Master Laminar (LMNR) with our step-by-step tutorial, detailed feature walkthrough, and expert tips.
Explore the key features that make Laminar (LMNR) powerful for analytics & monitoring workflows.
Restart a failed agent run from any step with full context. LLM calls replay from cached responses, external state such as browser sessions or sandboxes can be restored where supported. No full rerun needed.
An agent fails 40 minutes into a multi-step research task. Instead of rerunning the entire thing, restart from the exact decision point that went wrong and iterate on the fix.
Instrument supported frameworks and SDKs to capture inputs, outputs, token counts, latency, and cost for agent and LLM calls.
Get production visibility into an agent's behavior and cost by adding tracing instrumentation to the workflow.
Captures screen recordings from browser agents and syncs them with trace timelines. Integrates with Browser Use, Stagehand, Playwright, Kernel, and Browserbase.
Debug why a browser automation agent clicked the wrong button by watching the recording alongside the agent's decision trace.
Describe a failure pattern in plain English and Laminar finds matching instances across production traces. Runs continuously against new data where configured.
Find every instance where an agent entered a retry loop or a user expressed frustration, without writing custom log queries.
Run LLM-as-judge, deterministic, or custom evaluation functions against traces or curated datasets. Results can be tracked over time for regression detection.
Nightly evaluations against a golden dataset catch quality drops in a customer support agent before users report problems.
Query platform data with SQL. Feed evaluation inputs from SQL queries and pull data into external applications via SQL API where supported.
Build custom analytics correlating token usage with user satisfaction across different agent versions and prompt configurations.
Laminar is best used for observability and debugging of long-running AI agents. It is especially useful when an agent chains LLM calls, tool actions, browser interactions, and evaluations, because the platform keeps those steps visible in a trace. The website emphasizes understanding why an agent failed, rerunning from a specific step, and analyzing repeated failure patterns.
Laminar's debugger is designed to preserve context from previous steps so developers can rerun at step N instead of restarting an entire agent task. The site describes a workflow where teams can run locally, debug in the browser, tune system prompts, and see changes reflected as they save. This is most valuable for failures that happen late in a long workflow.
Yes. The website says Laminar captures browser screen recordings and automatically syncs them with agent traces. It lists integrations with Browser Use, Stagehand, Playwright, Kernel, Browserbase, and more, which makes it relevant for web automation agents that click, navigate, and extract information.
Signals are Laminar's natural-language analysis feature for finding patterns in traces. Users describe what they are looking for, define an output format, and Laminar extracts matching events from past and future traces. The supplied site content shows examples such as categorizing agent failures and returning structured details.
The public pricing page lists a Free tier with 1 GB of data, 1,000 Signals steps, 15-day retention, 1 project, 1 seat, and community support; a Hobby tier at $30/month with 3 GB data, 5,000 Signals steps, 30-day retention, unlimited projects and seats, and email support; a Pro tier at $150/month with 10 GB data, 50,000 Signals steps, 90-day retention, unlimited projects and seats, and Slack support; and custom Enterprise pricing with custom limits, on-premise deployment, unlimited projects and seats, and dedicated support. Teams should still confirm current limits and enterprise terms before buying.
Now that you know how to use Laminar (LMNR), it's time to put this knowledge into practice.
Sign up and follow the tutorial steps
Check pros, cons, and user feedback
See how it stacks against alternatives
Follow our tutorial and master this powerful analytics & monitoring tool in minutes.
Tutorial updated March 2026