Agentic WoW · by NPU Labs
A way of working for agent-led delivery.
The feature-driven framework we use to build RapportIQ, with a compounding memory loop that keeps human and AI agent teams moving in the same direction. Now available for your team to adopt.
What you get
For your teamCoherent delivery
Work stays right-sized. Nothing sprawls. Nothing gets lost between sessions.
Release rhythm
Small features close, often. The team builds momentum instead of debt.
Compounding memory
Every cycle ends smarter than it started. Your project remembers what it learned.
Humans and agents, same loop
AI teammates plug in without breaking the shape of the work.
The loop
Feature → Plan → Build → Memory.
Four steps that compound. Each cycle ends with the project knowing more than it did at the start, so the next cycle starts further ahead.
Feature
A spec sized for delivery: user journey, rules, validation.
Plan
Tasks decomposed to the right size. L and XL get split.
Build
Code, tests, and decisions tracked in the plan.
Memory
Wrap-ups compound into durable project context for next time.
Sizing
L and XL are hard stops.
Every epic, feature, and task carries a t-shirt size. L or XL items must split before work starts. No quietly bloated tasks, no sprawling features that never finish.
- XSTrivial changeGo
- SSmall contained changeGo
- MStandard piece of workGo
- LToo big. Must split.Split
- XLWay too big. Must split.Split
Tooling
Skills that enforce shape, not bureaucracy.
/wow-refine-featureRight-sizes epics by feature count and features by distinct user-observable behaviour. Sketches candidate split shapes when something is too big.
/wow-refine-planRight-sizes plan tasks. L or XL tasks must split into 2-N concrete sub-tasks. Bloated plans escalate back up to a feature split instead of papering over it.