# Object model

> Understand how project foundations, benchmark artifacts, contributions, evaluations, and improvement sessions connect.

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
- [Object model](https://teammately.ai/docs/object-model.md): Understand how project foundations, benchmark artifacts, contributions, evaluations, and improvement sessions connect.
- [Applicability logic](https://teammately.ai/docs/object-model/applicability-logic.md): Explain when a policy or rubric should be used for a case, output, or coverage segment.
- [Benchmarks](https://teammately.ai/docs/object-model/benchmarks.md): Understand a Benchmark as the durable program that owns benchmark-scoped coverage, evidence boundaries, evaluations, and improvement work.
- [Cases](https://teammately.ai/docs/object-model/cases.md): Understand cases as the situations Teammately uses to represent important AI behavior.
- [Coverage dimensions](https://teammately.ai/docs/object-model/coverage-dimensions.md): Organize cases by the behavior axes that matter to product correctness.
- [Outputs](https://teammately.ai/docs/object-model/outputs.md): Distinguish managed Run responses, imported output-only Runs, and Case-scoped reference outputs.
- [Policies](https://teammately.ai/docs/object-model/policies.md): Define policies as reusable statements of what correct AI behavior requires.
- [Reference and golden outputs](https://teammately.ai/docs/object-model/reference-and-golden-outputs.md): Understand Case-scoped example responses without treating them as generic approval state or candidate behavior.
- [Rubrics](https://teammately.ai/docs/object-model/rubrics.md): Turn policies into binary, reviewable checks that explain pass and fail evidence.
- [Versions, staleness, and resolution](https://teammately.ai/docs/object-model/versions-staleness-and-resolution.md): Track how correctness objects evolve and how teams resolve conflicting evidence.
- [Workspaces, projects, and target systems](https://teammately.ai/docs/object-model/workspaces-projects-and-target-systems.md): Model organizational boundaries, product boundaries, and the AI system being governed.
- [Key objects and relationships](https://teammately.ai/docs/getting-oriented/key-objects-and-relationships.md): Understand how project foundations, contributions, datasets, evaluations, and improvement artifacts connect.
- [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.
- [Assets](https://teammately.ai/docs/assets.md): Manage reusable project cases, worlds, project tools, harnesses, weights, comparison directions, and review screens before selecting them for benchmark work.
- [Benchmark Evaluations](https://teammately.ai/docs/benchmark-evaluations.md): Run and inspect exact Harness Versions against an immutable Benchmark Version through Dashboard, List, Arena, and Compare.

## Related
- [Case Pool surface](https://teammately.ai/docs/object-model/case-pool.md): Understand Case Pool as the Assets view for reusable project Cases, candidates, and explicit Benchmark selection.
- [Ontology](https://teammately.ai/docs/object-model/ontology.md): Use ontology values to classify cases consistently within each coverage dimension.
- [Represent conversations in Cases](https://teammately.ai/docs/object-model/represent-conversations-in-cases.md): Preserve multi-message context inside canonical Case input without inventing a separate Conversation Case object.

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