Product-work assistant · In development
From discussions to work ready for review
Not every sentence is a requirement
Illustrative example · fixed sample text · no live AI
Select a candidate to trace it to the discussion. Selection is not approval.
A fictional product discussion
- S1Product leadLinked source
Let's show the current payout status in the first release. Email notifications can wait.
- S2SupportLinked source
Users need to know whether they should wait or contact us.
- S3EngineeringLinked source
We still need to agree how to present manual-review cases.
- S4Product leadLinked source
Yes, keep email notifications out of release one. I'll review the proposed status wording before we commit it.
Review candidates
- D1 / Decision candidateSelected
Keep email notifications out of release one
The discussion sets status visibility as the first-release focus and explicitly defers email notifications.
Review noteCheck that the person speaking had the authority to make this scope decision.
- R1 / Requirement candidate
Explain whether the user should wait or seek help
Support describes a user need. The exact wording and acceptance criteria still need to be agreed.
Source: S2
Review noteThis is not yet an approved user story.
- Q1 / Open question
How should manual-review cases be presented?
Engineering raises an unresolved question. The discussion does not contain an answer.
Source: S3
Review noteKeep the question open instead of inventing a requirement.
A proposed requirement, a confirmed decision and an unanswered question should not become the same kind of task.
What is working, and what comes next
Used in my work
AI-assisted processing of stakeholder discussions into decisions, requirements and open questions.
Being developed
A modular assistant that connects those outputs with the surrounding product-management workflow.
Planned extensions
Routing clarification questions to the relevant people and preparing follow-up drafts with wider team context.
Technical exploration
Local and cloud models, task routing and workflow orchestration.
The workflow is more than a model call
I’m exploring how to separate input preparation, task routing, specialised modules and the model layer. The aim is to carry the right context into each task and keep draft outputs available for review.
Planned architecture
- Input preparation
- Task routing
- Specialised modules
Model adapters: local / cloud
- Draft outputs
- Human review
Preparation can be automated. Responsibility cannot.
The assistant can prepare material for review. Priorities, scope, trade-offs, release decisions and compliance acceptance stay with the responsible people.