Proposal assistant for services
Discovery notes become CRM notes, open questions and proposal outlines for review.
Case note
The implementation was treated as a small operating system: visibility first, ownership next, automation only after the workflow was clear.
The starting point
Proposal creation depended on scattered notes, memory and one senior person. The bottleneck was not writing a perfect proposal automatically; it was turning discovery into a structured first draft that could be reviewed quickly.
The important signal was not that the team was working badly. The issue was that work depended on memory, copied data, parallel system checks and priority decisions without a shared source of truth. The first value was turning invisible work into a visible workflow.
The implementation
Ductio created a meeting-to-proposal workflow. Transcripts or notes are converted into a discovery brief, scope signals, assumptions, open questions and a proposal outline. External-facing content stays in human review.
The scope stayed deliberately small. Rules cover repeatable work, AI summarizes or classifies where free text adds context, and sensitive decisions remain in human review. AI as support inside the process, not as autopilot.
What was used
Tooling was chosen from the process outward, not from a pre-decided technical preference. Each piece needed a clear owner, a stable integration path and a simple way to inspect errors.
In practice, the build combined Meeting transcript, CRM, Google Docs, AI extraction, Approval task, Make. The tools visible to the team stayed close to their daily work, while integration logic was documented and kept separate from sensitive commercial decisions.
The improvement showed up in daily work.
Rather than treating the result as a dashboard, the team felt it in three specific moments: less manual preparation, less context hunting, and fewer doubts about who needed to act.
Prep time: Typical discovery-to-draft cycle moved from 150 min to 45 min.
Missing notes: CRM context gaps moved from Frequent to Rare.
Review quality: Proposal review readiness moved from Manual to Structured.
What changed after launch
The client kept the commercial judgment inside the team while removing the slow blank-page step. CRM context and proposal context now come from the same structured artifact.
The most valuable change was operational calm. The team stopped chasing fragments and started working from a shared sequence: intake, context, decision, action and evidence. 70% faster prep
The workflow in one line
How it was built
The system processes transcript text, extracts operational entities, writes a normalized brief, updates CRM notes and creates a proposal task with checklist sections for scope, risks, pricing and approvals.
The stack was pragmatic: Meeting transcript, CRM, Google Docs, AI extraction, Approval task, Make. Tools were chosen for ownership, integration and maintainability, not for theater. The result is a system the team can understand and operate.
What was delivered
- Call summary
- CRM note
- Proposal outline
- Approval checklist
- Proposal preparation dropped from 2-3 hours to 35-50 minutes.
- Scope, assumptions and open questions became easier to review.
- CRM notes were generated from the same source as the proposal draft.
