Remove unsourced performance claims from README and package summary - #13
Merged
Conversation
…rounded language only Marketing flagged the 'sub-millisecond latency for most requests' tagline as contradicting our own tier table. Rather than swapping one unsourced number for another, all quantitative performance claims (per-tier timings, ~85% catch rate, ~10-15% escalation share) are replaced with qualitative, architecture-grounded statements until published benchmarks exist. Applies to the README tagline, tier diagram, and package summary. Co-Authored-By: Claude Fable 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Follow-up to #12 from the marketing review: the tagline claimed "sub-millisecond latency for most requests" while the tier table itself showed most traffic at ~15-50ms. Rather than replacing one unsourced number with another, this removes all quantitative performance claims (per-tier timings, "~85% of prompt injections", "~10-15% of traffic") and replaces them with qualitative, architecture-grounded language: local tiers are free with no LLM call; the Tier 3 judge is the only tier with token cost and runs only on escalation. Numbers return when we publish benchmarks to back them.
Touches README (tagline + tier diagram),
pyproject.tomlsummary, and the[0.2.2]changelog entry (release not yet tagged, so this rolls into 0.2.2).Type of change
Checklist
pytest,ruff check, andruff format --checkpass locally (no Python sources touched)CHANGELOG.mdupdated (under[0.2.2], which is unreleased)docs.humanbound.ai— matching docs-page fix ships via humanbound#47Linked issue(s)
Marketing GitHub-repo review 2026-07-09, item 3.
🤖 Generated with Claude Code