Skip to main content
Tensile helps teams understand and evaluate how AI agents behave in real workflows. Connect trace sources or instrument an agent, then use its evidence to define what success and failure mean for a repeated business decision. The product brings workflow discovery, evaluator-pack authoring, evidence review, and reliability analysis into one workspace. Configured organizations can also compare a declared task with destination evidence, assess whether human review can change, and inspect a scoped baseline-versus-candidate comparison. Trace data is evidence for review; it does not make a draft evaluator approved or cause it to score live traffic automatically.

​
The reliability workflow

Connect traces

Bring in traces from supported integrations or instrument turns and tool calls with the SDK or ingestion API.

Define evaluators

Discover repeated workflows and draft versioned evaluators that make the business decision and evidence explicit.

Review and validate

Review real examples and source evidence. Calibration, independent validation, and owner approval gate any production use.

​
How the signal flows

Tensile can receive new events from the SDK or ingestion API, or import existing traces from a supported connector. The exact data available depends on the source and its configuration.
1

Instrument

Connect a supported source such as Braintrust or Langfuse, or instrument your own turns and tool calls with the Tensile SDK, MCP wrapper, or ingestion API.
2

Ingest

Tensile normalizes source records into trace sessions and events. Events retain their parent relationships and source identity when the source provides them.
3

Distill

Workflow discovery and evaluator authoring use the available trace and source evidence. Reviewers see the question, answer criteria, and supporting evidence for eligible cases.
4

Improve

A draft pack is not a live score. Calibration, sealed validation, and authorized owner approval must pass before a pack can be promoted for production use.

​
Start here

Quickstart

Connect a source or send an event, then follow the steps to check that Tensile can read its trace data.

Data handling

How to keep user data pseudonymous, allowlist metadata, and redact sensitive content before it leaves your app.

Evaluator packs

Learn how packs move from discovered workflows and draft definitions through human review and validation gates.

Verified work

Follow an Outcome case from the agent’s claim to destination evidence, then inspect Readiness and Changes.

Connect a trace source

Connect a Braintrust or Langfuse workspace and understand what a trace connection does.
Tensile supports multiple trace sources and agent stacks. Available features depend on the connected source, organization configuration, and evaluator approval state.