When this workflow helps
If you are searching for how to build a GPT for sales discovery notes, first decide who owns the result and where it will be used. A good draft saves preparation time only when the underlying facts are available and a person can inspect the output. This guide is for that specific deliverable; the Custom GPTs for Repeatable Business Tasks hub collects adjacent tasks.
Gather the source material
A consented call transcript, CRM field definitions, qualification criteria, and examples of good notes. Use the current approved version. Remove details that the team is not permitted to place in an AI tool, or use a workspace and access controls approved for that data. Keep a link to the original material so reviewers can trace the result.
Build the first draft
Define a fixed field order: problem, current process, decision process, timing, agreed next step. Teach the GPT to distinguish customer statements from seller assumptions. Start on one representative example, not the entire backlog. If a required fact is missing, ask for a marked gap rather than a plausible completion. Save the output as a draft with the source date and an assigned reviewer.
Starting prompt
Format these discovery notes for our CRM fields. Use only what the prospect said, attach a source excerpt to key claims, and mark missing qualification fields unknown.
Replace the example input with your own approved documents and specify the output format your team actually uses. Ask for a short list of uncertainties alongside the draft. Keep the source and output together during review so a polished sentence does not hide a missing fact.
Review before use
The salesperson checks the transcript and edits the CRM record before saving; do not infer budget or authority. Check names, dates, figures, citations, and commitments against the originals. If a consequential decision or external communication is involved, the designated human owner makes the final call and follows the normal approval path.
Measure whether it worked
Track Time to complete the record and missing or incorrect qualification fields. Compare a small set of completed examples with the previous process. Record corrections, not only time saved; a faster draft that creates rework is not an improvement. Revise the prompt when the same error appears twice.
Next steps
Return to Custom GPTs for Repeatable Business Tasks for related tasks, or use the AI business strategy pillar to decide where this workflow belongs in the wider business.