Agent context
Twilio models
3 SQL models that turn the raw Twilio 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
- 3Raw tables
- 3Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Calls dailyVoice volume, outcomes, talk time and spend per day: the summary in Twilio's Voice Insights and Call Logs.grain: one row per day (UTC, call start) x account x direction x currency · 1 raw table
- Message errors dailyFailed and undelivered messages by Twilio error code: the Errors view in Messaging Insights. The first place to look when delivery rate drops.grain: one row per day (UTC) x account x messaging service x error code · 2 raw tables
- Messaging dailyMessaging volume, delivery and spend per day: the numbers on Twilio's Messaging Insights overview.grain: one row per day (UTC) x account x messaging service x direction x currency · 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 Twilio's own reports first. Each model's notes say what the synced data can and can't support.
Connect Twilio.
Your agents start with context.
Sync Twilio to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.