Topics

Agent loop

Every article on Agent loop published on this blog, newest first: 8 in total, written by Ramón Chancay.

8 articles on Agent loop

Illustration of an agent's hard limits: the agent loop enclosed in a frame of checks—budget, command allowlist, path allowlist—with a kill switch outside and a log of every turn

AI31 Aug 202633 min read

The hard limits of an autonomous agent: what keeps it from disaster

Hard limits that let you leave an autonomous agent running: iteration and token caps, command and path allowlists, a kill switch, idempotency, observability.

Illustration of the end-to-end system: a Jira ticket enters through a trigger, passes through a stateful queue, runs in an ephemeral workspace, and comes out as a pull request that returns to Jira as a comment

AI2 Jul 202629 min read

From a Jira ticket to a pull request: the end-to-end autonomous system

How I made the agent an autonomous system: a Jira ticket triggers it, a queue with persistent state runs it exactly once, and it returns a PR and a comment.

Illustration of an isolated agent: a separate working copy branches off the repository on its own branch, the loop works inside it, and the output is a pull request, not a merge

AI30 Jun 202619 min read

The agent inside a real repo: isolating tasks with git worktree and shipping a PR

How to put an agent loop to work on a real repo: isolate each task with git worktree, reproduce the bug with a test, run the suite and ship a PR, not a merge.

AI30 Jun 202621 min read

From generating files to using tools: a code agent's ReAct loop

From generating a whole function to a code agent that reads, searches, edits and runs with tools: the ReAct loop, and why the agent builds its own context.

Illustration of three levels of input for an agent: hand-written tests, examples the agent turns into tests, and the repo's existing suite as the evaluator

AI30 Jun 202624 min read

Who writes the agent's tests: three ways to define what's correct

Who writes a coding agent's tests decides what counts as correct. Three options: spec and tests by hand, examples it turns into tests, or the repo's own suite.

Execution sandbox illustration: the model's text enters an isolated enclosure with a timer, passes through four filters, and comes out as a classified observation

AI30 Jun 202621 min read

The sandbox in an agent loop: from the model's text to a reliable observation

The sandbox in an agent loop turns LLM-generated code into a reliable observation: extract the code, check it parses, run it with a timeout, isolate it.

Write-test-fix loop illustration: one node writes code, another tests it, and the failure feeds back as context until the tests pass

AI30 Jun 202624 min read

The simplest loop that works: a write-test-fix agent, step by step

The simplest agent loop that works: spec and tests by hand, the model writes code, it runs, and failures feed back as context. A complete write-test-fix loop.

Agent loop illustration: a goal enters a cycle of decide, act, and observe that repeats until a stopping condition

AI29 Jun 202612 min read

What an agent loop is (and isn't): state, action, stop

What an agent loop is and isn't: its three components—state, action, and stopping condition—and why 'build me an app' is input for a chat, not an agent.