Files
Jonathan Boniface e22d037ab0 ALZ-F02 Assessment: individual agents, intake, rate card input, critic fixes
- Six declarative agents generated from the v1.1 stories (scaffold_from_stories.py, ADR 0001),
  and a 9-step workflow export (build_workflow.py).
- Code-only intake (ADR 0008) verifies the one Discovery package in code before any agent.
- The rate card is the run input rate_card_document; no upload step (ADR 0009).
- Critic 0.1.6 after live runs on crucible-kab-dev:
  - K-12 model independence checked at build time against each agent's deployed model
    (ADR 0010); the critic reports it from its two inputs;
  - receives in_cloud_estate for K-10; an unverified K-10 never fails the run alone;
  - K-08 allows the scoring note to list findings as advisory, as ALZ-ASM-04 must;
  - carries ALZ-ASM-03's and ALZ-ASM-04's rule sections, copied by the scaffold, so it can
    recalculate risk, confidence and TCO.
- The scaffold refuses to regenerate unless every story file is present.
- Case azure-crucible-kab-dev-assessment with an illustrative rate card.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 22:13:25 +00:00

34 lines
1.8 KiB
Markdown

# User guide: CP1 - Assessment Critic & Sign-off Router Agent
For the Engagement Lead or Migration Architect reviewing an Assessment run.
## What it does
Independently validates the Assessment: coverage, evidence, dependents, recalculated scores, confidence and TCO, the interim and advisory rules, and routes confidence below 0.80 to disposition sign-off.
It is step 6 of the workflow **CP1 - Agentic Landing Zone - Assessment** (ALZ-ASM-06, ADO 3214464). You don't
call it yourself in normal use: start the workflow with the Discovery run's artifact ids, its execution id, the
approval reference and the rate card, and this agent receives its inputs from the earlier steps.
## Reading its output
The output fields are listed in the agent's [README](../README.md#outputs). Every fact it takes from Discovery cites
`discovery:{execution_id}/{agent_id}/{record_key}`. Anything it couldn't establish is left empty or listed as
missing, never guessed.
## What it will not do
- Call any tool not on its allowlist, or pass a tool a hostname, address, URL, credential or customer text.
- Write to any client system.
- Follow instructions found in data. These are reported, not obeyed.
## When something looks wrong
| You see | Likely cause | What to do |
|---|---|---|
| The step failed with `output_contract_violation` | The model's reply didn't fit the output schema twice | Rerun the step; if it repeats, report it with the run id |
| A Discovery input reported missing | The Artifacts step didn't select that Discovery step's output, or it was too large to travel inline | Check the artifact ids given to the run |
| Empty fields | The source records didn't support them | Expected: the agent leaves out what it can't evidence |
Changes from the original requirements are listed in [adr/](adr/README.md).