Moda vs Langfuse
Langfuse is the OSS-and-cloud LLM engineering platform — tracing, sessions, prompt management, datasets, experiments, custom dashboards, LLM-as-judge with evaluator tracing, and Agent Graphs (GA in Launch Week 4). It is a powerful substrate, but intent clustering and behavioral failure analysis live in its cookbooks (user-built pipelines) rather than as first-party platform features. Moda is self-improvement on the harness layer above whatever traces Langfuse stores — intent map, emergent intents, behavioral failures, and frustration root cause attributed to a specific harness component, with learnings outside the model weights so they apply across any model.
When you want intent clustering and behavioral failure detection out of the box without building the pipeline yourself.
| Capability | Moda | Langfuse |
|---|---|---|
| Trace storage | Hosted, OTLP-native. | Hosted or self-host; OTLP-native (`/api/public/otel`). |
| Intent clustering | Automatic 3-level taxonomy on every conversation segment, no prompting. | Cookbook pipeline (unsupervised classification example); not a shipped product feature. |
| Behavioral failure detection | Fixed taxonomy detected on ingest: tool misuse, context loss, agent laziness, hallucination, reasoning loops, goal drift. | Manual error analysis blog + LLM-as-judge for failures you can define; no prescriptive taxonomy. |
| Frustration root cause | Trigger, trajectory, affected goal, and agent counterfactual per event. | User scores + sentiment via LLM-as-judge; no counterfactual root cause. |