Cohort
Agentic AI workflows — designed and operated

Design the work. Watch it run.
Get a receipt.

Agents that know the job before they start.

Write what a job must find out, what it must never do, and when it is done. Cohort runs it, shows you the rules being met while it works, stops it at a ceiling you set, and hands back a sealed record of what it found and where each answer came from.

Start a run How a workflow is written What it costs
Running our own fleet and OmniDeck's live turns today.
Who runs on it

Already doing real work.

Real products, real traffic — each one metered and receipted like anybody else's.

live OmniDeck

Assistants people build by talking to one.

omnideck.ai live Trellis

Engineering agents that ship under governance.

xtrellis.ai in pilot Hakeem

Patient intake, in the patient's own Arabic.

hakeem.projexlabs.com live Our own fleet

The agents that build and run our products.

projexlabs.com
What the platform does

You can check every one of these.

Each of these is on screen in the console today.

01

Agents don't run blind

A run shows the rules it must satisfy being met, one by one, while it works — and what it is waiting for when it needs you. You are not reading a transcript afterwards trying to work out what happened.

On the run page: the rules, live
02

You design the work

A workflow is written as rules: what it must find out, what it must never do, when it is done. Start from one Cohort ships, then make it yours. The plain-language page is generated from the rules, so the description can never drift from what is enforced.

Must find out · must never · done when
03

Every run has a ceiling and a receipt

You set what a run may spend before it starts. It stops itself there, nothing can raise it while it runs, and either way you get a receipt: rules met, whether it went off-script, steps, how long it took, and what it cost.

Cost against the ceiling, settled or not
How it works — where your money sits

Three levels, and money only moves down.

This is the part people get wrong first, so it is worth thirty seconds. Cohort keeps your credit in three places, and it only ever travels downwards, one deliberate act at a time.

01

Your account

Everything you own. Credit lands here when you buy it, and this is the only level that holds money you have not yet committed to anything.

02

A workspace

One project, kept separate from your others. You move credit into it yourself — and only a signed-in person can. No automation, however trusted, can help itself to more.

03

A key

What a program presents to Cohort to get work done. Each key belongs to one workspace and carries its own small wallet, and a job spends that wallet and nothing else.

The consequence is the whole safety story in a sentence: an agent can only ever spend what was put in front of it before it started. A key with an empty wallet cannot begin work even when the project it belongs to is full of credit — not because something went wrong, but because nobody gave it any yet.

Already have an account? The console shows you your own figures at every one of these levels — go straight there rather than reading about it here.

How it works — proving what happened

You can give a job rules, and get a record back

Most of the time you want an agent to do something and tell you how it went. Sometimes you need to answer a harder question later: how does anyone know it actually did that? A transcript is not an answer — somebody still has to read it and form a judgement.

So a job can be given a charter: a written set of rules saying what it must find out and what counts as finished. Cohort records what the agent did against those rules as it works, and at the end there is a record stating which rules were met. Not a summary written afterwards by the same agent that did the work — a record built as it went.

It is optional, and most jobs do not need one. It is what you reach for when the work is the kind somebody may later have to defend: an intake, an assessment, anything where "we think it went fine" is not good enough.

How it works — what you pay for

Metered per turn, and bounded before the work starts.

Every exchange an agent has is measured — what went in, what came back, and the compute it took. Those measurements are itemised per job, so the question "what did this cost" has a real answer rather than an estimate at the end of a month.

Two properties matter more than the rate. First, the ceiling is set before the job begins, so an agent cannot run up a bill while nobody is watching. Second, the running total says whether it has settled yet — Cohort tells you where it does not yet know something instead of handing you a figure that merely looks final.

What it actually costs depends on which model you run and is published live rather than quoted here, because a price written into a web page is a price that goes stale without anybody noticing. The current rates for every model are in the console under Price list, and are readable over the API.

Who runs on it

The harness beneath OmniDeck — and our own fleet.

Cohort is deployed internally today: it runs our own multi-agent fleet and OmniDeck's live turns, sandboxed and metered, with serverless spawning proven on cloud container infrastructure. It's for builders of agent products and enterprises putting agents to work — anyone who needs the job defined before it starts, and a record of it afterwards.

OmniDeck — assistants & chat Our own fleet — multi-agent, live your workforce next

Safe & billable by construction — every turn sandboxed, every turn metered. Productization as a standalone offering is in development, not yet claimed.

Put your agents to work.

Write the rules once, watch the run keep them, and get a receipt when it is done. Every run bounded by a ceiling you set.

Sign in What it does Who runs on it