Results for “adversarial-panel”

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.