docs(catalog): claim the QA slot — Conversation QA & coaching as a paid module (HT-96)

[zaridan]

One entry in specs/modules/catalog.md §3.1, plus a revision-log line. No code.

Why now

The catalog had ~22 paid line items and nothing QA/quality-scoring shaped. §1's rule is one-way asymmetric — "free → paid never happens; paid → free stays possible" — so an unclaimed slot is one accidental free shipment away from being permanently unmonetizable.

Claiming it is the reversible direction. If QA later belongs in core, that move stays available; the reverse never does. Cheap now, impossible to undo later.

The boundaries, stated in the entry

QA sits next to three things already in the catalog, so the entry draws each line rather than leaving it to be re-litigated later:

Not this	Because
§2.2's free satisfaction ratings	That's the customer's verdict, freely collected. QA is the operator's rubric applied to their own team's work.
The sentiment-analysis facet named in §3.1 itself	Sentiment reads the customer's mood. QA evaluates an Agent's reply against a human-maintained rubric and carries its own review workflow — a module, not a facet.
§3.3's wallboards & advanced analytics	QA scores individual conversations; analytics aggregates whatever QA produced.

That third line matters for sequencing: wallboards without QA has nothing to aggregate.

Shape

Out-of-process on the substrate that already shipped — subscribes to conversation.reply_sent, reads the thread via the assistant API, posts results back as internal notes, hosts its own review UI on the design pack (#104).

No new core hook, so §4's build sequence is unchanged and this needs no §7 exception.

Backing analysis, including the verified separability audit of the scoring engine, is on HT-96.

🤖 Generated with Claude Code

Summary by CodeRabbit

• Documentation
  • Added the “Conversation QA & coaching” module to the paid catalog.
  • Documented rubric scoring, threshold and SLA criteria, human review workflows, and evidence-based coaching.
  • Clarified how the module differs from satisfaction ratings, sentiment analysis, and wallboards or analytics.
  • Updated catalog totals and changelog details.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 57817932-cbb4-4e82-9b90-c42d044f8c2c

📥 Commits

Reviewing files that changed from the base of the PR and between aca83cb and 4103d83.

📒 Files selected for processing (1)

• specs/modules/catalog.md

---

📝 Walkthrough

Walkthrough

The paid module catalog adds Conversation QA & coaching, defining its rubric, human review workflow, scope boundaries, integration behavior, and review UI. The changelog records the addition and updates paid-module totals and Intelligence cluster counts.

Changes

Conversation QA catalog

Layer / File(s)	Summary
Module definition and catalog accounting specs/modules/catalog.md	Adds the Conversation QA & coaching module with scoring, review, scope boundaries, and out-of-process integration details; updates the changelog and catalog counts.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

• Helpthread/helpthread#75: Earlier paid-module catalog additions and changelog updates in the same specification.
• Helpthread/helpthread#82: Related paid-catalog scope, cluster, and count updates.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly reflects the main change: adding Conversation QA & coaching as a paid catalog module.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch docs/ht-96-qa-catalog-slot

---

_{Comment @coderabbitai help to get the list of available commands.}