Company lore and the 'why' behind technical decisions often disappear when employees leave. An AI agent can analyze the entire codebase and its commit history to answer questions and reconstruct narratives, effectively turning your repo into a searchable archive.

Field engineers can bypass documentation limitations by querying the entire codebase with AI tools like Claude Code. This provides detailed, step-by-step answers that public docs lack, directly addressing complex customer problems and reducing reliance on the engineering team.

To improve communication with engineering, PMs should use AI to analyze their company's actual codebase. Asking the AI for a high-level architecture diagram or to explain a component is a practical way to learn the system and develop a shared language with developers.

Product managers can use coding agents like Codex for self-service technical discovery. Instead of interrupting engineers with questions, they can ask the AI about the codebase, feature status, or implementation details, increasing their autonomy and team efficiency.

OpenAI structures its repositories to be a complete, self-contained knowledge base for AI agents. All project artifacts—design docs, historical implementation plans, and even text versions of external library documentation—are checked in, allowing the agent to find any needed context via simple search.

Technical onboarding for new leaders has been transformed. Instead of relying on engineers for ad-hoc explanations, a CPO can now use AI tools to have "long conversations" with the codebase, gaining a deep understanding of the technical architecture quickly and without interrupting the team.

Creating user manuals is a time-consuming, low-value task. A more efficient alternative is to build an AI chatbot that users can interact with. This bot can be trained on source engineering documents, code, and design specs to provide direct answers without an intermediate manual.

PMs can use AI agents connected to their codebase to explore technical feasibility and iterate on ideas. This serves as a 'digital tech lead,' saving immense time for senior engineers who were previously burdened with speculative 'how hard would it be?' questions from product managers.

A more effective way to increase developer velocity with AI is to have champion engineers embed knowledge directly into the systems. This includes creating context engineering techniques, `agents.md` files, and agent skills within the repo itself. This way, any agent pointed at the repo benefits, rather than relying on every individual developer's expertise.