EXPERIMENT·10 DAY BUILD·MAR 2026
AI-assisted decision log
A lightweight framework for turning rough product thinking into reusable decision records.
Overview
This experiment tests whether a lightweight decision log — assisted by AI for structuring context — can turn messy product judgment into records teams can reuse later.
The problem
Product decisions often live in Slack threads, meeting notes, and memory. When context disappears, teams re-litigate the same tradeoffs and lose the rationale behind prior calls.
Approach
I defined a minimal decision schema (context, options, criteria, outcome), then used AI to help draft and normalize entries without forcing a heavy process. The goal was speed of capture with enough structure to stay useful.
What I built
A capture flow for decision records, AI-assisted summarization of options and risks, and a searchable log that surfaces past decisions by theme and product area.
1
Capture the context
Capture template
2
Structure the options
Decision log
3
Record the decision
Layout module
4
Find it later
Decision log
What I learned
Key takeaway
AI is most useful when it reduces friction to write things down — not when it tries to make the decision for you.
What's next
Add tagging by initiative, link decisions to outcomes, and experiment with weekly digests for stakeholders.
Tech stack
- NNotion
- OOpenAI
- ZZapier
- LLinear
More from the Playground
Prototype
Calmo Cafe — a reservation flow that skips the early SaaS bill
I built a branded site and request-to-confirm booking flow for a friend opening a café in Toronto, both to keep him off OpenTable fees before the room was proven and to learn a real stack end to end.
Tool
Field research capture template
A reusable structure for synthesizing interview notes into product actions.
Prototype
Portfolio experimentation system
Testing modular layouts, storytelling, and signal design for a product portfolio.