Skip to content

Conversation

@ericelliott
Copy link
Collaborator

@ericelliott ericelliott commented Jan 22, 2026

  • Add vision.md with north star: "The standard testing framework for AI Driven Development and software agents"
  • Add vision statement prominently to README
  • AIDD framework already initialized with ai/ folder structure

https://claude.ai/code/session_0135XoydQ5XAwSUrt6mrEdr6


Note

Introduces AIDD-focused positioning and planning materials.

  • Vision: Adds vision.md with the north star: The standard testing framework for AI Driven Development and software agents.
  • README: Elevates AIDD positioning, clarifies AI-native testing philosophy, and references upcoming riteway ai CLI and ecosystem pairing.
  • Planning: Adds tasks/2026-01-22-riteway-ai-testing-framework.md epic detailing migration of ai/riteway-ai/, prompt compilation to importable modules, riteway ai <file> CLI, rich TAP output to ai-evals/, and unit/E2E testing requirements.

Written by Cursor Bugbot for commit f84a708. This will update automatically on new commits. Configure here.

- Add vision.md with north star: "The standard testing framework for AI Driven Development and software agents"
- Add vision statement prominently to README
- AIDD framework already initialized with ai/ folder structure

https://claude.ai/code/session_0135XoydQ5XAwSUrt6mrEdr6
Create comprehensive task epic for implementing AI-native testing capabilities:
- Migrate PR #378 ai/ folder to riteway-ai/
- Build prompt compilation system for downstream use
- Implement riteway ai CLI command
- Add test output recording in ai-evals/
- Support rich TAP format with media embeds
- Full unit and e2e test coverage

Epic includes 9 sequential tasks with clear requirements and success criteria.

https://claude.ai/code/session_0135XoydQ5XAwSUrt6mrEdr6
- Clarify Riteway as assertion style and philosophy
- Highlight AI-native testing capabilities
- Introduce upcoming riteway ai CLI for prompt evals
- List modern tool compatibility (Vitest, Playwright, Claude Code, Cursor, Antigravity)
- Emphasize token efficiency ("fraction of the code")

https://claude.ai/code/session_0135XoydQ5XAwSUrt6mrEdr6
Key corrections:
- Vision: Enable users to test THEIR prompts like code (not test Riteway itself)
- Remove Phase 1 context references (already complete)
- Clarify prompt compilation: Riteway prompts for user import in their test suites
- Add test assertion flow: callSubAgent → iterate requirements → infer assertions
- Add browser rendering for test output
- Fix parsing approach: Don't parse SudoLang - pass whole file to agent
- SudoLang files are prompts (markdown, frontmatter, etc.) - treat as opaque

https://claude.ai/code/session_0135XoydQ5XAwSUrt6mrEdr6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants