Repository navigation
Benchmark: every result as the outcome it gives you, beside the setup it beat - #41
Merged
Merged
Conversation
… it beat The Evidence page is now Benchmark. It opens on one table of outcomes, each against the setup teams run today: 48 of 48 governance scenarios, every out-of-permission action stopped before it runs, 0 of 6 data-theft attempts out of a hijacked agent, 150 of 150 forged records caught, $0.024 against $0.078 per handed-off result, reuse 750 times faster than redoing the work, 42 times fewer tokens for agent memory, a 3.1 times lower worst-case research spend, and one identity check reused by 100 apps for $1.75 against $150. Run dates and per-section method asides are gone from the body; how each result was measured sits in one section for reviewers. A permission revoked mid-job now reads as production behaves: the call in flight is refused with its reason and nothing commits. The offline check points at the latest signed records. /evidence, /benchmarks and /use-cases/authority-at-dispatch open it. 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The Evidence page becomes Benchmark: one outcome table up front, each result beside the setup it was measured against, run dates and method asides out of the body, and how each result was measured in one reviewer section. The mid-job revocation row now matches production (refused in flight, nothing commits).
/evidence,/benchmarksand/use-cases/authority-at-dispatchredirect to/benchmark. Markdown and OpenAPI validation pass; rendered locally on desktop and mobile with every chart loading.🤖 Generated with Claude Code