{"query":"What AI Features Can and Cannot Do","corpusVersion":"local","generatedAt":"2026-09-14T05:51:31.134Z","results":[{"blockId":"governance.ai-feature-boundaries#what-ai-features-can-and-cannot-do","pageId":"governance.ai-feature-boundaries","title":"What AI Features Can and Cannot Do","pageTitle":"What AI Features Can and Cannot Do","url":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","humanUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do#what-ai-features-can-and-cannot-do","markdownUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","sectionId":"what-ai-features-can-and-cannot-do","kind":"reference","productArea":"governance","score":10006.931399959072,"reasons":["search_match","title_match","display_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"# What AI Features Can and Cannot Do"},{"blockId":"governance.ai-feature-boundaries#related-objects","pageId":"governance.ai-feature-boundaries","title":"Related objects","pageTitle":"What AI Features Can and Cannot Do","url":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","humanUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do#related-objects","markdownUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","sectionId":"related-objects","kind":"reference","productArea":"governance","score":3384.900888049889,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Related objects\n\nRead this with [Human Approval Boundaries](/docs/governance/human-approval-boundaries), [Comparison Directions](/docs/assets/comparison-directions), [Using Expert Judgment](/docs/concepts/correctness-elicitation), [Using Checkpoints](/docs/expert-contributions/complete-contribution), and [Noisy AI Suggestions](/docs/troubleshooting/noisy-ai-suggestions).\n\n{% example-demo title=\"What AI Features Can and Cannot Do boundary\" %}\nDraft suggestion: An AI-assisted workflow proposes a new compatibility policy after reading rejected cases.\n\nAllowed use: The suggestion can help a reviewer start the policy draft.\n\nNot allowed as governed evidence: A benchmark should not cite the policy until an accountable human approves the artifact and its applicability.\n\nInterpretation: The AI feature accelerated preparation; the human approval boundary still controls whether the standard can govern benchmark evidence.\n{% /example-demo %}\n\n{% example-demo title=\"Example: active AI-suggested direction\" %}\nAI-suggested direction: Teammately suggests a stale-source conflict Comparison Direction after project cases and ontology values show that gap.\n\nAllowed use: The direction can become active immediately and can guide preview examples or future variant generation.\n\nNot allowed as governed evidence: The direction does not approve a policy, rubric, generated case, benchmark membership, or downstream decision. Users still review generated examples and manage the direction normally.\n{% /example-demo %}"},{"blockId":"governance.ai-feature-boundaries#definition","pageId":"governance.ai-feature-boundaries","title":"Definition","pageTitle":"What AI Features Can and Cannot Do","url":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","humanUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do#definition","markdownUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","sectionId":"definition","kind":"reference","productArea":"governance","score":3311.612932054014,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Definition\n\nAI-assisted features can help prepare correctness work, but they do not own the approval boundary. They may draft, classify, summarize, propose, or organize artifacts; a human still needs to approve governed standards and review context before benchmark evidence depends on them.\n\nUse this page when a reader needs to separate preparation from authority. A fluent suggestion can be useful, but it is not an approved Policy, Rubric, Case-scoped reference output, Benchmark evidence, or downstream customer decision by itself.\n\n> Human approval boundary\n>\n> AI features can draft, summarize, classify, or suggest; they do not approve policies, rubrics, benchmark evidence, or customer-owned decisions by themselves."},{"blockId":"governance.ai-feature-boundaries#fields-states-or-lifecycle-rules","pageId":"governance.ai-feature-boundaries","title":"Fields, states, or lifecycle rules","pageTitle":"What AI Features Can and Cannot Do","url":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","humanUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do#fields-states-or-lifecycle-rules","markdownUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","sectionId":"fields-states-or-lifecycle-rules","kind":"reference","productArea":"governance","score":3231.3506947472747,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Fields, states, or lifecycle rules\n\n- AI-assisted output can be draft material, review support, classification help, or summarization.\n- AI-assisted output should not be treated as approved standards, benchmark evidence, or customer-owned decisions without human approval.\n- Suggested policies, rubrics, and classifications need visible approval or rejection state before they affect governed evidence.\n- AI-suggested Comparison Directions are different from suggested standards: they can become active directions immediately, but they still do not approve policies, rubrics, cases, benchmark membership, or review context.\n- AI-assistance language does not establish model-provider behavior, data retention, compliance posture, or autonomous approval.\n- Source-backed product pages decide exact supported behavior; this page defines the public boundary."},{"blockId":"governance.ai-feature-boundaries#source-confidence","pageId":"governance.ai-feature-boundaries","title":"Source confidence","pageTitle":"What AI Features Can and Cannot Do","url":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","humanUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do#source-confidence","markdownUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","sectionId":"source-confidence","kind":"reference","productArea":"governance","score":3161.8733872575854,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Source confidence\n\nCode-backed: generation surfaces can propose Dimension schemas, synthesize candidate Cases, and suggest Comparison Directions; Policy approval and contributed-artifact state establish separate human-governance boundaries. These sources support the product-state distinction here, not claims about model providers, retention, or autonomous authority."},{"blockId":"governance.ai-feature-boundaries#related-task-pages","pageId":"governance.ai-feature-boundaries","title":"Related task pages","pageTitle":"What AI Features Can and Cannot Do","url":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","humanUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do#related-task-pages","markdownUrl":"https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md","sectionId":"related-task-pages","kind":"reference","productArea":"governance","score":3122.5318097325503,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Related task pages\n\n{% related-card-grid title=\"Related task pages\" %}\n- [Human Approval Boundaries](/docs/governance/human-approval-boundaries)\n- [Comparison Directions](/docs/assets/comparison-directions)\n- [Using Expert Judgment](/docs/concepts/correctness-elicitation)\n- [Using Checkpoints](/docs/expert-contributions/complete-contribution)\n- [Product quickstart](/docs/quickstart)\n- [Task index](/docs/operating-manual/task-index)\n{% /related-card-grid %}"},{"blockId":"troubleshooting.noisy-ai-suggestions#related-task-pages","pageId":"troubleshooting.noisy-ai-suggestions","title":"Related task pages","pageTitle":"Noisy AI Suggestions","url":"https://teammately.ai/docs/troubleshooting/noisy-ai-suggestions.md","humanUrl":"https://teammately.ai/docs/troubleshooting/noisy-ai-suggestions#related-task-pages","markdownUrl":"https://teammately.ai/docs/troubleshooting/noisy-ai-suggestions.md","sectionId":"related-task-pages","kind":"error","productArea":"troubleshooting","score":793.2311671021059,"reasons":["search_match","term_match"],"markdown":"## Related task pages\n\n{% related-card-grid title=\"Related task pages\" %}\n- [What AI Features Can and Cannot Do](/docs/governance/what-ai-features-can-and-cannot-do)\n- [Human Approval Boundaries](/docs/governance/human-approval-boundaries)\n- [Comparison Directions](/docs/assets/comparison-directions)\n- [Editing Suggested Rubrics](/docs/correctness-governance/policies-and-rubrics)\n- [Product quickstart](/docs/quickstart)\n- [Task index](/docs/operating-manual/task-index)\n{% /related-card-grid %}"},{"blockId":"intro.what-is-teammately#what-is-teammately","pageId":"intro.what-is-teammately","title":"What is Teammately?","pageTitle":"What is Teammately?","url":"https://teammately.ai/docs/introduction/what-is-teammately.md","humanUrl":"https://teammately.ai/docs/introduction/what-is-teammately#what-is-teammately","markdownUrl":"https://teammately.ai/docs/introduction/what-is-teammately.md","sectionId":"what-is-teammately","kind":"concept","productArea":"introduction","score":722.1696234394375,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"# What is Teammately?\n\nTeammately is correctness infrastructure for teams building specialist AI. It turns in-house experts' judgment into an operating system for designing benchmark coverage, making correctness explicit, constructing challenging cases, evaluating candidate behavior, and deciding what to improve next. AI agents prepare and connect the work so scarce expert attention is spent on consequential judgment rather than manual organization.\n\n> Category boundary\n>\n> Teammately centers the definition and development of trustworthy AI behavior. Logs, traces, model endpoints, coding environments, and external data can enter the workflow, but the product's durable value is the connected correctness system built from expert judgment, cases, standards, evaluation evidence, and improvement history."}]}