Agent context
Asana models
3 SQL models that turn the raw Asana 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
- 6Raw tables
- 6Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Open task workloadCurrent open workload per assignee and project: what is open, overdue and due soon. A snapshot as of the last sync, not a history.grain: assignee x project · 4 raw tables
- Project overviewOne row per project: status, owner, team, task progress and overdue work. Recreates the overview Asana shows on a portfolio, as of the last sync.grain: project · 5 raw tables
- Task completionTasks completed per day, project and assignee, with on-time rate and time to complete.grain: completion date (UTC) x project x assignee · 5 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 Asana's own reports first. Each model's notes say what the synced data can and can't support.
Connect Asana.
Your agents start with context.
Sync Asana to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.