83 browser-use trajectories, visualized
Hey all, Justin here. I previously built Phind, the AI search engine for developers. One of the biggest problems we had there was figuring out what went wrong with bad searches. We had tons of searches per day, but less than 1% of users gave any explicit feedback. So we were either manually digging through searches or making general system improvements and hoping they helped. This problem gets harder with agents. Traces are longer and more complex. It takes more effort to review them, so I'm building a tool that lets you analyze LLM outputs directly to help developers of LLM apps and agents…
What it does
In the maker’s words, at launch
Hey all, Justin here. I previously built Phind, the AI search engine for developers. One of the biggest problems we had there was figuring out what went wrong with bad searches. We had tons of searches per day, but less than 1% of users gave any explicit feedback. So we were either manually digging through searches or making general system improvements and hoping they helped. This problem gets harder with agents. Traces are longer and more complex. It takes more effort to review them, so I'm building a tool that lets you analyze LLM outputs directly to help developers of LLM apps and agents understand where things are breaking and why. I've put together a demo using browser-use agent traces (gpt-5): https://trails-red.vercel.app/viewer It's early, but I have lots of ideas - live querying of past failures for currently-running agents, preference models to expand sparse signal data. Would love feedback on the demo. Also if you're building agents and have 10k+ traces per day that you're not looking at but would like to, I'd love to talk.
Does the same job
all alternatives →- IBi built an AI code reviewer for github (used it on itself during dev)2025 · codii.dev · ▲6
I’ve spent the last 2.5 months building a product that runs LLM-powered code reviews on my pull requests — and I just launched it. The tool is built specifically for solo developers. You install it on your repo, trigger a scan by creating a pull request, and it leaves structured review comments using OpenAI under the hood. Funnily enough, I used the dev version of this app to review its own pull requests while building it. It helped me spot bugs, simplify structure, and keep quality high — all with minimal need for another human in the loop. Things I want to try out in the next months : -…
- IBI built a tool to roast landing pages using AI agents2024 · roastmylandingpage.io · ▲9
I built a tool to roast landing pages with AI agents. I was gathering feedback from watching landing page roast videos, and figured out I could prompt LLMs to analyse a screenshot and roast based on the same criteria. It's not 100% accurate yet, but it has been really insightful when I've tested it on my own websites. Let me know what you think!
- IMI'm Building Ahrefs for AI Search Results2025 · linrush.com · ▲9
AI search results are quickly becoming more important than SEO, but as businesses, we have no visibility over it! That's why I'm building "Ahrefs for AI search results". Track keyword performance on AI tools like ChatGPT, Claude, Perplexity & more
- KTKeep track of what different AI's say about you2023 · haveibeenencoded.com · ▲5
Hi HN! I built this tool, because Large Language Models are hallucinating their asses off and I wanted to test just how bad it is with a topic I know best - myself. I'm sure there are other egos out there who google themselves and essentially this is the new googling yourself. It's early beta, so lots of room for improvement of course.
- IBI built a tool to make AI recommend you (and I'm conflicted about it)Dec 2025 · firstclick.so · ▲7
So I've been obsessed with a weird question for the past 6 months, what happens to SEO when everyone starts asking ChatGPT for recommendations instead of Googling? The answer, apparently, is chaos. And maybe opportunity? I built FirstClick because I noticed something strange. My previous startup was getting zero traffic from AI assistants, but our competitor (objectively worse product, sorry not sorry) was getting mentioned by Claude and Perplexity constantly. It drove me crazy. So I reverse engineered why. Turns out there's a whole new game being played and most founders don't even know it…
- SOState of AI Agents 2024 – 184B tokens · 786M runs analyzed2024 · langbase.com · ▲6
hello everyone, my first post! AA here, founder of ⌘ Langbase.com — we are a developer platform for building and scaling serverless AI memory agents. I know surveys can be boring, but this one’s different—it’s interactive! That's very much intentional. My team and I have been up for the last 21 hours putting together this report. This was a looot of work, so I hope y'all like it. Introducing … State of AI Agents 2024 report On Langbase, we processed 184 billion tokens and handled 786 million AI agent runs from 36K developers. From all that data plus insights from 3.4K builders who filled out…
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 · 16d 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 · 26d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
