Open-source dashboard for your domain experts to improve your AI Agents
Hey HN! We built EvalKit, a library you embed to capture agent actions and a UI where domain experts give feedback, evaluate and improve AI agents. We experienced, in large agentic systems, prompt-engineering or auto-prompt improvement tool can get accuracy from 0 to 50% but for increasing accuracy to 100% we had to work with domain experts. Example -> In a law ai agent, lawyers are needed because law is complex and lawyers have a deeper context compared to non-lawyers. Other evaluation tools in the market focus on the experience of the developer and we are focusing on making as easy as…
What it does
In the maker’s words, at launch
Hey HN! We built EvalKit, a library you embed to capture agent actions and a UI where domain experts give feedback, evaluate and improve AI agents. We experienced, in large agentic systems, prompt-engineering or auto-prompt improvement tool can get accuracy from 0 to 50% but for increasing accuracy to 100% we had to work with domain experts. Example -> In a law ai agent, lawyers are needed because law is complex and lawyers have a deeper context compared to non-lawyers. Other evaluation tools in the market focus on the experience of the developer and we are focusing on making as easy as possible for your domain experts to improve agentic systems on their own. Each agent action automatically routes a feedback request to the appropriate domain expert; once they respond, the system pinpoints the responsible agent and applies the necessary change which they can test. We’re borrowing our OSS business model from Supabase who makes it easy to self-host with features reserved for enterprise and a paid version for managed cloud service. Right now, all of our code is available under a permissive license (MIT). We’re admittedly early, and many features are in the process of being built. We would really appreciate a star and feedback on how we can make it useful to you. Thanks!
Does the same job
all alternatives →
- WBWe built an AI Website builder with better output2024 · dorik.com · ▲8
Hey HN, After GPT-3 created waves in the tech industry, a lot of AI tools were emerging and with that, some AI website builders But the results seemed way too generic to us. It felt like the developers were rushing to catch the wave instead of building a proper tool We took our time, did months of RnD and finally came up with something better than what others in the market are doing. It’s got better design output. While it’s still in beta, I wanted to show HN what we did. Will appreciate the feedback when you guys try it out. Here is the link to signup for the beta:…
- AEAgent-evals – Claude skill to build your own evalsMay 2026 · github.com · ▲9
I’ve spent the past 10 years working on AI in finance, with much of that time focused on building evaluation systems for production environments. As agents become more widely adopted, more software engineering and product people have start building them. But I’ve noticed that many teams are not yet fluent in systematic evaluation, or in the processes needed to keep agent quality high over time. For large organizations, that gap is rarely the bottleneck due to dedicated teams. But after speaking with a number of startups, it became clear that building strong, up-to-date evals is much harder…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
