Launch HN: Laminar (YC S24) – RL-trained model that finds errors in agent traces
58 points by skull8888888 19 hours ago
58 points by skull8888888 19 hours ago
Hi HN, we’re Robert and Din from Laminar (https://laminar.sh). We’ve been building open-source observability for AI agents since 2024. Recently, we released flow-1, a model trained with RL to find errors in agent traces. On our benchmark (https://laminar.sh/blog/flow-1), it matches GPT-6-sol in detection quality while being 23x cheaper. This makes it affordable to analyze every production agent trace, without sampling.
Here’s a one-minute walkthrough: https://youtu.be/KJa3h6ZJNLQ
We also put together a post with example traces and analyses from flow-1 and other models: https://laminar.sh/blog/flow-1-in-action
Agent observability is crowded, so instead of a bullet list of how Laminar differs from X, we’ll explain how we’re solving agent observability from first principles.
Agents now run for many steps and fail implicitly. An agent can click the wrong button or cite the wrong document while every call completes successfully. These errors are the most useful ones to catch and understand. To find them, you need to understand what the agent was trying to do and inspect its LLM calls and tool results. Simply looking at the final agent output is not enough.
Collecting traces alone doesn’t solve this. A lot of agent observability platforms are still data collectors at their core. You can end up paying to store traces that nobody has time to read or extract value from.
Using another LLM to inspect traces is THE solution, but capable models are expensive at scale and cheaper ones often miss errors or flag unrelated things.
So we built our model to solve exactly this problem. We finetuned a small OSS model and then post trained it with RL on thousands of synthetic investigations of realistic agent workflows in software, legal, customer support, etc. We got a model that is both good at agent trace analysis and very cheap to run.
flow-1 runs inside a harness we call Signals. It acts as a coding agent, treating an agent trace like a repo, with each span (an LLM call, tool call, etc.) as a file. It starts from a compressed string representation of a full agent trace and a user prompt, then greps across spans and reads the relevant ones in full.
The beauty of Signals is that it can respond to a general prompt. You can ask it to identify user frustration, check whether your browser agent completed a checkout, and so on. It’s not limited to raw error detection. It returns findings as JSON in a schema users can freely define. We call these signal events.
Once you’re analyzing every trace, you also have too many individual events to read. That’s why we automatically group similar signal events into clusters. You can see recurring problems and how often they happen, then drill into individual events and the traces behind them.
You can use traces from a cluster to build an eval dataset for that type of failure. You can then use your favourite coding agent to hillclimb on those evals and check that the fix works across these cases before shipping it to prod.
Trace → analyze → catch errors and form clusters → fix → release. Making this loop easy is why we built Laminar.
We’ve put the same thought into the rest of Laminar. Our blog (https://laminar.sh/blog) explains how looking closely at how agents actually work led us to build 20x trace compression, a custom SQL query engine and automatic task extraction.
Laminar is Apache 2.0 and self-hostable (https://github.com/lmnr-ai/lmnr). We make money from the managed cloud.
We’d love to hear how you track your agents’ performance today. How much do you learn from user feedback versus your own monitoring? And when you fix something, how do you check that it hasn’t introduced a different failure?
Nice. One thing I'd want from a checker like this is a calibrated probability rather than a severity label. Decision models in the Jev style give a probability for every option in one forward pass. You can then pick a threshold and know roughly what share of traces you'll send for review. Does flow-1 expose anything like that, or is severity the only knob? Interesting. Most of the failures I've seen aren't the agent doing something obviously daft, it's a tool call that returns fine but the result shouldn't be trusted. Stale cached data, or a web page or file with text in it that's basically trying to give the agent instructions. Everything after that looks reasonable, it's just built on a bad input. Can flow-1 flag that kind of thing? And how does it tell the difference between the tool giving back something wrong and the agent misreading a result that was actually fine? From the trace alone those look pretty similar to me. this is exactly what flow-1 in Signal harness catches. highly highly recommend checking this out https://laminar.sh/blog/flow-1-in-action. We got examples of traces and errors we caught in them there We ran into an interesting side effect of agent performance that we needed to explain in our results to our executive team. In our case we were rolling out an AI support agent that could help resolve customer problems. At the start we had calculated the total time and human cost per support ticket going back a few years. After a few months of running the AI agent, we found that both our time and cost per ticket had increased - but then digging in, the issue was that our overall cost and time had decreased and it was just that the more complicated issues the agent wasn't able to answer were the ones now going to the humans, skewing our per ticket cost up. So in this case it's not that it was a different failure, it was that a signal that seemed to indicate failure was actually a signal of success. hm, did the cost of tickets processed by an agent go down tho? Yes, significantly - even when adding in vendor costs etc. In general though it is best at answering routine questions or ones a customer could get by reading the docs. The net result then is the ones left for the humans are the harder ones. We’ve also heard from other companies that as the first line paper cut questions get answered, customer adoption increases - which further increases the “hard” support questions. Lesson learned for me on that one that was rolling out a support agent led to both a better experience for our customers and an increased need for talented human engineers. To your question about how we track ours: one failure I had left no trace at all. A morning run on a resident agent just didn’t happen. The host timer runs on the uptime clock, the Mac slept through the slot, and nothing retries. As far as I can tell from the post, Signals reads traces that exist. Do you do anything for the run that should have happened and didn’t, like diffing against an expected schedule? How do you reuse traces as benchmarks (eval datasets)? Is it about being able to synthesise an agent session from the trace, and having another agent watch the first agent's behavior? Having trouble wrapping my mind around all the little details. Edit: I initially asked also about general tips for observing agents, but later, noticing that there were no interactions with my comment yet, edited my comment to remove that question, because I felt that it was too broad and would detract from my main question. To my surprise, both were answered by op after my edit; kudos! Good questions. Agent observability is based on similar primitives as regular observability (OTEL), but is wildly different. Trace payloads are huge, and errors are much more subtle, they are not increased latency or elevated 500 response rate. We recommend tracing everything in detail, and reading a few traces manually at the beginning while you iterate. At scale, the answer is almost always use another LLM look at your traces, which is what this post is all about. Evals are critical. I really recommend adopting the Anthropic's capability / regression eval model [1]. We also deeply believe that agent evals should be end-to-end, and as high-level as possible. This again often involves a quality LLM-as-a-judge, tuned on a set of manually labelled data. With this idea in mind (to answer your question), we think that, for eval datasets, the most crucial bit is to be able to store input of what your agent was asked about in production. Collect a certain distribution of inputs for happy and unhappy cases, and then run evals on those inputs. That's why Laminar went great lengths to help our users automatically get actual inputs their users send to their agents [2]. [1] https://www.anthropic.com/engineering/demystifying-evals-for... [2] https://laminar.sh/blog/extracting-tasks-from-agent-runs The point about paying to store traces nobody reads hit home. We had the same problem with customer interviews. We did 8 of them and the notes just sat in a doc until we tagged each problem by how many customers it affected. Curious how you decide which flagged errors matter most. Is it how often they show up across traces, or do you weight them by user impact? >Curious how you decide which flagged errors matter most flow-1 actually predicts how critical each finding is Very cool. I liked the high level overview where you can view it like do a funnel analysis for failures. Good for fast decision making. I wonder if you have thought of using this for the voice AI space for creating traces from many test calls to speed up testing of voice bots? It's true there are a lot of challenges _before_ one gets to the stage of running actual calls like creating good test data etc, but I wonder if you see a definite role for this framework in that space? >for creating traces from many test calls to speed up testing of voice bots I assume you mean tracing voice agents in general. If so, it depends on the where do you want to trace things. Right now, Laminar, unfortunately, doesn't trace voice SDKs like OpenAI's realtime, but we're very actively looking into it. However, if somewhere in your pipeline you have transcripts of your voice agents, then it shouldn't be that different from tracing any other agent. In this case, Laminar and Signals work perfectly. We also trained and benchmarked flow-1 on a lot of multi-turn voice agent like conversations. Congrats on the product! I love the design of the website and the app. Curious whether it was made in-house, by an external design agency, with AI models, or something else Thanks!
Our design is all done completely in-house. Workflows are constantly changing but our design process happens across Figma, old-fashioned paper, and code. To answer your question - we use cheaper models to just flag if something looks obviously flawed. That covers the vast majority of things because it's the propagation of obviously stupid stuff that causes a problem for our system. To the extent we are doing something sophisticated, we use an appropriate architecture, like it's built into the system. Thanks for the response! Curious, can you expand on the architecture, how does that work? If you can share of course. There are all manner of documented architectures in papers and books, I don't know that there is anything new under the sun at this point, the devil is always in the details. That said, some of the things we use off the top of my head: generate multiple responses using different models and have a third model judge the best answer; generate an answer and have another model critique the answer and then a third take the answer and critique and generate a new answer; multi-model debate; iterate in a loop either x times or until some condition is satisfied; pipelines of specific single calls to check for specific conditions. I'd say in general, with respect to errors/low quality responses etc you have to be extremely clear about what you are doing because once you get into the weeds, what is and is not an error is very grey in many cases. Interesting. Seems to me like latency is not critical in your application and you are doing something more like background processing rather than serving humans on the other side in real time. Also, some of what you describe sounds expensive. Do you find these techniques + cheaper models better than single-shot with larger models? Correct, latency is not critical. Yes, it can get expensive. We do something in financial markets where the cost of a single end to end task could be $100. That doesn't mean cost doesn't matter though, it matters a lot - if we screw up and it propagates, it's money down the toilet. And if we could get the task down to $20, it would make a difference. You should try the bullet points then earning someone reading the rest, that's where I bounced. I can write some bullet points if you want. I'm serious, this is not a sarcasm. With which AO platform do you want a comparison? Maybe this is me being the wrong persona since I clicked for the model and not the platform, but literally the moment my eye caught > Agent observability is crowded, so instead of a bullet list of how Laminar differs from X, we’ll explain how we’re solving agent observability from first principles my brain shut down and bounced minus the comment because it's a launch and maybe you'd want feedback. I'd be using this for post-training in a custom harness: so what you focused on during post-training and what it excels at are the most interesting things this is a very valid point. I will expand on RL post train here. I used GSPO because it worked really well for very long prompts (we're dealing with traces analyses so prompts are very very long, and by prompts I mean what goes into LLM call). We RL-ed flow-1 in our harness, which made it very efficient at using tools it had. Our harness as I said in the post is basically coding agent, it has grep, read and couple of other aux tools. I spent a loooot of time and money on figuring out the right RL recipe and especially the reward. It was really hard to find the right balance between exploration and exploitation. Some RL runs are still running, because the prod checkpoint as good as it is, thinks a lot. It produces a lot of thinking tokens, which affects the throughput, especially on the large, complex traces to be analyzed. So the next big challenge for me is to make it efficient thinker - i.e. reduce thinking tokens, without losing quality.
pmichalas - 43 minutes ago
nucleus777 - 12 hours ago
skull8888888 - 12 hours ago
scottfalconer - 12 hours ago
skull8888888 - 12 hours ago
scottfalconer - 11 hours ago
sebastienburel - 5 hours ago
dmos62 - 16 hours ago
dinm - 16 hours ago
paulariquelmee - 14 hours ago
skull8888888 - 13 hours ago
ghm2180 - 18 hours ago
skull8888888 - 18 hours ago
SantiDev - 18 hours ago
kolbeyang - 18 hours ago
danielmarkbruce - 17 hours ago
dinm - 17 hours ago
danielmarkbruce - 17 hours ago
dinm - 16 hours ago
danielmarkbruce - 16 hours ago
BoorishBears - 17 hours ago
skull8888888 - 16 hours ago
BoorishBears - 14 hours ago
skull8888888 - 14 hours ago