Open-source work designed and written with an AI agent on SharpPyxis

How an agent works

Mon, 01 Jan 0001 00:00:00 +0000

How an agent works#

Read this if the way an agent works is not already familiar. Nothing here has to be taken on trust: it all follows from its mechanics, and those mechanics are simple.

What the tools already keep#

An agent does not start entirely from zero once the tool is involved. Most tools keep notes, reread at every start an instructions file you put there for them, and let you attach a piece of work to a folder, to documents and to standing instructions. All of that is real, and on a single subject it is often enough.

In practice

Mon, 01 Jan 0001 00:00:00 +0000

In practice#

Read this the day you try it. Nothing is to be prepared beforehand. The rule is simple: a prerequisite the agent can resolve is not a prerequisite. The runtime the checks need is verified by the agent, which offers to install it. It is required of nobody in advance. The rest — installing git, understanding a command, choosing between two ways of doing something — is already part of ordinary agent use.

In detail

Mon, 01 Jan 0001 00:00:00 +0000

In detail#

This page is read while working, not before. It gives the reference in the order a session meets it: the documents, the reading rules, how a session runs, who writes what, and what the checks verify — for a session opened as the manual describes.

Four locations, four tenses#

A workshop’s framing is organised around four locations, and an item lives in exactly one of them. Drift often starts when one document quietly takes on the role of another.