# Groq Runbook This runbook gives the exact commands for the main Groq experiment pairs used by the framework. ## Before Running Set the Groq key in PowerShell: ```powershell $env:GROQ_APIKEY="your_api_key_here" ``` The framework also accepts `GROQ_API_KEY`. ## Baseline and Defended Runs ### HackAPrompt override pair Baseline: ```powershell python -m prompt_injection_framework.orchestration.run_experiment --config configs/hackaprompt_override_25.yaml ``` Defended: ```powershell python -m prompt_injection_framework.orchestration.run_experiment --config configs/hackaprompt_override_25_mitigated.yaml ``` ### TensorTrust hijacking pair Baseline: ```powershell python -m prompt_injection_framework.orchestration.run_experiment --config configs/tensortrust_hijacking_25.yaml ``` Defended: ```powershell python -m prompt_injection_framework.orchestration.run_experiment --config configs/tensortrust_hijacking_25_mitigated.yaml ``` ## Comparison Commands After each pair finishes, compare the saved summaries. ### HackAPrompt comparison ```powershell python scripts/compare_runs.py --baseline results//summary.json --defended results//summary.json --output results/comparisons/hackaprompt_override_25_groq.json --markdown-output results/comparisons/hackaprompt_override_25_groq.md ``` ### TensorTrust comparison ```powershell python scripts/compare_runs.py --baseline results//summary.json --defended results//summary.json --output results/comparisons/tensortrust_hijacking_25_groq.json --markdown-output results/comparisons/tensortrust_hijacking_25_groq.md ``` ## Operational Note Groq rate limits can temporarily slow repeated runs. The current adapter now includes retry/backoff handling for temporary `429` responses, so the runner is more resilient during real experiments. ## What To Keep For each run pair, save: - baseline `run_id` - defended `run_id` - comparison JSON - comparison Markdown - a short note on any surprising ambiguous or review-worthy cases