SStudy ConsoleBackup
← All programs

Program · v1.0.0

Original 10-Day Challenge

The original guided sprint, retained as an optional program rather than the site's top-level structure.

0 of 11 completed
  1. 01
    ai product management

    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.

    Open
  2. 02
    ai product management

    Frame the learner failure with evidence

    Translate calculation-process observations into a testable problem statement and interview plan.

    Open
  3. 03
    calculation trainer

    Model solution graphs and student steps

    Represent the canonical Kp calculation path, structured student work, example tracing, and model tracing as separate inspectable objects.

    Open
  4. 04
    calculation trainer

    Freeze authority, policy, and provenance

    Bind a curated problem, solution graph, marking policy, and review state before making correctness or ECF claims.

    Open
  5. 05
    agent engineering

    Design deterministic validators

    Specify reproducible validators for arithmetic, units, expressions, species, dependencies, significant figures, and mark allocation.

    Open
  6. 06
    calculation trainer

    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.

    Open
  7. 07
    agent engineering

    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.

    Open
  8. 08
    calculation trainer

    Plan hints and reviewed follow-up practice

    Turn bounded diagnoses into hint decisions, learner weakness updates, and reviewed next-problem selection.

    Open
  9. 09
    product delivery evals

    Evaluate components and trajectories

    Consolidate the vertical slice with component-level correctness checks and end-to-end trajectory evaluation before claiming readiness.

    Open
  10. 10
    product delivery evals

    Run bounded learner evidence sessions

    Observe real use, separate learning evidence from product and review evidence, and permit only a bounded evidence-backed change.

    Open
  11. 11
    interview preparation

    Turn delivery evidence into interview stories

    Translate the calculation-trainer work into concise role-relevant stories, portfolio proof, and application evidence without overstating claims.

    Open