
What Dan Luu Learned About Agentic Coding
Dan Luu published field notes on coding with AI agents. This piece explains what he found and why bounded loops keep Codex work reviewable.
Field notes on Codex CLI, AGENTS.md, MCP permissions, review receipts, verification evidence, and production agent workflows.
Start with Codex CLI training, OpenAI Codex for teams, and Codex CLI workflows.

Dan Luu published field notes on coding with AI agents. This piece explains what he found and why bounded loops keep Codex work reviewable.

Why a Hacker News debate about LLM coding flow matters for Codex CLI, MCP, specs, and verification loops.

A story-first look at Manufact (YC S25), MCP Cloud, and the permission boundaries Codex users should care about.

Codex Workshop research on issue #2847, agent ignore files, and safer Codex CLI workflows around secrets.

A Codex-ready team rollout plan for shared agent workflows, MCP boundaries, and safer review habits.

Set up Codex agents with scoped AGENTS.md rules, safe MCP access, verification commands, and reviewable handoffs.

A practical Codex rollout for team AI coding governance with MCP boundaries, AGENTS.md rules, and review guardrails.

Connect Codex CLI to MCP with scoped AGENTS.md rules, safe permissions, and a verification loop your team can review.

A practical rollout plan for training engineering teams to use Codex and coding agents with guardrails.

Use Codex Remote with GitHub, AGENTS.md, MCP boundaries, and reviewable diffs in Codex CLI workflows.

A Codex-first convention for aligning AI code assistants, MCP boundaries, and review guardrails across a team.

A practical Codex Remote GA guide for teams using GitHub, AGENTS.md, MCP, and Codex CLI verification loops.

A practical Codex convention for safer agent-assisted reviews, MCP boundaries, and team-owned AGENTS.md checks.

Team workflow for Codex CLI, AGENTS.md, verification loops, and reviewable diffs after Codex Remote GA.

A practical team convention for orchestrating Codex and other agents with clear roles, MCP limits, and review rules.

A practical Codex CLI workflow for MCP servers, AGENTS.md rules, Remote runs, and reviewable verification.

A practical Codex workflow for llm code review, with AGENTS.md guardrails, MCP boundaries, and a copyable review receipt.

A practical Codex training guide for teams adopting Codex Remote, AGENTS.md, MCP, and reviewable CLI workflows.

A practical governance matrix for comparing Codex, Claude Code, and Codex across repo rules, MCP boundaries, and review loops.

A practical AGENTS.md convention for Codex CLI teams that want safer MCP access, verification loops, and reviewable diffs.

Signed isolation bundles help teams test coding agents with clear tool boundaries, review guardrails, and repeatable evidence.

A practical Codex CLI review workflow with AGENTS.md rules, MCP checks, verification loops, and a PR receipt.

A practical Codex team convention for autonomous coding agents, MCP boundaries, and code review guardrails.

A practical Codex team convention for autonomous coding agents, review guardrails, MCP boundaries, and safe verification loops.

A practical Codex workflow convention for governing autonomous coding agents with states, MCP boundaries, and review checks.

A practical Codex CLI MCP checklist for AGENTS.md, verification loops, and reviewable team workflows.

A practical Codex CLI MCP checklist for AGENTS.md rules, verification loops, and reviewable diffs after app updates.

A practical Codex CLI workflow for verifying MCP servers, setting AGENTS.md boundaries, and keeping diffs reviewable.

A team convention for reviewing agent skills, Codex workflows, MCP boundaries, and mixed-experience AI coding.

A practical Codex convention for AI coding training, skill rubrics, MCP boundaries, and review guardrails.

A practical Codex workflow response to app 26.616: AGENTS.md rules, CLI verification, MCP boundaries, and reviewable diffs.

How to respond to Codex app 26.616 with AGENTS.md rules, CLI verification, MCP boundaries, and review habits.

A practical Codex-first review workflow for governing coding agents across tools, MCP servers, and team rules.

A team convention for Codex AGENTS.md files, with scoped rules, MCP boundaries, and a reviewable verification loop.

A practical governance workflow for Codex teams using AGENTS.md, MCP boundaries, skills, and review checks.

Use Codex CLI, AGENTS.md, verification, and review receipts to make AI-assisted code review safer for teams.

A team training guide for Codex, MCP boundaries, AGENTS.md rules, skills, and review guardrails.

A practical Codex CLI MCP guide for teams: configure one server, document AGENTS.md boundaries, and verify diffs.

Install Codex CLI with AGENTS.md, MCP boundaries, and a verification loop your team can reuse for reviewable diffs.

A practical read on the workflow, tradeoffs, and next steps. Read the workflow, review rules, and team training patterns for AI coding tooling.

Team convention for Codex CLI context limits, AGENTS.md rules, MCP boundaries, and verification loops.

A practical team convention for reviewing AI-assisted code without slowing delivery or losing ownership.

A Codex CLI review workflow for AGENTS.md rules, MCP boundaries, verification loops, and review receipts.

How to set up an AI coding workshop: pick a format, scope it to your real repos and review habits, run hands-on labs, and leave with a shared playbook.

The five operational training modules DevOps teams need before Codex CLI touches delivery paths: guardrails, secrets, CI evidence, rollback, ownership.

The practical answer to what is MCP in Codex, plus the repo contract Codex CLI teams need before connectors touch shared code.

Codex CLI review workflow for openai codex cli review code changes, AGENTS.md, MCP, and verification loops.

A Codex CLI workflow guide for how to add mcp to codex, AGENTS.md, and reviewable verification loops.

A Codex CLI guide for how to install codex cli, AGENTS.md, MCP, and reviewable verification loops.

A Codex CLI guide for AGENTS.md, MCP, verification loops, and reviewable diffs. Read the workflow, review rules, and team training patterns for MCP.

A Codex code review workflow for AGENTS.md, MCP, and verification loops that turns CLI diffs into reviewable receipts.

Practical ai coding training for large teams: review guardrails, MCP boundaries, and team habits that improve delivery.

A Codex CLI workflow guide for openai codex cli github, AGENTS.md, MCP, and reviewable verification loops.

A practical Codex CLI comparison for codex cli vs claude code, with AGENTS.md, MCP, and verification loops.

A Codex CLI workflow guide for codex cli mcp, AGENTS.md, MCP boundaries, and verification loops teams can use to ship reviewable production work.

Practical mcp training for engineering teams using agentic coding, review guardrails, and connector boundaries.

A Codex CLI workflow guide for codex github, AGENTS.md, MCP, and reviewable diffs in production repos.

Codex CLI 0.132.0 tightens AGENTS.md, MCP, and verification loops for reviewable diffs.

A codex governance note for engineering teams: the slash catalog, verification latch, browser bridge note, and model pin that keep Codex CLI work reviewable.

A codex mobile cli pattern for running Codex CLI from anywhere: verification latches, model pins, and connector rosters that keep remote runs reviewable.

Agentic coding governance beats speed: connector cards, child receipts, decision stubs, and scope ledgers that make agent diffs defensible after merge.

A field guide to agentic coding workflows and guardrails: handoff receipts, connector ownership, and review gates for engineering teams under deadline.

Codex workflows for mobile handoffs: the repo contract of model pins, connector rosters, done checklists, and slash catalogs that lets agent work change hands.

The codex mobile cli question is a docs question: how a team keeps AGENTS.md rules, run notes, and verification transcripts readable away from the desk.

Codex workspace agents and Codex cloud agents need repo rules: scoped boundary files, connector cards, and replay receipts reviewers can check.

How to govern codex workflows from the repo: a connector roster, a ten-line done checklist, a slash catalog, and a verification latch reviewers can replay.

The fast model is a tradeoff you make on purpose: scope ledgers, replay sandwiches, and connector cards that keep fast agent runs reviewable.

Codex-auto-review trials showed Codex catching syntax drift and missing permission drift. The fix is transcript evidence and repo contracts, not more autonomy.

An operational memo for Codex CLI 0.129.0: MCP boundaries, connector owners, allowed actions, AGENTS.md instructions, and reviewable diffs.

A field guide to AI agent guardrails for recursive agent chains: connector ownership, child receipts, and review evidence that survives the merge queue.

Codex workflows that cross into Chrome: the browser bridge note, model pin, connector roster, and done checklist that keep two surfaces telling one story.

A PR review workflow for agentic coding teams: connector ownership, scoped tasks, replay transcripts, and human approval lanes from PR to merge.

What codex-cli 0.130.0 means for production repos: the AGENTS.md boundaries, MCP permissions, and review receipts that hold across any Codex CLI release.

Codex CLI 0.121.0 repo workflows: named connector owners, a pinned model in AGENTS.md, and PR receipts that survive reviewer handoffs.

Codex CLI workspace tools that carry the operating contract: model pin, connector roster, done checklist, and slash catalog for reviewable agent runs.

A Codex CLI 0.122.0 workflow guide: AGENTS.md instructions, permission boundaries, MCP rosters, and verification reviewers can replay.

Codex CLI 0.123.0 workflows that hold up in review: replay recipes in the diff, a pinned model, a connector roster, and a ten-line done checklist.

Codex CLI 0.124.0 as a workflow moment: shrink the rollback contract, pin the model, and keep a connector roster and done checklist where reviewers live.

Codex 5.5 questions are model governance questions: pin the default model and escalation rule in AGENTS.md, and keep browser checks bridged to CLI receipts.

A practical Codex CLI /goal workflow guide: persistent goals carry intent, AGENTS.md carries boundaries, and receipts carry proof across handoffs.

An operational memo for codex-cli 0.125.0: reviewable agent loops, AGENTS.md pins, verification transcripts, and connector rosters.