Pando

The branch you share with your agent

2026-08-16

Most agent setups fail on permissions or on amnesia. One shared branch with three parts fixes both, and you can read it.

Two things go wrong when you give an agent real work. Either it cannot reach what it needs, so every task begins with you pasting context. Or it can reach everything, and you find yourself hoping it behaves, which is not a security model.

Both are the same missing thing: a place the collaboration lives, that you can see.

Three parts, one branch

A branch shared with an agent in Pando: a briefing, the agent's own working notes, and an inbox with one task ticked

Share one branch with your agent and give it three children.

Briefing is what it may do here, in your words. Not a system prompt buried in a settings page: bullets you can edit on a Tuesday when the rules change. "File captures under their projects. Never delete. Never touch a protected bullet."

Working notes are the agent's own. What it did, what it could not decide, what it noticed. This is the difference between an agent that repeats a mistake weekly and one that recorded it once.

Inbox (from your agent) is where it puts what it needs from you, as checkboxes you tick. That pattern is worth its own post; the short version is that a request in a chat scrolls away and a checkbox does not.

Why permissions stop being scary

The branch is the boundary. The agent sees that branch, and what you explicitly share beyond it, and nothing else. Not your whole outline with a promise. Not a folder you hope it stays in. A grant, revocable in one press, scoped to a bullet and everything under it.

That makes the interesting move safe: you can share ONE project with an agent and nothing else, and watch what it does there for a week before widening anything. Trust arrives by evidence rather than by configuration.

Why it stops being amnesia

Everything the agent learns lands in Working notes, which survives every session because it is a bullet in a real outline rather than a context window. When it is wrong, you fix the NOTE, and every future session inherits the correction.

There is a second effect worth naming: because you can read the notes, you find out what your agent misunderstands. That is normally invisible, and it is usually the most useful thing on the page.

The rule of thumb after a month of this

Put the judgement in the Briefing, the memory in Working notes, and the asks in the Inbox. Anything that does not fit those three is usually a task that should have been a bullet somewhere else in your tree.

Take the branch

Open the template, press "Show in my Pando", then share that branch with your agent and tell it one sentence: "Read the Briefing before you work, keep Working notes, and put anything you need from me in the Inbox as a checkbox."


More from the blog · Try Pando