Integration

Forward workflow runs to for observability with LangSmith from alerts to fixes in one flow

Send run data to LangSmith to trace executions, attach metadata, and monitor workflow performance.

2 operations0 triggersAuth: api-key

About LangSmith

Unlock deep visibility and understanding of your AI workflows with LangSmith – a powerful platform for tracing, debugging, and monitoring LLM-powered applications and automations.

What teams automate with LangSmith

Trace and debug runs: Forward workflow, tool, or model runs to LangSmith, record hierarchical execution details, and pinpoint bottlenecks or failures quickly.
Attach rich metadata: Enrich your traces by logging inputs, outputs, tags, custom metadata, reasons for failure, and more for in-depth insight and analytics.
Monitor workflow performance: Visualize executions, monitor error rates, durations, and success metrics over time to improve reliability and efficiency.
Collaborate and audit: Enable team-based debugging and track changes, enabling transparent auditing and rapid iteration on chained LLM workflows.
Automate observability: Seamlessly connect LangSmith traces to your workflow automations for always-on, effortless monitoring without manual instrumentation.

Read full documentation

What can you do with the LangSmith integration?

What can you do with the LangSmith integration? Unlock deep visibility and understanding of your AI workflows with LangSmith – a powerful platform for tracing, debugging, and monitoring LLM-powered applications and automations. Integrate LangSmith into your processes to capture detailed execution traces, log input/output data, attach metadata, and optimize your workflows through data-driven observability. With the LangSmith integration, you can: AptlyStar exposes 2 operations so teams can automate end-to-end processes without maintaining brittle scripts.

Automate & integrate LangSmith

Compose LangSmith with the rest of your stack using visual workflows and agents.

Create & update LangSmith records

Insert, upsert, and patch objects so LangSmith workflows stay synchronized automatically.

Create Run
Create Runs Batch

LangSmith create & update records

Insert, upsert, and patch objects so workflows stay synchronized automatically.

LangSmith manage lifecycle

Archive, delete, merge, and reconcile records with guardrails and approvals.

LangSmith notify & orchestrate

Trigger downstream actions, alerts, and hand-offs when something changes.

LangSmith analyze & report

Aggregate metrics, export datasets, and feed BI or agent summaries.

LangSmith automate on events

React to webhooks and polling triggers the moment something happens.

Build LangSmith agents

Ship AI workflows that read, decide, and act on LangSmith — with guardrails and human approvals where you need them.

LangSmith agent-run tracer

Build a workflow that wraps an agent step and forwards each run to LangSmith with inputs, outputs, and latency so the ML team can trace executions in one project.

Explore templates

LangSmith error logger

Create a workflow that on a failed agent step forwards a LangSmith run tagged as an error with the inputs and error message, and posts the run link to Slack for the ML team.

Explore templates

LangSmith feedback capture

Build a workflow that collects user-reported agent failures from a table and forwards each as a tagged LangSmith run with the inputs and expected output for later review.

Explore templates

LangSmith batch run shipper

Create a scheduled workflow that reads completed agent runs from a table and posts them to LangSmith in a single batch so observability stays in sync without per-run overhead.

Explore templates

LangSmith session tagger

Build a workflow that forwards each agent run to LangSmith tagged with the originating feature and environment so traces can be filtered by surface in the LangSmith project.

Explore templates

LangSmith RAG step logger

Create a workflow that runs a retrieval-augmented agent and forwards a LangSmith run per step — retriever, prompt, and llm — so the ML team can inspect each stage of the chain.

Explore templates

Ready to solve your LangSmith integration challenges?

Connect LangSmith once, then reuse the same blocks across agents, workflows, and templates.

Start for free Browse templates

Challenges AptlyStar solves

Keep LangSmith in sync with the rest of your stack

Teams lose hours copying data between LangSmith and CRMs, inboxes, and spreadsheets. AptlyStar connects LangSmith to 2+ operations so updates flow automatically.

Learn more

Scale LangSmith automations without custom glue code

One-off scripts break when APIs change. Use visual workflows, retries, and typed blocks so LangSmith automations stay maintainable as you grow.

Learn more

Give AI agents secure, scoped access to LangSmith

Agents need live LangSmith context without over-permissioned keys. Connect credentials once, apply guardrails, and let agents act through audited workflow runs.

Learn more

Featured LangSmith templates

Ready-to-use workflow templates that include LangSmith, just like in the app.

LangSmith agent-run tracer

Build a workflow that wraps an agent step and forwards each run to LangSmith with inputs, outputs, and latency so the ML team can trace executions in one project.

Browse templates

LangSmith error logger

Create a workflow that on a failed agent step forwards a LangSmith run tagged as an error with the inputs and error message, and posts the run link to Slack for the ML team.

Browse templates

LangSmith feedback capture

Build a workflow that collects user-reported agent failures from a table and forwards each as a tagged LangSmith run with the inputs and expected output for later review.

Browse templates

LangSmith batch run shipper

Create a scheduled workflow that reads completed agent runs from a table and posts them to LangSmith in a single batch so observability stays in sync without per-run overhead.

Browse templates

LangSmith session tagger

Build a workflow that forwards each agent run to LangSmith tagged with the originating feature and environment so traces can be filtered by surface in the LangSmith project.

Browse templates

LangSmith RAG step logger

Create a workflow that runs a retrieval-augmented agent and forwards a LangSmith run per step — retriever, prompt, and llm — so the ML team can inspect each stage of the chain.

Browse templates