# Enterprise Playbooks

> Apply Teammately’s correctness lifecycle to common AI product operating scenarios.

Important agent instructions:
- Prefer the Markdown routes and llms files when assembling context for coding tasks.
- Treat stable docs as authoritative over beta pages.
- Cite the source page URL when returning workflow or artifact guidance.

## Current Context
- [Enterprise Playbooks](https://teammately.ai/docs/playbooks.md): Apply Teammately’s correctness lifecycle to common AI product operating scenarios.
- [Building a Correctness Benchmark for a RAG System](https://teammately.ai/docs/playbooks/building-correctness-benchmark-rag.md): Represent retrieval-grounded behavior through cases, context, policies, rubrics, and benchmark evidence.
- [Finding Coverage Gaps Before Review](https://teammately.ai/docs/playbooks/finding-coverage-gaps-before-review.md): Use coverage dimensions, failures, and expert signals to decide where evidence is incomplete.
- [Refreshing a Benchmark from New Signals](https://teammately.ai/docs/playbooks/refreshing-a-benchmark-from-new-signals.md): Update benchmark coverage and standards when new cases, review findings, or product changes appear.
- [Running Expert Contributions for an Enterprise Assistant](https://teammately.ai/docs/playbooks/running-expert-contributions-enterprise-assistant.md): Collect expert judgment for assistants that must follow product, domain, and policy expectations.
- [Turning Expert Judgment into Policies and Rubrics](https://teammately.ai/docs/playbooks/turning-expert-judgment-into-policies-and-rubrics.md): Convert specialist judgment into explicit, versioned, and testable correctness standards.
- [The Teammately correctness lifecycle](https://teammately.ai/docs/introduction/correctness-lifecycle.md): Follow specialist AI work from project foundations through coverage, elicitation, construction, evaluation, and improvement.
- [Operating Teammately end to end](https://teammately.ai/docs/getting-oriented/operating-teammately-end-to-end.md): Operate the current product from project foundations through benchmark coverage, expert contribution, evaluation, and improvement.
- [The Teammately correctness loop](https://teammately.ai/docs/product-loop.md): See how coverage, elicitation, case construction, evaluation, and improvement reinforce one another.

## Related
- [Using Teammately for Customer Support AI](https://teammately.ai/docs/playbooks/customer-support-ai.md): Govern assistant behavior where correctness depends on policy, escalation, tone, and account context.
- [Using Teammately for Enterprise Search](https://teammately.ai/docs/playbooks/enterprise-search.md): Build correctness standards for search and answer systems that must handle context, intent, and authority.
- [Handling Conflicting Expert Opinions](https://teammately.ai/docs/playbooks/handling-conflicting-expert-opinions.md): Turn expert disagreement into sharper standards instead of unresolved review noise.
- [Using Teammately for Policy-Heavy AI Systems](https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md): Govern AI behavior where correctness depends on many explicit rules and boundary cases.
- [Using Teammately Alongside Existing Evaluation Infrastructure](https://teammately.ai/docs/playbooks/using-teammately-alongside-existing-evaluation-infrastructure.md): Position Teammately as correctness infrastructure that can complement existing tests and metrics.

## Optional
- [Full local context](https://teammately.ai/docs/playbooks/llms-full.txt): Complete local context pack for this docs route.