Show HN: Dari-docs – Optimize your docs using parallel coding agents
Documentation just became a QA problem. Dari-docs runs parallel agents across your docs to find where Claude, GPT, and Pi agents fail—before your users do.
Why it matters
As AI agents become the primary interface for developer onboarding, documentation optimization has shifted from human-readability to agent-reliability. Dari-docs directly solves this by stress-testing docs with multiple models in parallel, surfacing agent failure modes that humans would miss.
The key facts
7 to knowProduct: Dari-docs — documentation optimization tool using parallel agent testing
Use case: Test documentation with Claude Code, Codex, Pi agents across different intelligence/cost tiers
Key feature: Live API verification with test credentials for end-to-end workflow validation
Deployment method: Web UI or CLI (dari-docs check . --live-verify)
Core insight: Agent-optimized docs require objective, concrete problem-solving vs. human-compensatable inconsistency
Agent behavior tested: Search, instruction-following, command execution, examples, debugging
Output: Feedback markdown files with actionable agent failure patterns
Go to the source
Hacker Newsgithub.com
Publisher excerpt: It’s well known at this point that documentation needs to be optimized for AI agents - we’re all pointing our Claude Code / Codex / Pi agents at documentation, and expecting the models to figure out how to implement a product. This, however, changes the entire optimization problem when writing…