| # Decisioncraft tutorials |
|
|
| Each completed milestone includes reproducible commands, their purpose, alternatives, troubleshooting and evidence limits. Read the chapters in order: later measurements depend on the data and software boundaries established earlier. |
|
|
| | Milestone | Status | What you learn and why it comes here | Tutorial and evidence | |
| | --- | --- | --- | --- | |
| | 0 — Kickoff | Verified | Define routing labels, validate strict inputs and outputs, lock the CPU environment, and pin upstream source before executing it. | [Kickoff tutorial](01-kickoff.md), [source inspection](../../reports/kai-inspection.md) | |
| | M1 — Feasibility | Verified | Establish actual inference, differentiable classification, intended parameter updates and fresh-process reload before investing in a dataset or training study. | [Feasibility tutorial](02-feasibility.md), [measured report](../../reports/m1-feasibility.md), [portable evidence](../../reports/m1-summary.json) | |
| | M2 — Data and benchmark | Verified synthetic study | Write consistent labels and group related scenarios before splitting; create an independent holdout that later model choices cannot contaminate. | [Data tutorial](03-data.md), [label policy](../labeling.md), [independent review](../../reports/m2-review.md) | |
| | M3 — Baselines and adaptation | Verified selection study | Compare rules, MiniLM, unchanged Kai and adapted Kai under common inputs; use selection data to choose among measured alternatives. | [Adaptation tutorial](04-adaptation.md), [measured results](../../reports/m3-results.md), [independent review](../../reports/m3-review.md) | |
| | M4 — Calibration and protocol | Verified; protocol frozen | Fit probabilities and routing thresholds on separate calibration data, then freeze the analysis before observing final results. | [Calibration tutorial](05-calibration.md), [measured report](../../reports/m4-calibration.md), [fitted policies](../../reports/m4-summary.json) | |
| | M5 — Evaluation and integration | Verified | Measure unseen-case routing, uncertainty and resource costs, and demonstrate integration without shell execution or inflated claims. | [Roadmap: M5](../roadmap.md#m5--evaluate-the-frozen-study-and-demonstrate-integration); tutorial accompanies the final report and working demonstration. | |
| | M6 — Reproducible release | Planned | Package exact software/model identities, document limitations, and verify installed inference from freshly downloaded authorized releases. | [Roadmap: M6](../roadmap.md#m6--package-and-release-the-verified-result); tutorial accompanies the verified release. | |
|
|
| Planned rows describe objectives, not completed work or runnable future commands. A chapter becomes verified only after its instructions agree with the implementation and saved evidence. The [roadmap](../roadmap.md) defines the acceptance gates; plan.md (private development record) identifies the current milestone. A passing milestone can expose a limitation or a negative result without requiring a claim of improved model quality. |
|
|
