Agent context
HiBob models
3 SQL models that turn the raw HiBob 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
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Employee rosterOne row per person: role, team, manager, employment terms, tenure and time off taken in the last 12 months. HiBob's People directory plus a few derived columns.grain: employee (active and inactive) · 3 raw tables
- Headcount monthlyHeadcount, hires, leavers and turnover per month, department and site. HiBob's headcount and turnover analytics, as a table.grain: month x department x site · 3 raw tables
- Time off dailyTime off taken or booked, per day, person and policy.grain: date x employee x policy type x request status · 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 HiBob's own reports first. Each model's notes say what the synced data can and can't support.
Connect HiBob.
Your agents start with context.
Sync HiBob to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.