Bohea

A phone call becomes a structured spreadsheet row — in about 16 seconds, with zero human touch

Production system for donation-call intake: every incoming call is recorded, transcribed, understood by an LLM, and written to Google Sheets before the caller has put their phone down.

TwilioPythonSpeech-to-TextLLM ExtractionGoogle Sheets APIProduction

The problem

The client received donation pledges by phone. Every call meant a human listening, writing down the amount, the processing fee, and the beneficiary charity — slow, error-prone, and impossible to scale past business hours.

The constraint

No staffed call center, no CRM, no appetite for new software. The output had to land somewhere the team already lived: a Google Sheet. And the system had to run unattended — self-activating on every incoming call, day or night.

The solution

A self-contained daemon on a Linux server, wired into Twilio's webhook:

End-to-end time from hang-up to spreadsheet row: ~16 seconds.

The part that makes it trustworthy: confidence scoring

LLM extraction is never blindly trusted. Every row carries a 0–100 confidence score computed from explicit rules — deductions for an unstated amount, an unclear charity name, hesitation in the caller's voice, or poor audio clarity:

ScoreWhat happens
≥ 90Auto-committed, no review needed
70–89Human spot-check
< 70Flagged for manual review

The AI does the work; the score decides when a human needs to look. That's the difference between a demo and a system you can run a business on.

Proof

Shipped and running in production. Delivered with a handover document covering: how to start and monitor the daemon, the exact Twilio console settings (including the media-auth setting that silently blocks recording downloads), the full field reference, and a step-by-step guide for migrating every credential to the client's own accounts. The client owns the system outright — no dependency on me.

Where else this applies

The same pipeline works anywhere a phone call needs to become structured data: missed-call capture for contractors, after-hours intake for service businesses, order lines, appointment requests. If your business runs on phone calls that someone has to write down — this removes the writing down.

If a machine you build needs an interface, a device connection, or data that has to land somewhere else, tell me what it's costing you now. You'll get an honest read on whether it's solvable, and usually something running to look at. Start here →

← All case studies