Product operations
AI agents the whole product team runs, and the feedback framework the company adopted as its standard.
What I've done
- Moved product operations onto agentic workflows: research and data analysis, customer feedback triage, documentation updates and formatting, specification to tickets
- Wrote each one as a reusable specification the whole product team runs
- Put a measured accuracy loop behind the workflow that touches customer-facing documentation
- Reinvested the time it returns into discovery
- Ship production code alongside the engineers, from interface fixes to architecture changes
- Designed 3F, the feedback framework the company adopted as its standard: every customer request attaches to the problem behind it
Rough size
- Agents in daily use16
- Recurring workflows replaced6
- Product team running them16 people
- Company size110 people
Impact metrics
- 1 day+
- given back every week to each product manager (10 hours)
- 1 in 5 → 1 in 12
- documentation errors, after the accuracy loop
- 90s → 5s
- dashboard load time, after a fix I shipped to production