# What AI Features Can and Cannot Do

> Explain the difference between AI-assisted suggestions and approved correctness infrastructure.

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
- [What AI Features Can and Cannot Do](https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do.md): Explain the difference between AI-assisted suggestions and approved correctness infrastructure.
- [Human Approval Boundaries](https://teammately.ai/docs/governance/human-approval-boundaries.md): Define which AI-assisted suggestions require accountable human review before becoming standards.
- [Correctness Elicitation](https://teammately.ai/docs/concepts/correctness-elicitation.md): Turn tacit specialist judgment into attributable contributions, governed policies, applicability conditions, and binary rubrics.
- [Complete an Expert Contribution](https://teammately.ai/docs/expert-contributions/complete-contribution.md): Work through form, chat, interview, case-review, and checkpoint tasks while keeping specialist judgment attributable.

## Optional
- [Full local context](https://teammately.ai/docs/governance/what-ai-features-can-and-cannot-do/llms-full.txt): Complete local context pack for this docs route.