Agent context
Sprout Social models
4 SQL models that turn the raw Sprout Social 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
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Case resolutionOne row per customer care case with its timings: how long it has been open, or how long it took to close. The case-level detail behind Sprout's case reporting.grain: one row per case · 3 raw tables
- Case volume dailyCases opened and closed per day, with the median and 90th percentile time to close: Sprout's case volume and resolution trend.grain: date_day (UTC) x group_id x queue_id x case_type x case_priority · 3 raw tables
- Message volume dailyDaily message volume per profile and message type: what came in, what went out, how much of it went out through Sprout, and how much became a case. The basis of Sprout's inbox and engagement volume reporting.grain: date_day (UTC) x customer_profile_id x post_type · 2 raw tables
- Team activity dailyMessages each Sprout user sent from Sprout, per day and profile: the volume side of Sprout's team report.grain: date_day (UTC) x sent_by_user_id x customer_profile_id · 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 Sprout Social's own reports first. Each model's notes say what the synced data can and can't support.
Connect Sprout Social.
Your agents start with context.
Sync Sprout Social to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.