Agent context
LaunchDarkly models
3 SQL models that turn the raw LaunchDarkly 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
- 4Raw tables
- 4Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Context activityHow many contexts each environment has seen, and how many were active recently. LaunchDarkly bills client-side usage on monthly active contexts, so the 30-day column is the one to watch against your plan.grain: one row per project x environment x context kind (current state as of the last sync) · 3 raw tables
- Flag health by projectFlag debt per project: how many flags are live, how many of those are temporary, how many are overdue for cleanup or have nobody responsible for them.grain: one row per project (current state as of the last sync) · 2 raw tables
- Flag inventoryEvery feature flag with its age, lifecycle state and owner: the flag list in LaunchDarkly, with the columns you need to find flags that should be cleaned up.grain: one row per project x flag key (current state as of the last sync) · 2 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 LaunchDarkly's own reports first. Each model's notes say what the synced data can and can't support.
Connect LaunchDarkly.
Your agents start with context.
Sync LaunchDarkly to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.