responsibleai/ASSERT

Requirement-driven evaluation harness for AI agents and LLM applications. Generate behavior-specific test cases, run them against any target (hosted models, callable wrappers, OTel-traced agents), and inspect local-first artifacts.

Latest release v0.3.0 — ASSERT v0.3.0 Release · 4 Sept 2026

6 files for Claude Code, Cursor, GitHub Copilot, Codex and OpenCode: run-assert-eval, cursorrules, ASSERT copilot-instructions.md, ASSERT AGENTS.md and 2 more — 6,087 tokens loaded in every session.

Open on GitHub responsibleai.github.io

Instructions

ASSERT copilot-instructions.md .github/copilot-instructions.md A 478 tok
ASSERT AGENTS.md AGENTS.md A 5,349 tok
ASSERT CLAUDE.md CLAUDE.md A 180 tok

Cursor rules

cursorrules .cursorrules A 80 tok

Skills

run-assert-eval .claude/skills/run-assert-eval/SKILL.md A 181 tok

Commands

run-assert-eval .github/prompts/run-assert-eval.prompt.md A 125 tok

These files are responsibleai/ASSERT's own configuration — they tell Claude Code, Cursor, GitHub Copilot, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.