Convert consented interview notes into an evidence-led brief with claims a human can trace.
This guide proposes a workflow to synthesize recurring customer evidence for a product decision. It is a planning pattern, not a claimed firsthand test, guarantee, or substitute for professional judgment.
You need redacted notes, an agreed research question, and permission to process the material. Do not paste passwords, API keys, health information, government identifiers, or unredacted customer/employee data into an AI service unless your organisation has explicitly approved that processing.
Input: interview notes and the question being decided.
Expected output: a one-page decision brief with attributed themes.
Tool availability, model behavior, plan limits, and terms can change. Check each vendor's current documentation and your organisation's account settings before configuring a workflow.
Write one sentence describing the decision this work must support: a one-page decision brief with attributed themes. List what is confirmed, what is unknown, and who can approve a final version. Put source links beside material claims; generated text is never the source of a claim.
Create an input packet containing interview notes and the question being decided. Remove names, direct contact details, account credentials, and any material that is not needed for this task. For example, use a source link or internal record ID in place of a pasted confidential document. State what the output must not do: it must not make a decision about a person, publish automatically, or represent an uncertain statement as confirmed.
Handoff: give the bounded brief, input packet, and source folder to the person doing the first draft. That person should be able to explain why every included item is necessary.
Make one row per interview question, then record the exact note or timestamp that supports each theme. Keep contradictory responses in a separate column so a product lead can see where the evidence is mixed.
In ChatGPT, ask for a structured first pass-not a final answer. A useful instruction is: “Use only the material below. Produce headings, an evidence table, open questions, and a draft. Label anything not supported by the material as needs verification.” Attach the source IDs next to the relevant paragraph or row.
Read the result line by line against the input packet. Delete claims that cannot be traced, and separate a useful hypothesis from a decision. The working output at this point should be a source-linked draft, not a polished asset.
Handoff: pass the draft, source links, and unresolved questions to the domain reviewer. Ask the reviewer to respond with corrections, missing context, and an explicit go/no-go on any sensitive claim.
Use Claude to organise the reviewer’s changes into three groups: required corrections, choices the accountable owner must make, and optional improvements. Do not ask the model to resolve a disagreement or infer approval. The accountable owner decides which version becomes the approved working copy.
Only then use Notion AI to make the requested output: a one-page decision brief with attributed themes. Keep the source-linked working copy alongside the formatted version. If a handoff changes format-for example, from notes to a deck, a prototype, or an automated message-compare the two versions for dropped qualifiers, altered numbers, and misleading visual emphasis.
If automation is part of the final step, configure a named human approval before anything is sent, published, or changes a record. Include a stop condition, an error alert, and a way to reverse a partial action without deleting the evidence trail.
Handoff: the accountable owner signs off on the final a one-page decision brief with attributed themes.
Before release, confirm:
AI can omit context, produce plausible errors, and reflect bias in the material it is given. This workflow is unsuitable for autonomous decisions about people, regulated advice, or irreversible actions. Start with a small sample and inspect usage-based charges, generation credits, storage, and paid-seat limits before scaling.