{"query":"Using Teammately for Policy-Heavy AI Systems","corpusVersion":"local","generatedAt":"2026-09-13T04:40:51.429Z","results":[{"blockId":"playbooks.policy-heavy-ai-systems#using-teammately-for-policy-heavy-ai-systems","pageId":"playbooks.policy-heavy-ai-systems","title":"Using Teammately for Policy-Heavy AI Systems","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#using-teammately-for-policy-heavy-ai-systems","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"using-teammately-for-policy-heavy-ai-systems","kind":"recipe","productArea":"playbooks","score":8369.739684200675,"reasons":["search_match","title_match","display_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"# Using Teammately for Policy-Heavy AI Systems\n\nUse this playbook when an AI system can appear fluent while still violating explicit rules, exceptions, ownership boundaries, or customer-impacting policy."},{"blockId":"playbooks.policy-heavy-ai-systems#govern-policy-heavy-behavior","pageId":"playbooks.policy-heavy-ai-systems","title":"Govern policy-heavy behavior","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#govern-policy-heavy-behavior","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"govern-policy-heavy-behavior","kind":"recipe","productArea":"playbooks","score":4779.4627370781445,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Govern policy-heavy behavior\n\n1. Connect the controlling sources in **Reference Materials** and identify the owner and effective boundary for each rule family.\n2. Use Expert Contributions to resolve exceptions, cross-policy conflicts, missing facts, and operational interpretation.\n3. In **Correctness Governance**, create narrow Policies with explicit applicability and one-obligation binary Rubrics.\n4. Link representative passing, failing, and boundary Cases to the governed standards.\n5. Configure Coverage Facets for policy family, exception type, authority, required context, and consequence.\n6. Use Coverage Management to find Policy families or exception combinations with thin representation.\n7. Create a Snapshot and Benchmark Version only after the selected Dataset and governing standards are ready.\n8. Evaluate saved Harness Versions and inspect failures by Policy, Rubric, and Coverage Facet before changing the candidate."},{"blockId":"playbooks.policy-heavy-ai-systems#establish-the-policy-inventory","pageId":"playbooks.policy-heavy-ai-systems","title":"Establish the policy inventory","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#establish-the-policy-inventory","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"establish-the-policy-inventory","kind":"recipe","productArea":"playbooks","score":3464.864101367723,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Establish the policy inventory\n\nUse this when correctness depends on several controlled rules, exceptions, or source hierarchies and each rule has an accountable owner. If the team cannot identify controlling sources and owners, begin with Reference Materials and Expert Contributions rather than drafting a large generic Policy set."},{"blockId":"playbooks.customer-support-ai#using-teammately-for-customer-support-ai","pageId":"playbooks.customer-support-ai","title":"Using Teammately for Customer Support AI","pageTitle":"Using Teammately for Customer Support AI","url":"https://teammately.ai/docs/playbooks/customer-support-ai.md","humanUrl":"https://teammately.ai/docs/playbooks/customer-support-ai#using-teammately-for-customer-support-ai","markdownUrl":"https://teammately.ai/docs/playbooks/customer-support-ai.md","sectionId":"using-teammately-for-customer-support-ai","kind":"recipe","productArea":"playbooks","score":2578.2585340602127,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"# Using Teammately for Customer Support AI\n\nUse this playbook when support behavior must respect customer policy, escalation rules, account context, and tone without reducing correctness to satisfaction scores."},{"blockId":"playbooks.policy-heavy-ai-systems#evidence-to-collect","pageId":"playbooks.policy-heavy-ai-systems","title":"Evidence to collect","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#evidence-to-collect","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"evidence-to-collect","kind":"recipe","productArea":"playbooks","score":2512.418044230623,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Evidence to collect\n\n- Policy sources, accountable owners, and effective boundaries.\n- Applicability triggers for each policy family and risk tier.\n- Must-level binary rubrics and any lower-priority preference criteria.\n- Coverage dimensions for exceptions, conflicts, stale policy, and missing context.\n- Benchmark evidence grouped by Policy, Rubric, and Coverage Facet, with unresolved authority questions kept explicit."},{"blockId":"playbooks.policy-heavy-ai-systems#source-confidence","pageId":"playbooks.policy-heavy-ai-systems","title":"Source confidence","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#source-confidence","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"source-confidence","kind":"recipe","productArea":"playbooks","score":2474.7810548885495,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Source confidence\n\nDoctrine-backed: the approved product model separates source context, expert interpretation, governed standards, coverage, and evaluation. Linked code-backed pages define the active controls for each layer."},{"blockId":"playbooks.policy-heavy-ai-systems#maintenance-triggers","pageId":"playbooks.policy-heavy-ai-systems","title":"Maintenance triggers","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#maintenance-triggers","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"maintenance-triggers","kind":"recipe","productArea":"playbooks","score":2452.918552418391,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Maintenance triggers\n\nRefresh the governed boundary when a controlling source changes, an exception is added, applicability changes, a Rubric no longer tests one observable requirement, or new Cases expose a conflict. Historical Runs remain evidence under their original Benchmark Version.\n\n{% example-demo title=\"Subscription entitlement assistant\" %}\nAn assistant answers whether an account can use an enterprise integration after a plan change. Specialists separate three governing boundaries: plan entitlement, contract exception, and administrator permission. Each gets distinct applicability and a binary Rubric. Evaluation shows that the candidate reads the plan correctly but assumes administrator permission and ignores contract overrides, so the team can fix two precise behaviors instead of tuning a generic entitlement score.\n{% /example-demo %}"},{"blockId":"playbooks.policy-heavy-ai-systems#related-docs","pageId":"playbooks.policy-heavy-ai-systems","title":"Related docs","pageTitle":"Using Teammately for Policy-Heavy AI Systems","url":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","humanUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems#related-docs","markdownUrl":"https://teammately.ai/docs/playbooks/policy-heavy-ai-systems.md","sectionId":"related-docs","kind":"recipe","productArea":"playbooks","score":2452.918552418391,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Related docs\n\n{% related-card-grid title=\"Related docs\" %}\n- [Handling Boundary Cases](/docs/coverage-engineering/boundary-cases)\n- [Work with Policies and Rubrics](/docs/correctness-governance/policies-and-rubrics)\n- [Inspect Dataset representation](/docs/benchmark-datasets/representation)\n- [Compare Harness Versions](/docs/benchmark-evaluations/compare)\n- [Read run results](/docs/benchmark-evaluations/inspect-results)\n- [Run a benchmark](/docs/benchmark-evaluations/run-evaluation)\n- [Importing cases](/docs/operating-manual/import-and-prepare-cases)\n{% /related-card-grid %}"}]}