Agent context
Claimlane models
5 SQL models that turn the raw Claimlane tables into the reports people ask about. Deploy them in Weld and your agent queries the definitions behind every number.
How the set is built
- 5Raw tables
- 5Staging
- 7Core
- 5Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- B2b claim linesEvery product line on every retailer-to-supplier claim, with the supplier's decision grouped into a small set of outcomes.grain: claimlane_account x ticket_id x product_index · 2 raw tables
- B2b claims by monthRetailer claims per brand and claim type per month: volume, the supplier's decisions, and the acceptance rate.grain: month x claimlane_account x brand_name x claim_type · 2 raw tables
- B2c claim linesEvery product on every consumer ticket, with the ticket's type, outcome and the refunds booked against the line.grain: claimlane_account x ticket_id x product_index (one row per claimed product line) · 3 raw tables
- B2c claims by monthConsumer claim volume and refunds per month: how many tickets, of which type, how they were settled, and how much money went back.grain: month x claimlane_account x organization_id x ticket_type x currency · 3 raw tables
- B2c claims by productWhich products come back, why, and what they cost in refunds.grain: claimlane_account x organization_id x currency x product_sku x issue_tag · 3 raw tables
- Weld or dbt
- The same SQL in both dialects. Sync the folder with GitHub Sync, or copy the dbt models into your project.
- Check before you rely on it
- Reconcile a month against Claimlane's own reports first. Each model's notes say what the synced data can and can't support.
Connect Claimlane.
Your agents start with context.
Sync Claimlane to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.