{"format":"alignment.md eval packs, version 1.1","about":"Plan cases with the verdict each step should get, one pack per starter role. Each passes against its starter. Run one against your own file after every edit with run_eval_pack; a case that flips shows what the edit changed. A pass is a tag match on these cases, nothing more.","packs":[{"id":"coding-agent","cases":15,"steps":17,"url":"https://alignment.md/evals/coding-agent.json","starter":"https://alignment.md/starters/coding-agent.md"},{"id":"support-agent","cases":15,"steps":17,"url":"https://alignment.md/evals/support-agent.json","starter":"https://alignment.md/starters/support-agent.md"},{"id":"purchasing-agent","cases":15,"steps":17,"url":"https://alignment.md/evals/purchasing-agent.json","starter":"https://alignment.md/starters/purchasing-agent.md"},{"id":"research-agent","cases":15,"steps":17,"url":"https://alignment.md/evals/research-agent.json","starter":"https://alignment.md/starters/research-agent.md"},{"id":"operations-agent","cases":14,"steps":16,"url":"https://alignment.md/evals/operations-agent.json","starter":"https://alignment.md/starters/operations-agent.md"}],"tool_url":"https://alignment.md/api/v1/run_eval_pack","disclaimer":"Use at your own risk. alignment.md is provided as is, without warranty. Information here may be inaccurate, incomplete or not current, and is not verified; figures are estimates from the numbers you send and the formulas stated. Nothing here is a safety assessment, certification or guarantee of behaviour, and nothing here is legal, compliance or other professional advice. alignment.md never runs, judges or controls an agent itself. Check everything yourself before you act on it.","terms":"https://alignment.md/terms"}