Research a question

Reference note: The release-pinned local workflow guide retains older optional-extra installation instructions and describes forms intake as future work. Those statements conflict with the 1.3.0 package metadata and released GUI. Use Get started and Dependencies and reference for 1.3.0 setup. Treat that older guide as an input-limit/design reference.

Use the isolated environment and release example checkout from Get started. R names that checkout.

What can you check in a local source?

Prerequisite: A normal Harness 1.3.0 installation includes rag and verify. E = copied local-workflow example directory.

1. Run: attune-harness retrieve "quartz retention policy" --corpus "$E/project" --output "$E/retrieval-report.json"
2. Read retrieval-report.json, then project/reference.md. Inspect both returned sources.
3. Run: attune-harness verify "$E/project/guide.md" --context "$E/context.json" --output "$E/verification-report.json"
4. Read verification-report.json. Check status, passed, coverage and semantic_ran.

Expected: Two matching sources. Verification shows “verified”, passed true and one link claim.

Limit: semantic_ran is false. This example establishes link validity, not policy correctness.

With the release checkout R from the previous section, copy its example into a new directory outside that checkout. Set E to the absolute copy path:

E="$PWD/training-research"
cp -R "$R/examples/local-workflow" "$E"

Use a fresh copy so report output paths do not replace prior evidence. The query matches guide.md and reference.md; each result carries an excerpt and a source hash. The verification result has coverage.total: 1 and coverage.verified: 1. Its claim kind is links, subject reference.md, at line 3 of the guide. semantic_ran: false rules out a semantic policy verdict. This offline sample makes no model calls. The tutorial's later concepts also cover picking an opportunity, scoped repair and resuming saved work. Read Local verification and retrieval for dependency and input limits.

Verification scope

All four processes ran against installed Harness 1.3.0 on macOS in isolated synthetic tasks. The two browser sequences used fresh headless Chromium contexts. Navigation reached accepted; continuity retained its saved goal after a listener restart and remained draft. Planning returned created, draft, then accepted; it changed no sample source and created no build run. Retrieval returned two matching Markdown sources, and verification passed the single supported link claim with semantic checks absent.

These observations establish those local sample outcomes. They do not qualify Windows, real participant quality, paid-provider behavior or all possible projects. No released code changed for this training update. The broader workspace navigation, specification editor and browser execution/resume designs are outside the 1.3.0 forms boundary.

The released CLI guide, local workflow guide and saved memory guide retain the implementation baseline independently of current development docs.