feat(website): FAQ + definition content, orchestration-aligned (extracted from #12)#13
Merged
Conversation
FAQ section + FAQPage JSON-LD, 'What is a meta-harness?' definition H2, hidden keyword H1 decoupled from dot-canvas wordmark, README reframe, new meta description. Title stays 'Meta-Harness 101' to avoid a second identity change during Google re-evaluation.
…ning Site's subject is the orchestration sense (layer above harnesses: cross-repo coordination, session memory, policy), not the Stanford paper's optimization sense. Rewrite FAQ answers, definition lead, hidden H1, meta description, two-senses section (orchestration first + focus), README back to layer-above wording. Paper disambiguation FAQ now draws the distinction instead of claiming same-idea.
✅ Deploy Preview for nrwl-harnesstools ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
- Answer section now owns the two meanings (orchestration vs optimization), each with its own visualization - New HarnessOptimizationLoop animation: proposer/candidate-harness/experience- filesystem outer loop from the Stanford Meta-Harness paper - Capabilities section refocused on orchestration meta-harnesses - Fix pre-existing unused-const typecheck errors in two kernels
- Two meanings laid out as text-column + full-size viz rows (capabilities row pattern), orchestration badged as the site's focus - HarnessOptimizationLoop: DOM sizes in cqw so boxes keep world proportions at any width (fixes overlap at column/mobile widths); boxes pinned to world rects so arrows land on their edges; label shift - Capabilities: drop separator line, de-duplicate orchestration-focus copy
- Scores were four different agents from the paper's TB2 leaderboard posed as one run's candidates; now illustrative unitless scores with an early regression, matching the Appendix A trajectory shape. 'pass rate %' -> 'score', end label no longer claims 'best of 4 candidates' - Log arc lands on the filesystem box's right edge (mirrors read arc) - 'proposes new harness code' label moved clear of the harness box - Outer frame gets the same surface fill treatment as MetaHarnessLayers
max-w-2xl (672px) too narrow for the longer subtitle at text-3xl; bump to max-w-4xl + text-balance so narrow viewports wrap evenly.
juristr
marked this pull request as ready for review
July 24, 2026 10:19
vsavkin
approved these changes
Jul 24, 2026
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
2 participants
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
Extracts the additive SEO content from #12 while keeping the current
<title>("Meta-Harness 101: The Layer Above AI Agent Harnesses") — a second title change days after commit 3a27701 would restart Google's re-evaluation mid-SERP-shakeup. All copy is realigned to the site's confirmed orchestration positioning (layer above harnesses: cross-repo coordination, session memory, policy), not the Stanford paper's optimization sense that #12 assumed.FaqV3.astro) with FAQPage JSON-LD built from one array; includes Stanford-paper disambiguation ("related, but different") and spelling-variants Q&AAnswerV3.astro<h1>("the layer above AI agent harnesses"), dot-canvas wordmarkaria-hiddenSupersedes #12.
View session information ↗