# Context: CP1 - Assessment Critic & Sign-off Router Agent For coding agents. People's documentation is in `docs/`. | | | |---|---| | Story | ALZ-ASM-06 (ADO 3214464); v1.1 story files `drafts/cp1/agentic-landing-zone/stories/F02-assessment/ALZ-ASM-06-*` in the engineering hub workspace | | Workflow step | 6 of `../workflows/cp1-alz-assessment-individual.json` | | Inputs | `discovery_documents` <- `p1.parsed_content`, `discovery_files` <- `p1.file_metadata`, `tasks` <- `s1.tasks`, `applications` <- `s1.applications`, `coverage_gaps` <- `s1.coverage_gaps`, `preconditions` <- `s1.preconditions`, `in_cloud_estate` <- `s1.in_cloud_estate`, `profiles` <- `s2.profiles`, `profile_gaps` <- `s2.gaps`, `scores` <- `s3.scores`, `high_risk_tail` <- `s3.high_risk_tail`, `posture_status` <- `s4.status`, `security_findings` <- `s4.findings`, `dispositions` <- `s5.dispositions`, `signoff_queue` <- `s5.signoff_queue` | | MCP tools (read-only) | none | | Model | `gpt-5.4` (`kubernetes/configmap.yaml`) | ## How the prompt was made `prompt.md` is the story's System Prompt and Guardrails, plus generated sections (MCP tools, steps, Discovery documents) at the top and the charter at the end. The rules stay as the story's pseudo-code: a declarative agent has no functions, so the model applies them itself and ALZ-ASM-06 recalculates them (ADR 0001). ## Invariants 1. The reply is exactly `schemas/output.json`. Later steps read its fields by name. 2. Every MCP tool in `agent.yaml` `mcp:` is read-only, from an existing server, and in the story's allowlist. 3. Discovery records are cited `discovery:{execution_id}/{agent_id}/{record_key}`.