Write a PRD
Can the model turn a brief into a spec engineers could build from, including how an AI feature behaves when it is wrong?
Not yet testedMaking product behaviour, uncertainty and eval requirements executable
The task library
Every task is a job PMs actually do in a normal week, with a realistic brief and messy inputs. 9 are in the core suite. The rest are planned, and they’ll join only once the current ones prove they can tell good work from bad.
Define
Deciding what to build and why
Develop product strategy
Can the model make a coherent choice grounded in the evidence, rather than list aspirations?
Not yet testedChoosing where to play and what not to do, from supplied evidence
Build a roadmap
Can the model sequence bets against capacity and dependencies, and explain the order?
Not yet testedSequencing under constraints
Write a GTM plan
Can the model pick a segment, a message and a channel, and say why?
Not yet testedLaunch focus
Discover
Learning from customers and markets
Extract discovery insights
Can the model separate evidence, themes and hypotheses without inventing consensus?
Not yet testedFaithful synthesis of qualitative research
Customer research call guide
Can the model write a guide that uncovers behaviour rather than opinions?
Not yet testedQuestion design
Interview discussion guide
Can the model structure a stakeholder or customer research interview?
Not yet testedInterview structure
Market research
Can the model size and describe a market from supplied sources without fabricating figures?
Not yet testedSource-faithful research
Competitor analysis
Can the model find where competitors are actually weak rather than list features?
Not yet testedCompetitive insight
Design
Shaping the experience
Activation & onboarding review
Can the model find the friction that matters most and prioritise the fixes?
Not yet testedConsequential critique
One-shot prototype
Can the configuration produce a working, constraint-compliant prototype in one attempt?
Not yet testedTurning a spec into a usable interactive artefact
Wireframe generation
Can the model lay out a flow's screens with the right information hierarchy?
Not yet testedInformation hierarchy
Experiment
Testing and reading results
Analyse experiment results
Can the model separate evidence from speculation, identify decision-relevant uncertainty and recommend a sensible next action?
Not yet testedInterpreting results within their limits
Experiment specification
Can the model design a test that could actually change the decision?
Not yet testedTest design
Challenge
Stress-testing ideas
Challenge an idea
Can the model find the strongest reason an idea may fail, backed by evidence?
Not yet testedEvidence-based critique
1000x an idea
Can the model expand an idea's ambition while keeping it tethered to a real mechanism?
Not yet testedAmbitious expansion
Operate
Running launches and reporting progress
Write a stakeholder update
Can the model turn messy project status into an honest update that leads with what the reader needs to know or decide?
Not yet testedHonest, decision-first status communication
Make the launch call
Can the model make a clear go / no-go call from mixed launch evidence, checked against the criteria agreed up front?
Not yet testedDeciding against agreed launch criteria
Agent interaction & voice
Can the configuration hold a consistent product voice across a multi-turn agent session?
Not yet testedVoice consistency
Stick to an agreed plan
Can the configuration complete agreed scope without silently expanding or changing it?
Not yet testedScope discipline across a multi-step build