AI 대리인을 위한 Reflexion의 인간 실행 버전은, fifty 년간 표준 연습이었습니다 군 방법에 건축했습니다.

실행 /aar-loop 어떤 작업이나 세션 후. 그것은 세 가지:

1. ** 세션을 검토 ** 미국 육군의 4 퀘스트 후 행동 검토. 2.Finds 무엇 고정 당신의 기술 또는 규칙 파일로 개선을 작성, 그래서 수정은 당신이 그것을 다시 필요로하기 전에, 그냥 어딘가에 작성하지.
2. Saves the Lesson to a persistent LESSONS.md file that your AI loads next time.

그 파일에서 다음 세션을 포인트 (그리고 어떤 기술 또는 규칙은 패치) 및 에이전트는 동일한 실수를 반복합니다. 각 세션을 실행하고 에이전트 화합물 대신 0에서 다시 시작.

방법은 어디에서 왔는지

미국 육군은 훈련 운동을 위해 구조상 파편으로 베트남 후 1970 년대 중반에 행동 검토를 형성했다. 그것은 필드 매뉴얼 TC 25-20와 1993의 공식 교리가되었으며, 그것은 여전히 세계에서 가장 현실적인 전투 훈련 환경 중 하나 인 National Training Center, Fort Irwin에서 모든 회전 후 실행됩니다.

AAR Loop

A human-run version of Reflexion for AI agents, built on a military method that’s been standard practice for fifty years.

Run /aar-loop after any task or session. It does three things:

1. Reviews the session with the US Army’s 4-question After Action Review.
2. Finds what’s worth fixing and writes the improvement straight into your skills or rules files, so the fix is there before you need it again, not just written down somewhere.
3. Saves the lessons to a persistent LESSONS.md file that your AI loads next time.

Point the next session at that file (and at whatever skill or rule got patched) and the agent stops repeating the same mistake. Run it every session and the agent compounds instead of restarting from zero each time.

Where the method comes from

The US Army formalized the After Action Review in the mid-1970s, in the years after Vietnam, as a structured debrief for training exercises. It became official doctrine in 1993 with field manual TC 25-20, and it’s still run after every rotation at the National Training Center, Fort Irwin, one of the most realistic combat training environments in the world. Fifty years of continuous use on one method, because the mechanism is simple and hard to argue with: separate the debrief from blame, ask what was supposed to happen versus what actually happened, and the gap tells you exactly what to fix before the next fight.

The 4 questions, verbatim:

1. What was supposed to happen?
2. What actually happened?
3. Why was there a difference?
4. What do we do the same or differently next time?

The research parallel

This is also, functionally, a manual version of Reflexion (Shinn et al., 2023, arXiv:2303.11366): an agent framework where a model generates a verbal self-reflection after a failed attempt, stores it in an episodic memory buffer, and carries it into the next attempt. Reflexion agents that keep their reflections outperform agents that start every attempt from scratch.

Nobody’s wired that loop into your AI harness by default. This skill is the manual version: you run the reflection step yourself, once per session, and LESSONS.md is the buffer. Same idea, no automation, and it costs you five minutes.

Install

Paste this into Claude Code, Codex, or your AI harness:

Install this skill globally: https://github.com/coopersimson96/aar-loop

Use

/aar-loop

or just say “run an aar” after finishing something. Sample output:

AAR · production deploy

1. What was supposed to happen?
   Deploy the new build and have all three services (web, worker,
   scheduler) come up on the new version.

2. What actually happened?
   The deploy script reported success and exited 0. Web and worker were on
   the new version, but the scheduler was still running the old one; it had
   never actually restarted.

3. Why was there a difference?
   The deploy script only checks the exit code of the restart command, not