# LLM evaluation and observability platforms vs. outcome verification

> Braintrust, LangSmith, Langfuse and Arize let teams score their own agent with evaluators they choose. Outcome verification checks claimed outcomes under a published rule, in the customer's records.

Published 2026-11-12 · Reviewed 2026-11-12. Canonical: https://attify.app/compare/evals-and-observability

Evaluation and observability platforms are instruments for the team building an agent: they trace its runs and score them with evaluators the team chooses (code checks, LLM judges, human review), offline on datasets and online on production traces. Outcome verification is a measurement for the agent's buyers and their buyers' trust: it tests the agent's claimed outcomes under a published rule, against what happened next in the customer's own systems.

## What the platforms describe

- **Braintrust**: datasets of examples, scorers and classifiers built with code or LLM-as-a-judge, online scoring of production traces, which relies on LLM judges because live requests have no ground truth ([Braintrust](https://docs.braintrust.dev/evaluate)).
- **LangSmith**: offline evaluation on datasets with reference outputs before deployment, online evaluation on live traces without them; human review, code, LLM-as-judge and pairwise evaluators ([LangSmith](https://docs.langchain.com/langsmith/evaluation-concepts)).
- **Langfuse**: LLM-as-a-judge, code evaluators, datasets and experiments, online evaluation, user feedback and annotation queues ([Langfuse](https://langfuse.com/docs/evaluation/overview)).
- **Arize AX**: evaluators that return a label, score and explanation at span, trace or session scope, for monitoring, batch runs or experiments ([Arize](https://arize.com/docs/ax/evaluate/evaluators)).

## Side by side

| | Evaluation platform | Outcome verification (Attify) |
|---|---|---|
| For | The builder | The buyer, and the vendor's buyers |
| Evaluator | Chosen and written by the builder | Rules plus a published judge prompt validated against people |
| Sees | What the application traced | What happened next in the customer's own systems: a repeat contact, a no-show |
| Comparable across companies | No | Within a job type, under one standard |
| Public | No | Published verifications and the Index |

## Connecting them

Attify reads LangSmith and Langfuse accounts directly, and takes OpenTelemetry traces: one instrumentation serves both ([how to send data](https://attify.app/guides/send-agent-data-to-attify)). The agent's claim travels as `proven.outcome`; handoffs as `proven.handoff`.

## Questions

### Can Attify read my LangSmith or Langfuse traces?

Yes. Connect the account with an API key (on Langfuse, a read-only Viewer key). If it is the vendor's own account, the data is witnessed and counts toward a verification only after the customer consents and reconciles it.

### Should I put my eval scores in the trace for Attify?

Send the agent's own claimed outcome as proven.outcome. Your evaluators' scores are yours; Attify tests the claim against what happened in the customer's systems.

## Sources

- Braintrust: [Evaluate](https://docs.braintrust.dev/evaluate), read 2026-11-08
- LangChain (LangSmith): [Evaluation concepts](https://docs.langchain.com/langsmith/evaluation-concepts), read 2026-11-08
- Langfuse: [Evaluation overview](https://langfuse.com/docs/evaluation/overview), read 2026-11-08
- Arize AX: [Evaluators](https://arize.com/docs/ax/evaluate/evaluators), read 2026-11-08
