LLenny's Podcast
← All frameworks
ProductivityThe future of software development with OpenAI’s Sherwin Wu

Context-First Agent Debugging

When a coding agent won't do what you want, treat it as a missing-context problem, not a model problem.

Difficulty
Easy
Time to result
~days to results
Steps
4
Confidence
90%

OpenAI's internal experience is that most cases where a coding agent fails to complete a task are caused by under-specification or missing information, not model incapability. The fix is to encode the tribal knowledge in your head into the repository itself — through code comments, code structure, and text/MD files (skills, agents.md) — so the agent has what it needs to succeed on the next attempt.

Origin

Learnings from an internal OpenAI team running an experiment to maintain a 100% Codex-written codebase, shared by Sherwin Wu.

Core principles

  • 01Most agent failures are context failures, not capability failures
  • 02Tribal knowledge in a human's head is invisible to the agent until encoded in the repo
  • 03The codebase itself is the durable place to store the context an agent needs
  • 04Removing the human 'escape hatch' forces you to actually solve the context gap

How to run it

  1. 1

    Diagnose the failure as a context gap

    When the agent won't complete a task, first assume you underspecified it or there isn't enough information available to the agent about how to do it.

    Watch out Don't immediately conclude the model can't do it — that reflex leads you to abandon the agent prematurely.

  2. 2

    Locate the missing tribal knowledge

    Identify what you know in your head about how this task should be done that the agent has no way to access.

  3. 3

    Encode it into the repository

    Add the knowledge as code comments, better code structure, or text files (MD files, skills, agents.md) inside the repo so the model can use it.

    Pro tip Persist context in the codebase rather than re-explaining it per prompt, so future agent runs inherit it automatically.

  4. 4

    Re-run and iterate

    Have the agent retry with the added context and repeat the loop, steering rather than taking over.

In the wild

The no-escape-hatch team

An internal OpenAI team maintaining a fully Codex-written codebase removed the usual fallback of dropping to tab-complete or hand-coding when the agent got stuck. Forced to make the agent succeed, they found failures were usually context problems and had to encode missing knowledge into the repo.

A set of best practices and paradigms fell out, slated for a public blog post.

Common mistakes

Reaching for the escape hatch too early

Rolling up your sleeves to hand-code the moment the agent struggles hides the real (context) problem and prevents you from building the durable documentation that makes agents reliable.

Blaming the model instead of the prompt/repo

Attributing failures to model incapability leads you to under-invest in specification and repo context, so the same failures recur across tasks.

Is it for you?

Best for

Engineers and teams leaning heavily on coding agents who hit repeated agent failures

Not ideal for

Genuinely novel tasks that exceed current model capability, where more context won't help

From the transcript

when the coding agent is not doing what you want, it's usually a problem with context

14:00

encode more tribal knowledge that's in your head somehow into the codebase

14:30

either via you know code comments itself or code structure itself or via text files like you know MD files skills

14:30

this team uh uh for the experiment this team doesn't have that escape hatch

13:30

From the episode

“Engineers are becoming sorcerers”

The future of software development with OpenAI’s Sherwin Wu