Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

CJ Hess says Tenex standardized engineering skills into repo documentation and a CLI, then required agents to log decisions and work. Everything is checked into Git, so context lives in a durable record rather than someone's head. That gives agents and tools the context many teams keep only in conversations.

Related Insights

When multiple AI agents need to modify a shared knowledge base, Lindy avoids complex database transaction logic by using a Git-backed file system. This allows agents to handle collaboration issues like merge conflicts using a battle-tested paradigm from human software development.

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.

The defensibility of AI-native software will shift from systems of record (what happened) to 'context graphs' that capture the institutional memory of *why* a decision was made. This reasoning, currently lost in human heads or Slack, will become the key competitive advantage for AI agents.

The effectiveness of enterprise AI agents is limited not by data access, but by the absence of context for *why* decisions were made. 'Context graphs' aim to solve this by capturing 'decision traces'—exceptions, precedents, and overrides that currently live in Slack threads and employee's heads, creating a true source of truth for automation.

Manage collective team context—docs, queries, research—in a version-controlled repository. Everyone, including non-technical members like ops and strategy, contributes via pull requests, creating a single, evolving source of truth for AI agents and humans.

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.

When an agent fixes a production issue, a human can instruct it via Slack to also update the core reliability documentation. This not only solves the immediate problem but durably encodes the process knowledge, turning ephemeral conversations into persistent, automated process improvements.

By organizing all product documents—PRDs, quarterly plans, research, and meeting notes—into a version-controlled GitHub repository, PMs create a single source of truth. This "product repo" becomes a structured environment that AI agents can easily navigate to access context and generate new artifacts.

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.

The team centralizes crucial context—product strategy, customer intelligence, meeting outcomes—into a repository of markdown files. This ensures all AI agents and team members pull from a single, up-to-date source of truth, making their outputs relevant and consistent.