Laminar’s platform captures every LLM call, tool use, and browser action to help developers debug long-running AI agents.
Laminar today announces a $3 million seed round led by Atlantic.vc, with participation from Y-Combinator, AAL.vc, and notable angels including Ben Sigelman, co-creator of OpenTelemetry and Ant Wilson, CTO of Supabase.
Founders Robert Kim (CEO) and Dinmukhamed Mailibay (CTO) grew up together in Kazakhstan, studied at KAIST, and worked side by side in London before founding Laminar. Robert built infrastructure at Palantir and Bloomberg; Din built payment infrastructure at AWS. They are YC S24 alumni.
The observability tools that exist today were designed for single LLM calls and simple chains. They weren’t built for agents that run for hours, generate thousands of spans per session, and need browser session replay to debug —Laminar was.
With a single line of code, Laminar captures everything an agent does: every LLM call, tool use, and function execution.
For browser agents, Laminar even captures browser session recordings and syncs them directly with traces, so developers can see exactly what the agent was looking at when it made a decision.
Its Signals feature uses AI to automatically surface failure patterns and anomalies at scale, turning raw observability data into a continuous improvement loop. Its Agent Debugger lets developers rerun an agent from any step, preserving full prior context, so they can iterate without starting from scratch.
According to Robert Kim, CEO, Laminar:
“When your agent fails 40 minutes into a task, today’s tools show you a wall of thousands of spans and say ‘good luck.’ We built Laminar so you can pinpoint the exact decision that went wrong and rerun from that point.”
Since launching in 2025, Laminar already counts Browser Use, OpenHands, Rye.com, and Alai among its customers.
Its SDK is directly integrated into OpenHands’ software agent and benchmarking infrastructure, and it is the default observability solution in Browser Use’s documentation.
Multiple companies have chosen Laminar over incumbent platforms specifically for its Signals feature, and at least one well-funded AI company has built a similar capability in-house, validating that agent-native observability is becoming a critical layer in the stack.
“Robert and Din are technically exceptional and deeply customer-obsessed. Agent observability is a critical infrastructure layer for the next generation of AI, and Laminar has the right architecture to own it,” shared Lukas Erbguth, Principal at Atlantic.vc
The funding will accelerate product development and go-to-market expansion as AI agents move from prototypes into production at scale.