panoma
Kind of explanation

How a sentence of yours becomes something your agents remember

You write to your coding agent. This is, step by step and without jargon, what panoma does so that sentence ends up as a rule every one of your agents receives, and to check that they received it. Scroll to see it.

1 / 12

You write something to your agent

For example, to Claude Code: “Keep the journal append-only until the migration finishes.” It is a sentence inside a conversation, like any other.

Nobody stores it as a rule. If you open another session tomorrow, the agent does not remember it.

2 / 12

The conversation is saved in a file, on your computer

The agent writes down everything that happens — what you tell it and what it does — in a file. That file belongs to the agent and lives on your disk.

panoma does not touch it: it may read it if you allow that, but it never writes into it.

3 / 12

panoma cannot read that file until you allow it

You decide, agent by agent. And they are three separate permissions:

Permission to read in panoma: capture: panoma may open the file and write down what the agent did — which files it touched, whether the tests passed. It never copies what was said.

Permission to ask the AI in panoma: extraction: panoma may send your sentences — only yours, never the agent's — to an AI to look for rules in them.

Permission to learn your taste in panoma: Twin: panoma may notice what you keep repeating and propose taste criteria (you will see it in step 9).

Without the first, nothing is read. Without the second, nothing leaves your computer. This journey uses the first two.

Right now panoma cannot read anything. Turn the permissions on to see what happens next.
4 / 12

With permission, panoma reads the file and writes down what happened

Only a short list of facts, without the conversation's text: the agent read 3 files, changed 1, the tests passed.

It reads a little at a time and in the background, so your computer is not slowed down.

5 / 12

When the conversation has been idle for half an hour, it asks the AI

panoma gathers your sentences (masking any password) and the facts it wrote down, and asks the AI: is there anything here that should be a rule of this project?

Asking costs money, so there is a cap: 12 questions a day at most. When the cap runs out, it waits for tomorrow.

6 / 12

The AI proposes a rule

It returns a short sentence and points at the message of yours it came from.

It is only a proposal: it counts for nothing yet and no agent sees it.

7 / 12

You decide

The proposal shows up in the panoma app, in the project's Memory tab. Only you can approve or discard it: no agent can, not even with its key.

There are never more than 20 proposals waiting, so reviewing them never becomes an endless chore.

8 / 12

Now it is a rule of the project

Short (500 characters at most) and numbered: version 1. If you change it one day, panoma keeps how it was before.

You can add details: which folder it applies to, what must stay true (for example, that a file exists) and until which date.

9 / 12

panoma also learns how you like things done

With the third permission, panoma notices what you tell your agents again and again — “short answers”, “no colours outside the colour file” — and turns it into taste criteria. That part of panoma is called the Twin.

The criteria are written into a file of yours, TASTE.md, which the agents receive too. You can edit it by hand: delete a line and panoma reads it as a no; rewrite one and it reads it as a yes in your own words.

A new criterion publishes itself only when panoma has seen it in at least three different conversations and you have said, once, that it may. Otherwise it waits for your yes like any proposal.

10 / 12

The next time an agent starts, it receives the rules before your first message

panoma gathers the project's rules and your taste criteria into one package and hands it to the agent when the session opens.

Before handing it over, it keeps a copy of exactly what it sent, with a fingerprint: a unique code that identifies that content.

11 / 12

panoma checks that it really arrived

Later it looks at the file of that new conversation and searches for the package, byte by byte, in the place where the agent stores what it receives.

If it is there: it arrived whole. If it is missing or partial, panoma writes that down as it is. It does not trust; it checks.

12 / 12

And it keeps watching

A rule can stop being true. panoma checks your files every so often: if the rule said “this file exists” and it no longer does, it sets the rule aside and tells you, with the evidence.

And if one day you want to delete a rule, panoma shows you first what it is going to delete and writes it into a log.

In short

  • Nothing is read without your permission, and permission is given agent by agent.
  • Nothing becomes a rule without your yes.
  • Every rule and every criterion reaches the agent when the session starts, and panoma checks in the agent's own file that they arrived.
  • What stops being true is set aside, and you are told.

What each thing is called inside panoma

capture
the permission to read the conversation file and write down what happened
extraction
the permission to send your sentences to the AI
Twin
the part of panoma that learns your taste, and the third permission
proposal
a rule waiting for your yes
note
an approved rule of the project
criterion
a taste of yours, written in TASTE.md
contract
the package of rules and criteria the agent receives when it starts
receipt
the check that the package arrived
patrol
the check that the rules are still true

The reference