# Sovara

## Docs

- [Efficient annotation](https://docs.sovara-labs.com/annotations/annotate.md): Review surfaced runs and save useful labels.
- [Why annotate?](https://docs.sovara-labs.com/annotations/overview.md): Why annotation matters for improving agent behavior.
- [Recommendation Algorithm](https://docs.sovara-labs.com/annotations/recommendation-algorithm.md): How Sovara decides what should be reviewed.
- [Creating benchmarks](https://docs.sovara-labs.com/benchmarks/creating-benchmarks.md): Design benchmark workflows for Sovara.
- [Why benchmarks](https://docs.sovara-labs.com/benchmarks/why-benchmarks.md): Why benchmarks matter for improving agent systems.
- [Available tools](https://docs.sovara-labs.com/cli/available-tools.md): The commands exposed by the Sovara CLI.
- [Claude Code](https://docs.sovara-labs.com/cli/claude-code.md): Use the Sovara CLI with Claude Code.
- [Codex](https://docs.sovara-labs.com/cli/codex.md): Use the Sovara CLI with Codex.
- [Overview](https://docs.sovara-labs.com/cli/overview.md): The role of the Sovara CLI in the Sovara workflow.
- [Microsoft Azure](https://docs.sovara-labs.com/enterprise/azure-entra-setup.md): Deploy Sovara Server on Azure and connect the Remote desktop app with Microsoft Entra login.
- [On-prem Setup](https://docs.sovara-labs.com/enterprise/on-prem-setup.md): Install Sovara with a private server, language runners, and remote desktop clients.
- [Palantir Foundry](https://docs.sovara-labs.com/enterprise/palantir-integration.md): Connect Sovara Server to Palantir Foundry for ontology-backed storage and AIP embeddings.
- [Installation](https://docs.sovara-labs.com/get-started/installation.md): Install Sovara and prepare your local development environment.
- [Quickstart](https://docs.sovara-labs.com/get-started/quickstart.md): Record and inspect your first Sovara run.
- [Tracing your agent](https://docs.sovara-labs.com/get-started/tracing-your-agent.md): Run the FinanceBench demo and inspect a real Sovara trace.
- [Manual inspection](https://docs.sovara-labs.com/observability/manual-inspection.md): Inspect traces, nodes, inputs, and outputs by hand.
- [Runs](https://docs.sovara-labs.com/observability/runs.md): Recorded executions in Sovara.
- [SovaraChat](https://docs.sovara-labs.com/observability/sovarachat.md): Use chat to query and reason about recorded runs.
- [Improve](https://docs.sovara-labs.com/sovara/improve.md): How Sovara turns observations into targeted improvements.
- [Observe](https://docs.sovara-labs.com/sovara/observe.md): How Sovara observes agent behavior during development.
- [Philosophy](https://docs.sovara-labs.com/sovara/philosophy.md): The principles behind Sovara’s approach to improving agents.
- [Surface errors](https://docs.sovara-labs.com/sovara/surface-errors.md): How Sovara helps expose failures and weak execution paths.
- [Sovara's auto-injection](https://docs.sovara-labs.com/sovaradb/auto-injection.md): How Sovara injects relevant priors at runtime.
- [The context-problem of AI agents](https://docs.sovara-labs.com/sovaradb/context-problem-ai-agents.md): Why agent context needs durable memory and retrieval.
- [Creating and managing priors](https://docs.sovara-labs.com/sovaradb/creating-managing-priors.md): Create, organize, and maintain Sovara priors.
- [What are priors?](https://docs.sovara-labs.com/sovaradb/priors.md): Define priors and how they shape agent behavior.