Unl for teams

Many people.
Many agents.
A shared why.

People and agents take on different parts of the work. They inherit a shared purpose through what the team decided and why. Unl keeps those reasons, with who decided them, so every agent can reason from them.

Team plans coming soon

Memory keeps what. Unl keeps why.

A rule your team writes lists the cases someone thought of. A reason your team decides reaches the ones nobody wrote down, for every agent that works for it.

Anyone can ask

Ask how it is going.
Everyone gets the same answer.

Whoever asks, in whichever AI, reads the same decisions, the same changes and the same reports. So the answer is the same true one, for the person who decided and for everyone working from it.

  1. The questionClaude Code, a new chat

    Asked How's Crumb going? Where do things stand?

    Answer, summarised

    • Decided. Which database to use, and the one it ruled out. Invite-only for two weeks, then open signup.
    • Changed today. Two weeks replaced the earlier call of a month, so two weeks is the current plan.
    • Built. An agent built the signup section a minute after that change.
    • Out of sight. The code itself, since the folder it was asked in is empty. It said so rather than guess.
  2. The follow-upClaude Code, a new chat

    Asked Yes, open it. What's left before launch?

    Answer, summarised

    • Found. The signup forms are front end only. Nothing is stored yet.
    • Left. A signup backend on the chosen database, as decided. A way to issue and check invite codes. An email to the waitlist when signup opens. The switch to open signup on day fourteen.
    • Where that came from. Gaps in the build report, not a plan written down. It said so, and offered to keep the list as tasks.

Unl keeps what you decided, why, and what replaced what, so the answer is current and not a guess.

A replay of a real run on a test account, 10 Oct 2026. Crumb is that account's test project, and its decisions, the change and the build came from earlier sessions that day. The questions are copied word for word. The answers are summarised. Team plans are coming soon. Today each person can ask about their own work.

The model we are building towards

Shared reasons.
Room for your own.

An organisation, its teams and each person have their own decisions. The company's why reaches down into team work. Each team and person fills in what it leaves open.

Organisation

What the company decided.

The decisions and reasons that apply across the organisation. They reach every team doing work within that area.

Team

What your team decides.

Your team decides its own work within the organisation's decisions. Other teams do not see your team's decisions by default.

Individual

What stays yours.

Your own decisions and conversations stay private. Your personal why works alongside the team's reasons.

The full nested organisation model is the direction of travel. It is not available as an enterprise product today.

The person responsible decides

A proposal can come from anyone.

A person or an agent can propose a change, with its reason. Unl brings the case to the person who holds responsibility for that area.

They decide it in their own words. If the people responsible disagree, both cases go to the person responsible one level above. Agents contribute to the reasoning. Human judgement makes the decision.

The resulting why reaches the agents doing the relevant work. They can continue within what the team has decided.

Where the conversation happens

Talk it through
in Slack.

See Unl in Slack

A change to a team decision deserves a conversation. The member, the person responsible and Unl can work through the reasons in a thread.

Slack is an operating surface for this model. The team model also carries the organisation's and each person's why into their AIs, wherever they work.

Multi-agent Slack participation is in development. Team plans remain separate from the individual Unl you can connect today.

Start with your own why.

Unl is your why agent. It keeps what you decided and why, and gives the relevant part to every AI and agent you use before it acts.