AI Product Managementnow
Orient to the calculation-path coach
Define the active Standard Trainer direction, its learner outcome, and the authority boundary between deterministic tools and AI assistance.
product-boundaryauthorityCAIE-9701
Validated Study Items
Learn by need, not by calendar.
Filter the Git-backed catalog across five focused tracks. Programs provide order when you want it.
11 Study ItemsCanonical content from docs/study
AI Product Managementnow
Frame the learner failure with evidence
Translate calculation-process observations into a testable problem statement and interview plan.
discoveryinterviewsproblem-framing
Calculation Trainernow
Model solution graphs and student steps
Represent the canonical Kp calculation path, structured student work, example tracing, and model tracing as separate inspectable objects.
solution-graphsstructured-stepstracing
Calculation Trainernow
Freeze authority, policy, and provenance
Bind a curated problem, solution graph, marking policy, and review state before making correctness or ECF claims.
authorityprovenancemarking-policy
Agent Engineeringnow
Design deterministic validators
Specify reproducible validators for arithmetic, units, expressions, species, dependencies, significant figures, and mark allocation.
toolsvalidatorsdeterminism
Calculation Trainernow
Localise the first invalid step and bound ECF
Align structured work to the solution graph, identify the earliest invalid step, classify misconceptions, and apply bounded error-carried-forward rules.
alignmentfirst-invalid-stepbounded-ECF
Agent Engineeringnext
Route tools with inspectable traces
Design constrained runtime routing across validators, diagnosis, marking, and hint paths without granting the model authority it does not own.
routingtool-callstraces
Calculation Trainernext
Plan hints and reviewed follow-up practice
Turn bounded diagnoses into hint decisions, learner weakness updates, and reviewed next-problem selection.
hintsweakness-modelfollow-up-selection
Product Delivery and Evalsnext
Evaluate components and trajectories
Consolidate the vertical slice with component-level correctness checks and end-to-end trajectory evaluation before claiming readiness.
component-evalstrajectory-evalsCI
Product Delivery and Evalslater
Run bounded learner evidence sessions
Observe real use, separate learning evidence from product and review evidence, and permit only a bounded evidence-backed change.
usabilitylearner-evidencefailure-analysis
Interview Preparationlater
Turn delivery evidence into interview stories
Translate the calculation-trainer work into concise role-relevant stories, portfolio proof, and application evidence without overstating claims.
portfoliointerviewsstory-bank