Picture a small board of department heads who check the business every day and never act alone. Each one owns a part of your company and tells you what needs a decision.
An executive is not a chatbot you have to prompt. It has a role, goals, the accounts you let it read, its own memory and a daily review. It works on a schedule, reacts to events from your apps and asks its colleagues for help.
A title is a role, not a legal authority. An AI CFO cannot sign anything, and an AI CHRO never hires or dismisses anyone.
CEODirectionTurns the team's findings into the three decisions you must take this week.
CFOFinanceExplains cash, runway, collections and cost variances from your books.
CMOMarketingRelates channel spend to qualified pipeline and keeps your positioning distinct.
CTOEngineeringTracks delivery and reliability, diagnoses failed runs and proposes bounded repairs.
COOOperationsFinds stalled handoffs and duplicated work, then proposes the workflow that removes them.
CROSalesMoves qualified opportunities forward and keeps the pipeline honest.
Also on call: CPO, CXO, CHRO, CISO, CLO, CDO, CSCO and CQO. A role that sleeps costs nothing.
Every piece of work follows the same path, left to right. Reading is free to happen. Anything that leaves stops at the gate.
Obsidian vault, Notion, Google Drive, Confluence and your website, plus mail, books and CRM through your own connections.
Each one reads with its charter, its own memory and the team's shared knowledge, and cites every passage it uses.
A daily brief, tasks with evidence, drafts and questions to colleagues. None of this needs a card.
Anything that sends, changes or spends stops here as a card in the app, by email, on Telegram or on WhatsApp.
Telegram
WhatsAppThe exact call you approved runs, after grants, budget and the account are checked again.
Every call leaves a receipt. Approve the same thing three times and the executive proposes a precise rule.
Two routines straight from the role templates. The names and numbers below are fictional.
Every plan runs the whole team end to end. The plan sets how far the executives may go. Inside that ceiling you still choose Observe, Prepare or Run within rules.
EXCOM is in limited preview. These ceilings apply as access opens. Your plan's pipeline limits stay as they are. Compare plans and prices
| Plans | Sandbox and Outpost | Forge | Bastion and Citadel |
|---|---|---|---|
| Read assigned sources and accounts | Yes | Yes | Yes |
| Daily brief, tasks with evidence, questions to colleagues | Yes | Yes | Yes |
| Draft messages and documents | No | Inside Melaya | Yes |
| Send, post or change a record | No | No | Your approval or a rule you accepted |
| Spend, delete, deploy, legal and people matters | No | No | Always asks you |
| Run scheduled pipelines | Proposed as a task | Proposed as a task | After a trial and two approvals |
| Change its own permissions | Never | Never | Never |
Yes. EXCOM is the operating layer, not a model subscription. Each executive uses the model you pick: a cloud key, a router, or a CLI agent on your own machine through the Melaya runner.
With Claude Code, Codex or GitHub Copilot behind the runner, your executives think on the subscription you already pay for. The Melaya server still decides every tool call, so a runner model meets exactly the same approval gate as a cloud one. If the runner cannot get an answer, it runs nothing.
GitHub Copilot
Ollama
LM Studio
OpenRouterKeep the runner up to date. An older runner keeps its executives in Observe.
Safety here is not a prompt. It is a check that runs on every tool call, before anything happens.
Setup grants read access only, and every executive's first pass is read-only, whatever autonomy you chose.
Each account is read, draft or write, per executive. A read account never writes, even in Run within rules.
Payments, deletions, deploys, legal and people matters ask you every time. No rule can cover them.
Executives have no tool to widen their own grants, budget, rules, schedule or approvers.
Each executive reads only what it was granted. A colleague answers with its own access and never lends it.
Checked before every call: pause, grants, account, caps, rules, autonomy.
Six short steps in one window, about two minutes. The wizard saves after every step, so you can leave and come back.
Your own team, or a shared project with its own connections and members.
Paste your website or point at a vault, a Drive folder, a Notion page or a Confluence space. Melaya drafts the profile with a source on every line, without calling a model.
Roles proposed from the tools you already connected, each bound read-only to the accounts it needs.
Observe, Prepare or Run within rules. Prepare is the recommended start.
In-app inbox, email, phone push, Telegram or WhatsApp, each with a guided setup.
Every executive runs a read-only first pass, then asks for what is missing: a connection, an account, a document.
Fictional example. A line under the confidence floor stays empty for you, never a guess.
What EXCOM does, what it never does, and what you keep control of.
EXCOM gives your company a team of AI executives, such as a CEO, CFO, CMO, CTO and COO. Each one owns a department, keeps its own memory and conversation, reads the accounts you assign, reviews them every day and proposes work with evidence. Sending, changing records and spending follow the autonomy and the approvals you set.
A chat waits for your next prompt. An executive works on a schedule, reacts to events from your apps, asks colleagues bounded questions and tracks its work as tasks that only a check or a human can mark complete. You read one brief instead of starting a conversation.
Yes. Claude Code, Codex, GitHub Copilot, Ollama and LM Studio run on your own machine through the Melaya runner, and each executive can use one of them. The server decides every tool call, so the approval gate is the same as for cloud models. Keep the runner up to date: an older runner keeps its executives in Observe.
Sends only happen on Bastion and up, from an account you raised to write, after your approval or under a rule an approver accepted. Payments, refunds, purchases and deletions always ask you, on every plan, and no rule can change that.
Whatever you connect and assign, for example Gmail, Stripe, Odoo, HubSpot, GitHub, Google Drive, Notion, Confluence and an Obsidian vault. Each executive gets only the accounts you grant, read-only at first.
In the Melaya app inbox, by email, as a phone push, or on Telegram and WhatsApp with Approve and Decline buttons. A decision on one surface updates the others and resumes the parked work. Cards show the tool and the argument names, never the values.
The model work runs on your own provider, subscription or machine, and Melaya never pays for it with a model of its own. Setup is free because it never calls a model. Daily limits in money or tokens, per team and per executive, keep usage bounded.
Yes. A personal team works for one person with that person's connected accounts. A project team works for a shared Melaya project, and its members get roles from viewer to owner.
No. Executives own ongoing responsibilities. Pipelines handle repeatable workflows, and an executive can propose one that only gets a schedule after a dry-run trial and your approval.
EXCOM is in limited preview while we measure capacity, and access opens in stages. As it opens, Sandbox observes and proposes, Forge drafts inside Melaya, and Bastion and up act within your rules.
Executives that read, prepare and ask. You keep the final say on everything that leaves.
Limited preview · Your model · Your approvals
mailchimp · campaign report
github · read pull requests
