td-60191d

Ingest Shopify app store reviews into merchant-knowledge

closed task P2 Parent: td-5a8ff4
Created Mar 22, 2026 9:06 AM Updated Mar 23, 2026 1:30 PM Closed Mar 22, 2026 10:20 AM
Description
Import ReferralCandy's Shopify app store reviews (~1000+) into the merchant-knowledge repo. Reviews provide unfiltered user sentiment, feature requests, pain points, and competitive mentions from active merchants. Scope: export reviews, store structured data, embed for semantic search, optionally link to existing merchant profiles. Key design questions: 1. Export method: Shopify Partner API? Scrape? Manual CSV? 2. Storage format: JSON per review or bulk JSONL? 3. Schema: reviewer name, store name, rating, date, title, body, RC response 4. Profile linking: match reviewer store to existing merchant profiles 5. Embedding: add to same embeddings.npz or separate vector store? 6. MCP tools: extend merchant_search with review data? New review-specific tool? Privacy: review content is publicly visible on Shopify, so no PII concerns.
Handoff
Done
Session Log (6 entries)
Mar 22, 9:06 AM
lg-87a53fd2 ses_9e4920
progress
SCOPING: Shopify app store reviews for ReferralCandy. DATA SOURCE: - Shopify app store page: publicly visible reviews - Shopify Partner API has a reviews endpoint (GraphQL) - Alternative: apps like Appfigures or manual CSV export from partner dashboard PROPOSED ARCHITECTURE: - reviews/ directory in merchant-knowledge repo - reviews/reviews.jsonl — one JSON object per review - Schema: {id, store_name, store_url, reviewer_name, rating, date, title, body, rc_response, rc_response_date, linked_merchant_id} - reviews/index.md — summary stats (avg rating, rating distribution, top themes) EMBEDDING STRATEGY: - Add reviews to the same embeddings.npz (unified vector space) - Each review becomes a document: 'Review by [store] ([rating] stars): [title]. [body]' - Tag metadata with source='review' so semantic search can distinguish from call transcripts - Estimated: if 1000 reviews, adds ~1000 docs to the 400 existing = 1400 total - Build time still <1 min with local model MCP TOOL OPTIONS: 1. Extend merchant_semantic_search — reviews show up alongside transcript matches (preferred — one search surface) 2. Add merchant_reviews(query, rating_filter, limit) — dedicated review search tool 3. Both — unified search + dedicated review tool for filtering by rating PROFILE LINKING: - Match review store_name to existing merchant profiles via fuzzy matching - Add linked_merchant_id to review record - When viewing a merchant_profile, could show associated reviews NEXT STEPS: 1. Check Partner API access for review export 2. If no API, scrape public review page or use partner dashboard CSV 3. Build ingest script 4. Add to embedding pipeline 5. Extend MCP server
Mar 22, 9:59 AM
lg-b8e20ade ses_11e343
progress
Started work
Mar 22, 10:20 AM
lg-d7c89dc9 ses_a29fc2
progress
Completed review ingestion: - Scraped 1,505 reviews from Shopify app store (146 pages) - Stored in reviews/reviews.jsonl with normalized dates - Built reviews/index.md with summary stats - Extended build-embeddings.py: 1,613 docs (122 profile + 1,491 review) - Added merchant_reviews() tool to MCP server - Updated semantic search for mixed profile+review results - Commits: merchant-knowledge 20bd1f2, b3efa58; product-toolkit f89c360
Mar 22, 10:20 AM
lg-f69102b6 ses_a29fc2
progress
Submitted for review
Monday, March 23, 2026
Mar 23, 10:17 AM
lg-0bf90118 ses_a29fc2
progress
Session summary: scraped 1505 reviews, built scraper + MCP tool + embeddings + themes synthesis. Weekly cron (rc-review-sync) installed.
Mar 23, 1:30 PM
lg-5f3a90bc ses_1dc5f1
progress
1505 reviews, clean schema, MCP tool + embeddings rebuilt. Good quality.
Git State
Started 79d2a5c (master) Current 79d2a5c (master)
Sessions Involved