Jev call copilot for CurrencyTransfer
Working documents for a live call copilot built on Cloudflare Workers and TypeSafe's Jev model, modelled on the open-source sales copilot and adapted for onboarding and customer-success calls. Read the architecture first; the research documents are its evidence.
Documents
Review now
- Rate objections: your playbook in the system
How the five objections, the qualifying questions, the do-nots and the concession terms map to situations, questions, cautions and the checklist; the approved lines table.
- Call plan designs: E, F, G, H
Round 3 of the live screen: four independent directions around a living call plan. Pick one, or say what to combine.
- Round 3 design brief
The concept of the living call plan, what the screen must do, the anti-patterns from your review, and the four directions.
- Red-pen sheet: real rep lines per move
For each move: the drafted lines, then the phrasings your reps actually use most, with how many calls and reps say them and two verbatim exemplars. This is the sheet the question rounds work from.
- Red-pen sheet: playbook lines
Every line the copilot may show a rep, generated from the policy JSON. 81 draft lines, 9 marked VERIFY. Send me your decisions and I apply them.
- Design board: variant D plus A, B, C
Variant D (live view and review view, from your review) first, then the earlier three layouts. Pick the one to approve.
- Your design review and the answers
Your 25 September feedback verbatim, with a numbered answer to each point.
- Dashboard design system
The written spec: tokens, layout, panels and states. Mockups are shown at the top of the page.
Plan
- Milestone 1 PRD
The otto product requirements document: 78 one-commit stories with runnable acceptance criteria, invariants, risks, and the answered and open questions.
Architecture
- Architecture
The synthesised design: components on Cloudflare, data model, the per-utterance decision loop, curation, evaluation, compliance, and milestone 1.
- Proposal A: fastest proof of concept
Least machinery to get milestone 1 in front of you.
- Proposal B: production-shaped
The shape the system needs in production, with milestone 1 as its first vertical slice.
- Proposal C: data-first
Curation and evaluation loop first; the live dashboard consumes corpus-derived policy.
Research
- Reference copilot dissection
How the open-source Jev sales copilot works, line by line, and what transfers.
- CurrencyTransfer domain brief
Customer journey, product facts, draft question banks and playbooks for onboarding and customer success. Marked DRAFT for review.
- Corpus and curation
Using the historical call corpus: ingestion, Jev quality rubric, the admin curation loop, storage, evaluation harness.
- Speech-to-text options
Whisper vs Deepgram nova-3 on Workers AI, diarisation, costs, and the live verification on a real recording.
- Prior art
Other Jev call copilots, commercial coaching tools, and the ten most transferable ideas.
Reference
- Jev builder's guide
Request and response contract, semantics, Cloudflare integration, patterns, limits and gotchas. Verified against the vendor docs.
Verified so far
Decisions taken
- Milestone 1: upload or pick a recorded call and replay it against a live dashboard: signals, stage, must-say checklist, objection handling, next best move.
- Both scenarios from the start: onboarding (the activation call after the sign-up wizard) and customer success.
- Headline metric: must-say completeness plus risk flags for onboarding; resolution and call health for customer success. No closing probability.
- Suggested lines: pre-approved playbook lines, plus tailored rewrites when Jev verifies them for invented facts, promises and rate predictions.
- Curation: Jev scores every historical call; the admin marks Jev-tagged moments as model, acceptable or avoid.