Field reps finish a meeting, record a two-minute voice note, and move on. Whisper transcribes it. An open-source LLM structures it into action items, CRM updates, and notes — pushed into the CRM automatically. The rep spends two minutes reviewing, not twenty typing.
Reps finishing back-to-back client meetings had 15–20 minutes of CRM logging per meeting — most skipped it under time pressure.
Voice notes recorded on phones piled up unreviewed — the information existed, but locked inside audio files no one had time to transcribe.
Action items surfaced verbally — "send the revised pricing by Friday" — then forgotten because nothing captured them at the point they were said.
Deal stages reflected the last weekly review, not where things were today — pipeline visibility was always a week stale.
Client preferences, budget signals, and relationship context never made it into the CRM — lost to memory decay by the time anyone looked.
Only ~40% of client meetings were logged at all — the ones that were had inconsistent depth.
Four stages. The rep records and moves on; only a two-minute review stands between voice and CRM.
After a meeting or call, the rep records a voice note — phone recorder, WhatsApp, any voice memo app. No new tools or training. The audio is submitted to the pipeline via a simple upload or shared inbox. The rep moves on immediately.
Friction removed: no typing, no form fields, no CRM login at the point of capture.
Whisper transcribes the audio on-premise — no audio or transcript leaves the organisation. The information locked inside the recording becomes searchable, structured text.
Privacy: on-premise STT — client data never reaches a third-party API.
An open-source LLM reads the transcript and classifies every segment: action items (with owner and deadline if mentioned), CRM field updates (deal stage, next meeting, budget, contact changes), and general notes (sentiment, context, preferences). Output is structured JSON — not a blob of text.
Triggers Stage 4: structured output sent to the rep for confirmation.
The rep receives a structured summary: action items with suggested owners and due dates, a preview of CRM fields about to update, and the general notes. They edit anything wrong, confirm, and the CRM is updated. Total time: under two minutes.
Result: action items auto-assigned; CRM data current the same day.
| Metric | Before | After |
|---|---|---|
| Post-meeting logging time | 15–20 minutes manual typing per meeting | ~2 minutes — review structured output, confirm |
| Meeting capture rate | ~40% — most meetings never logged under time pressure | 100% — voice note takes 2 minutes at the car door |
| Action item tracking | Verbal, buried in email threads or forgotten entirely | Auto-extracted, assigned with due dates, visible in CRM |
| CRM data freshness | Updated at weekly review — always a week stale | Updated same day — pipeline reflects today's reality |
| Data privacy | Notes typed into cloud SaaS — client data on third-party servers | On-premise — audio and transcript never leave the org |
| Logging consistency | Variable — depth depended on time the rep had | Consistent structure every time — same fields, every meeting |
"The note should take less effort than saying it."
The constraint was not capability — reps knew what needed logging. The constraint was friction. Fifteen minutes of structured typing at the end of a full day is fifteen minutes most reps don't have. So it doesn't happen.
The voice note removes friction at the point of capture; the STT and LLM pipeline does the structuring the rep would otherwise do by hand. What's left for the human is judgement — reviewing, correcting, confirming. The open-source LLM wasn't a cost decision, it was a data decision: client meeting content is sensitive, and running classification on-premise means it never touches an external API.
A spa manager records a 90-second note after speaking with a guest. Preferences ("prefers deep tissue"), complaints ("room temperature"), and follow-up requests are extracted automatically and logged against the guest profile — before the manager reaches the next guest.
After a session, a therapist records a brief note on client progress and technique feedback. The pipeline structures it into session notes and follow-up reminders — keeping records current without administrative write-ups after a full day.
A client mentions the annual membership or asks about a new treatment. That signal, captured verbally, becomes a CRM action item: "Follow up on membership enquiry — budget resets in March." In the system before the rep is off the call.
Notes from supplier conversations — pricing discussed, delivery terms, decision dates — are structured and logged automatically. The follow-up action is created at the point the conversation happens, not pieced together later.
90-minute AI Opportunity Audit. No pitch — just findings you can act on.