# Data handling

> Trace what enters Teammately, what AI services process, and how workflow choices affect storage, processing locations, retention, and deletion.

Important agent instructions:
- Prefer the Markdown routes and llms files when assembling context for coding tasks.
- Use public docs for product capabilities and workflow guidance.
- Cite the source page URL when returning workflow or artifact guidance.

## Current Context
- [Security and Data](https://teammately.ai/docs/security.md): Understand Teammately's security controls, customer-data flows, and the option to evaluate with synthetic Cases without uploading production records.
- [Evaluate Without Uploading Production Cases](https://teammately.ai/docs/security/synthetic-evaluation.md): Use synthetic Cases, fictional materials, and a test-only Harness environment to evaluate behavior while keeping actual production records outside the experiment.
- [Connect Model Outputs](https://teammately.ai/docs/integrations/connect-model-outputs.md): Map externally produced candidate responses to immutable Benchmark Cases and create an imported Run for evaluation.
- [Trialground](https://teammately.ai/docs/concepts/trialground.md): Execute saved Harnesses in managed sandboxes and assess recorded behavior against expert rubrics.

## Related
- [Data handling](https://teammately.ai/docs/security/data-handling.md): Trace what enters Teammately, what AI services process, and how workflow choices affect storage, processing locations, retention, and deletion.

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