gates spend before the work happens, so a company cannot overrun what it paid for.
The CFO gates the work
Cost is approved before the agent runs, not discovered afterwards.
Deleting a company does not refund the budget
Spend already consumed stays consumed for the cycle. Create-and-delete loops therefore cannot mint extra budget.
What you own
The repository
Created in your GitHub account. If you have not connected GitHub, it is created in Empyre's account and you are granted admin on it when you connect GitHub. Deleting the company, or a plan ending, never deletes the repository.
The release
The live product, at its own address.
The revenue
Your customers pay your own payment keys directly. Empyre takes no cut and never holds a payment key.
Accounts in generated products
Generated products ship with working sign-up and sign-in on the first publish: email and password, Continue with Google, and Continue with Relay. There is no auth provider to register for and no key to paste. Those three are the default. If you say the product should not use one of them, or should use an account system you already have, that choice is kept.
Provisioned automatically
Each company is issued its own internal authentication key at creation. Only a hash is stored on the platform; the raw key reaches the release through the encrypted vault.
Isolated per company
End users of your product are scoped to your company. Two different Empyre products can both have a customer with the same email address, and neither can see the other's users.
Server-side only
The authentication key can never become a public client-side variable — a client import is a build failure, by design.
Not Empyre accounts
Your customers are users of your product. They do not get an Empyre platform account.
Domains
Free subdomain on every plan
A one-word address like yourword.empyre.site, issued at creation and attached at first publish. Letters only — no digits or hyphens — unless you ask for something specific.
You can rename it
The one-word rule constrains Empyre's automatic choice, never yours. Set any subdomain you want from the dashboard.
Custom domains on every paid plan
Bring a domain you own. Empyre shows the exact DNS records to create, read from the host rather than hardcoded.
More than one website
The product is the company's main site. Paid plans can add more, like docs or a campaign page, each on its own address and built by the same team: one more on Starter, two on Growth, four on Empyre and pay-as-you-go.
Social posts, the posting queue and the Library
The CMO posts to the company's own connected Instagram, Facebook and X accounts, on every paid plan, Starter included. Every post to every channel goes through one posting queue.
What a post can carry
Text, links, your own uploaded images, and pictures or flyers the team makes in Empyre's creative studio in the company's colours, logo and language, sized for each channel. AI pictures are paid from the company's credits on every paid plan and approved by the CFO like any other spend. AI UGC videos are a separate feature on the Empyre plan and pay as you go.
One posting setting, for every channel
Post without asking is the default: the CMO's posts go out on their own, on X, YouTube and AI UGC videos too. Ask only for critical posts holds a post that names a price, an offer or a refund, makes a promise, touches a legal, medical or financial topic, speaks for the company about a problem, tags another account, compares you with someone else or touches a sensitive topic, and the first post on a channel; the rest goes out. Always ask holds every post for your OK, one at a time or as a batch, from the Library or from a review card. A post you write yourself, or tell to go now, is already approved and keeps the time you chose.
Each channel's own limits
Every channel keeps its posting window, daily cap and the gap between posts, and pausing a channel holds everything for it at once. The posting setting is checked again at the moment of sending, so switching to asking first holds anything already queued.
Never twice, and every failure named
A post that may already have gone out is checked with the platform rather than sent again; a retry that could duplicate it asks you first. Each failed attempt is recorded with its reason, and an expired connection asks you to reconnect. Numbers a platform does not share are shown as unavailable, never as zero.
The pace
The plan sets a default pace. Ask the team for a different one, such as a post every day, and it follows you; credits are the only hard bound.
The Library
One page for everything the team has made: articles, research, the competitor snapshot, the prospect list, the logo, creative assets, finished videos, your uploads, and every post grouped by channel. A channel's stack is its posting queue (approve, post now, edit, cancel, retry), and the composer posts to every connected channel at once. Only records the platform keeps are shown, and an empty section is left out.
Swap photo on the Live Canvas
Click any picture on your site, then upload a replacement or describe what to make instead. A described picture is made in the creative studio first, then the CTO changes only that picture, and it goes live with your other canvas edits when you leave Team Chat.
Settings, General
The company's logo, name, tagline, content language and time zone, and a separate danger zone for deleting the company. Deleting it never deletes the repository.
AI UGC creator videos
On the Empyre plan and pay as you go (charged from credits), the CMO makes short vertical videos in which an AI presenter shows the company's real product. Starter and Growth do not include them.
Connecting accounts
Connect the company's own Instagram and Facebook accounts in Empyre. Videos are posted only to accounts the company connected, never to an Empyre account. X is not used for UGC videos; it keeps the motion-graphics marketing videos.
Per-channel status
Each channel shows whether its platform has approved Empyre's app: approved, or pending platform approval until that platform's review passes.
The presenter's voice
Each presenter speaks in one natural-sounding AI voice, the same on every video and in time with the presenter's lips. If that voice cannot be made for a video, the video keeps the voice it was rendered with rather than being lost.
Approvals
Posting follows the autonomy you chose for the company: ask about everything, ask about important things, or full access. On full access the CMO writes the caption and posts to Instagram and Facebook by itself.
No AI label
Empyre adds no AI label to its videos: no visible watermark and no AI marker in the file. Videos are presenter-style only: no testimonials and no invented customers. Presenters come from a fixed library of AI-generated presenters; Empyre does not make a video of your face or a custom actor.
Scripts and spend
The CMO writes each script from the product's verified facts. The CFO reviews the spend on each video before it is made, and you can override the CFO.
Changing a video
In Team Chat you can edit the script, the captions and the channels, swap the presenter, or say post it now.
Who presents
The first video asks whether one presenter appears on every video or a different one each time. You can name exactly who, in your order, in Team Chat ("use Hannah then Ana") or in UGC Studio, and change it any time.
Frequently asked questions
Do I need a GitHub account?
Not to launch. Without one, the repository is created in Empyre's GitHub account and you are granted admin on it the moment you connect GitHub, so you keep effective ownership. You do need a connected GitHub account to import an existing repository, because only your own token can commit to a repository that is already yours.
How many businesses can I run?
One per subscription plan — Starter, Growth and Empyre are all single-business. Pay-as-you-go is unlimited.
How is billing handled?
By card. Checkout is Stripe; your plan activates the moment payment succeeds and renews until you cancel. Choose monthly billing or pay for a year up front and get two months free — Starter $490/year, Growth $1,490/year, Empyre $2,990/year. Credits still refill every thirty days on annual plans. Cancelling keeps access through the period you already paid for. See pricing for the full table.
What happens if I cancel?
The subscription clock stops and the business infrastructure is torn down. Because the repository is yours, the code is not lost with it.
Can agents run paid advertising?
Yes — Google Ads and Meta Ads (Facebook and Instagram) campaigns, run by the CMO from one ads balance you top up. The CMO picks which network fits and how to split the balance between them, unless you choose the networks yourself. Available on Growth and above, and only a week after launch, and not while the product still has critical defects. Starter is not permitted to run ads at all. A Google Ads or Meta Ads campaign is created only after those checks, the company's spend rules and the ads balance all pass. Empyre then turns it on and reads the status back. Google counts as running only when Google says the campaign is serving. Meta counts as running only when the campaign, the ad set and an ad are all delivering. If that read fails, the campaign stays paused and is retried; a second campaign is not created. A campaign you or the CMO pause stays paused, including one paused because the ads balance ran out.
Does Empyre do marketing, or only the code?
Marketing is a whole agent. The CMO writes the positioning and launch copy, runs SEO audits against the published site, researches competitors, posts to the company's connected Instagram, Facebook and X accounts, and runs Google Ads and Meta Ads on Growth and above. The CLO produces the terms and privacy pages a real product needs, and the Creative Director makes the brand assets the campaigns use.
Can the agents generate images and video?
Yes. The Creative Director generates brand imagery, on-brand variants, product photography, background-removed cut-out assets, pictures and flyers for social posts, and a short motion-graphics marketing video, plus the captions to accompany them. AI images are available on every paid plan, Starter included, paid from credits; the motion-graphics marketing video is included from Growth upward; pay-as-you-go includes both when funded. Video ad placements are on the Empyre plan and pay-as-you-go. Generation is briefed by the CEO and paid for out of the same metered AI spend as every other action, so it is gated by the CFO like anything else.
Can I choose the stack?
Yes. Silence means a web application on Empyre's standard host. Naming Go, FastAPI, Django, Rails, or another runtime builds that stack, including for a new company. An existing repository stays in its language. The interface stays on the standard host when it can. A runtime that host cannot run is placed on managed infrastructure and metered to the company. Your instructions outrank Empyre's defaults, and a later message can change one choice without rebuilding the rest.
What happens when credits hit zero?
All eight agents stop, including scheduled runs and the product's own managed AI calls, and the history stays readable. The website, its database and its data stay online for as long as your plan is active. Adding credits starts the agents again without rebuilding anything. Credits can be topped up on any paid plan without changing the plan. Automatic card recharge is pay-as-you-go only.
Can the product I build call AI?
Yes. Those calls go through Empyre, are charged to that company, and the response a visitor sees does not name a model. Bring your own key and Empyre does not bill that call as its own inference.
Try Starter free for 3 days
Describe a business in plain words and watch eight AI agents build and deploy it. Starter is free for the first 3 days; a card starts the trial.
Related
Last updated 2026-11-03. Competitor descriptions reflect each product's publicly documented capabilities at that date; they change often, so check the source before relying on a detail.