Launch HN: Voker (YC S24) – Analytics for AI Agents

Nice, sounds like you've set up your own solution in house. We definitely see some teams do that, and for some it works perfectly, for others, its too expensive to maintain - they get new requests for new dashboards or different subcuts of data from product or design teams, or they run into an issue like way too many intents generated to be useful, and its not worth the tradeoff of investing time in building internal tooling. But for some it makes sense to roll your own! It also really depends on how many people on the team are involved in building the agent products, and how much volume your agents have. If you have millions of conversations a month with thousands of unique intents, you have to set up data eng pipelines just to process categorize, and store all that data in a way thats usable for the whole team.

When it comes to Langsmith, we hear about them a lot from our customers, pretty much all of them love it as an obs tool, but most say that only the engineers have access or spend time in it, and they've told us the strength of Langsmith is its technical tracing, not its visualizations, ui, or usability. They've told us any "insights" are very canned (because thats not Langsmith's key focus).

We add self-serve analytics - like how Google Analytics lets marketers see how their website is performing without needing to ask engineers to write SQL queries on cloudwatch logs.

Ex: PM can self-serve and look at trends in what users are asking of agents, notice a problem, do a quick RCA, look for reproducibility across other sessions - before deciding to assign as an issue to engineer. Old way would be: PM hears a complaint from a customer, asks the engineer to "look into it" and the eng spends 4 hours combing through Langsmith logs to hunt down one session without even knowing if its actually a widespread issues

- To me, the line "Do you really know what your agents are saying to your users?" doesn't match at all with the screenshot directly above, which is the first screenshot on the page. On first glance, all that screenshot conveys to me is "some analytics app". Perhaps the first graphic could better express what about agents' activities, is being made easier to inspect.

- I click "How it Works" and I just get vaguely described screenshots. Only from reading the Python import line in the fourth screenshot, I get that it acts as a middleware by sitting in for the OpenAI import. Maybe this nav should link to the section above, with the 3 integration steps?

- Scrolling down and seeing Intents vs Corrections vs Resolutions, I'm actually getting a sense of what Voker does. To me, that still doesn't fully align with "Do you really know what your agents are saying to your users?"

- I'm mildly amused by the fact that whiteboard desk guy is copying roadmap suggestions from ChatGPT.