# Production Operations

Use these artifacts after design begins—not only after launch. They define how a production-agent workflow is promoted, observed, contained, recovered, changed, reviewed, and retired.

| Need | Start with | Output |
| --- | --- | --- |
| Establish a company adoption operating model | [Operate and Scale](https://davidahmann.github.io/applied-ai-field-guide/study/playbooks/03-operate-and-scale/#company-operating-model-centralize-rails-preserve-workflow-accountability) and [workflow portfolio review](https://davidahmann.github.io/applied-ai-field-guide/study/templates/workflow-portfolio-review/) | Named decision rights, shared-versus-workflow capability boundary, temporary delivery substitutions, and proof-to-operation gates |
| Decide whether to promote | [Release gates](https://davidahmann.github.io/applied-ai-field-guide/production-ai-readiness/) | Evidence-backed hold, shadow, canary, bounded-production, or autonomy decision |
| Define runtime evidence | [Telemetry contract](https://davidahmann.github.io/applied-ai-field-guide/study/operations/telemetry-contract/) | Trace, effect, version, identity, outcome, and cost events |
| Set service targets | [SLO scorecard](https://davidahmann.github.io/applied-ai-field-guide/study/operations/slo-scorecard/) | Segment-specific objectives, budgets, capacity, and recovery policy |
| Operate data readiness | [Data quality and drift](https://davidahmann.github.io/applied-ai-field-guide/study/operations/data-quality-and-drift/) | Source, quality, lineage, correction, drift, rebaseline, and retirement decisions |
| Contain and recover | [Incident runbook](https://davidahmann.github.io/applied-ai-field-guide/study/operations/incident-runbook/) | Scoped containment, reconciliation, regression, ownership, and re-enable decision |
| Change behavior safely | [Change management](https://davidahmann.github.io/applied-ai-field-guide/study/operations/change-management/) | Compatible release bundle, evaluation report, canary, rollback, and post-change decision |
| Keep dependency views useful | [Map freshness and change impact](https://davidahmann.github.io/applied-ai-field-guide/study/operations/map-freshness-and-change-impact/) | Derived maps with source provenance, freshness, impact review, and no shadow authority |
| Detect dangerous divergence | [Behavior monitoring](https://davidahmann.github.io/applied-ai-field-guide/study/operations/behavior-monitoring/) | Independent intent/action signal routed to trusted containment controls |
| Govern capability provenance | [Capability supply chain](https://davidahmann.github.io/applied-ai-field-guide/study/operations/capability-supply-chain/) | Admitted, pinned, constrained, monitored, and revocable tools, MCP servers, skills, CLIs, and code packages |
| Measure adoption and transfer ownership | [Delivery and adoption plan](https://davidahmann.github.io/applied-ai-field-guide/study/templates/delivery-and-adoption-plan/) and [customer handoff](https://davidahmann.github.io/applied-ai-field-guide/study/templates/customer-enablement-handoff/) | Predeclared adoption contract, exercised harness ownership, and artifact lineage |
| Review production value and service health | [Production service review](https://davidahmann.github.io/applied-ai-field-guide/study/templates/production-service-review/) | Expand, continue, constrain, pause, improve, or retire decision |
| Review an applied-AI workflow portfolio | [Workflow portfolio review](https://davidahmann.github.io/applied-ai-field-guide/study/templates/workflow-portfolio-review/) | Cohort-aware investment, continuation, operating ownership, productization, transfer, capacity, or exit decision |
| Route field learning | [Field-learning register](https://davidahmann.github.io/applied-ai-field-guide/study/templates/field-learning-register/) | Confidentiality-reviewed customer configuration, product backlog, reusable artifact, or retirement input |
| Improve or retire | [Operate and Scale](https://davidahmann.github.io/applied-ai-field-guide/study/playbooks/03-operate-and-scale/#10-run-the-improve-expand-or-retire-sequence) | Gated compatible release or verified decommission |

Start adoption instrumentation, artifact-lineage capture, and customer harness pairing during the pilot. The recurring cadence and improve/retire sequence are in [Operate and Scale](https://davidahmann.github.io/applied-ai-field-guide/study/playbooks/03-operate-and-scale/).