docs(catalog): claim the QA slot — Conversation QA & coaching as a paid module (HT-96) - #106
Merged
Merged
Conversation
…id module (HT-96) The catalog had ~22 paid line items and nothing QA/quality-scoring shaped. §1's rule is one-way asymmetric — free -> paid never happens — so an unclaimed slot is one accidental free shipment away from being permanently unmonetizable. Claiming it is the reversible direction; paid -> free stays open. QA sits next to three existing entries, so the entry states each boundary rather than leaving it to be re-litigated: - not §2.2's free satisfaction ratings (customer's verdict vs. operator's rubric on their own team's work) - not the sentiment-analysis facet in this same section (sentiment reads the customer's mood; QA evaluates a reply against a human-maintained rubric and carries its own review workflow) - not §3.3's wallboards (QA scores conversations; analytics aggregates them) Out-of-process on the shipped substrate — conversation.reply_sent, assistant API read, notes write, own review UI on the design pack (HT-95). No new core hook, so the build sequence is unchanged. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThe 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. ChangesConversation QA catalog
Estimated code review effort: 1 (Trivial) | ~3 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
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.
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:
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