Create a Centralized Directory
Create a docs directory organized by real engineering domains such as frontend, backend, testing, accessibility, and operations. Put setup and conventions where they can be versioned with the code.
Move engineering guidance into the repository, keep full human documentation under docs, and create concise central agent rules that link to it. Tool specific files then point to one source instead of duplicating instructions.


Source episode · 07:55
How I AI: Zach Davis's 3 Workflows for Enterprise Engineering with AIwith Claire Vo
Zach shows documentation moved from Confluence and Google Docs into the monorepo, a central `.agents/rules` directory, and thin Cursor or Augment files that point to the same guidance.
Repository documentation for humans plus concise central agent rules reused by each coding tool.
AI-first code editor
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Create a docs directory organized by real engineering domains such as frontend, backend, testing, accessibility, and operations. Put setup and conventions where they can be versioned with the code.
Move useful material from Confluence, Google Docs, READMEs, and tribal knowledge into the repository. Mark a canonical file for each topic and link old locations to it instead of maintaining two copies.
Create a central agent rules directory with concise instructions for common decisions. Each rule should state when it applies, the correct repository pattern, and a link to the full human documentation.
Ask an agent to consolidate existing tool rules into the central structure, but require it to cite the source rule and repository docs for every instruction it keeps.
Create a central agent rule for [topic] from the attached Cursor, Claude, and repository documentation. Keep it concise, state when it applies, name the correct commands or code patterns, and link to the canonical docs for detail. List conflicts or unsupported claims instead of choosing silently.
When a developer or agent gets a repository convention wrong, improve the canonical documentation and the shortest relevant rule. Add the example that would have prevented the failure, then test the same task with the updated context.
The agent used Jest even though this repository uses Vitest. Update the canonical testing doc and the central test rule with the correct command, file pattern, and one repository example. Keep tool specific files as pointers to the central rule.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building

Create context-aware guardrails for your enterprise AI agent using a 'Project' governance layer. As a project owner, define rules, scope tools, and require human-in-the-loop approval for sensitive actions, ensuring safe and effective AI use.

Transform a successful AI chat session into a reusable skill that anyone in your company can use. Package prompts, tools, and code into a standardized workflow, making it easy to share and scale automation across your organization.

Use a natural language AI agent to instantly generate and iterate on custom data dashboards. This workflow queries your company's data securely, allowing non-technical users to perform their own 'last mile' data analysis without filing tickets.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.