Repository navigation
docs(agents): rules for agent tests on real data; Experiment B round 3 - #367
Merged
Merged
Conversation
Rounds 1-2 of Experiment B were simpler than real use: clean questions naming the chat, 10 chats, WireCat without vectors or typo-tolerant search. The page lists the rules for questions, data, setup and scoring; README, CLAUDE.md and the agents index link it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…RULES Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Totals only; per-question rows stay in cli-private. ask.sh takes WF_STATE so the wf store no longer shares the folder wf writes its answers to. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
leemour
force-pushed
the
docs/agent-testing-guide
branch
from
November 14, 2026 01:21
e4f05d7 to
b9b4353
Compare
leemour
changed the title
…earch check by chunk The first scoring left bulk checklists to each scorer; unchanged sheets moved by up to 1.2 points. The meaning-search check now counts a hit only when a returned chunk holds a source message (2 of 6, not 6 of 7). Adds time, cost and tool calls. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Task
Write down how to test an agent on real data, and run Experiment B round 3 by those rules.
Why
Rounds 1 and 2 concluded "a plain export answers as well as WireCat". The owner disagreed, and the setup was simpler than real use in five ways, four of them against WireCat.
What
docs/dev/AGENT-TESTS.md: the rules (questions as the user asks them, mixed forms, variants, the user's data scope, every contestant at its best, blind scoring, scoped conclusions); linked from README, CLAUDE.md andperformance/agents/README.md.performance/agents/source-coverage/README.md: round 3 totals. With the full history of 10 chats: WireCat 13.17 (0 confidently wrong) against the export 15.33, WireCat on the owner's everyday store 7.17, telegram-mcp 5.0. Variants of the same facts: export 11 of 12, WireCat 6.ask.sh: contestantswf/wfh,WF_STATE;score.sh:SCORE_RULES.Testing
pnpm docs:check, cspell, rumdl. Per-question rows are private (cli-private).🤖 Generated with Claude Code