An LLM-heavy startup uses LangChain today but expects to add Mastra (TS service) and DSPy (compile pipeline) in year two. They are choosing between LangSmith and Langfuse for observability. Make a recommendation and defend it on architecture grounds, not personal preference.
Free · 2 AI evals / day
Both LangSmith and Langfuse are observability platforms for LLM applications. They look similar in screenshots. Trace views, span trees, evaluation dashboards. The architectural difference is what they read from.
LangSmith is built by the LangChain team and consumes LangChain's native callback events. It is the most polished experience if your stack is purely LangChain because it knows the framework's structure intimately.
Langfuse is built on OpenTelemetry's GenAI semantic conventions. Any framework that emits OTel-compliant spans, LangChain via an instrumentation library, Mastra natively, DSPy via its tracer, feeds into Langfuse with the same shape.
For the startup in the question, year two adds Mastra and DSPy. LangSmith does not have a path to ingest non-LangChain traces. Langfuse does. Both Mastra and DSPy can emit OTel spans that Langfuse accepts alongside the LangChain traces.
The right call is Langfuse. The lock-in cost of LangSmith grows in year two, and the time to switch is harder once dashboards and eval datasets live there.
Pick Langfuse, on architecture grounds.
The deciding fact is the framework heterogeneity in year two. LangSmith's data model is shaped around LangChain's callback events; the integration assumes the framework is LangChain. Mastra is a TypeScript framework with its own observability hooks, not LangChain callbacks. DSPy is a Python compile and execute system, also not LangChain. Routing those two through LangSmith would require parallel instrumentation pipelines, separate dashboards, and a fragmented eval story.
Langfuse uses OpenTelemetry's GenAI semantic conventions as the ingest format. Instrument once against the conventions and all three frameworks flow into one trace store with comparable attributes. The team writes one observability stack and one query language, not three.
Self-hosting matters too. Langfuse can run inside the team's VPC, which keeps prompts and PII off a third-party vendor. For a startup that may sell into regulated industries (healthcare, finance, EU sovereignty requirements) this is the difference between a six-month security review and a same-day adoption.
LangSmith's legitimate strengths are real. The dataset-eval UI tied to LangChain runs is genuinely polished, and for a pure-LangChain shop it removes friction. But year-two the startup is not a pure-LangChain shop. The lock-in cost compounds as more dashboards and eval sets live in the proprietary backend.
Making the portable choice early is asymmetrically cheap. Switching is hardest in year three, easiest in year one.
Quick reference
TL;DR
Pick Langfuse. It is OpenTelemetry-based, so LangChain, Mastra, and DSPy all flow into one trace store; LangSmith is LangChain-coupled and would leave two of three year-two frameworks dark.
Imagine choosing between two delivery companies for a growing business. Company A only delivers parcels from one specific shipping label brand. Company B accepts parcels from any brand that follows the standard postal format. Today you only ship with that one brand, so both companies work fine. Next year you plan to add two more brands. Pick company A and you will need separate delivery contracts for the new brands, or those parcels will pile up in your warehouse with nobody to pick them up. Pick company B and the new brands slot in for free because they all follow the same postal format. The right pick gets easier the further out you look.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
A team committed to pure LangChain with no plan to diversify LangSmith's tight integration removes friction; the lock-in cost is acceptable if it is permanent by design
A team without the ops bandwidth to operate Postgres and ClickHouse for Langfuse self-host Langfuse Cloud is an option but if hosted is the only acceptable option, both vendors look similar
A research lab where polished eval-dataset UI matters more than portability LangSmith's dataset workflow is meaningfully nicer for active human evaluation; portability matters less in research
Quick scan · 2–4 min
Everything important, quickly.
6 minutes: the architectural difference, the year-two scenario, the four deciding facts, and the honest counter-cases for LangSmith.
Side-by-side
Axis
LangSmith
Langfuse
Ingest format
LangChain callbacks
OpenTelemetry GenAI conventions
Multi-framework support
Requires parallel instrumentation
Native via OTel
Hosting
Vendor-hosted only
Vendor-hosted or self-hosted
Data residency
Vendor controls
Team controls
Eval dataset UI
Polished, LangChain-tight
Solid, framework-agnostic
Lock-in trajectory
Grows with usage
Portable via OTel
Real-world examples
Real products, models, and research that use this idea.
1Anthropic and OpenAI both publish OpenTelemetry GenAI traces from their server SDKs in 2026; both flow into Langfuse with no custom code.
2Vercel ships AI SDK telemetry as OTel spans; the same Langfuse instance ingests them alongside LangChain.
3Klarna and Shopify publicly describe Langfuse-based observability for multi-framework LLM stacks.
4DSPy 2.6 documents the tracing hook and recommends OTel exporters for production deployments.
Interviewer follow-ups
What an interviewer would ask next. Try answering before peeking at the approach.
QHow would you instrument a Mastra service so it emits compatible traces alongside the LangChain ones?
Sign in or go Pro to see the approach for this follow-up.
QWhat would change in your recommendation if data residency is not a concern?
Sign in or go Pro to see the approach for this follow-up.
QHow do you handle eval datasets when migrating from LangSmith to Langfuse?
Sign in or go Pro to see the approach for this follow-up.
Don't say this
Red flags and common mistakes that signal junior thinking. Click to expand.
Most common mistake
Picking LangSmith for the dataset-eval UI without thinking through what happens when the next service is not LangChain-shaped.