Weco AI Functions- a text-to-agent dev tool
Hey HN, I’m Zhengyao, one of the creators of Weco AI Functions — a platform that transforms plain-English task descriptions into reusable AI endpoints that you can use as Python functions. We take a plain-English description of your task (e.g., “get the top 10 contributors of a given GitHub repo,” “extract phone numbers from text”) and turn it into an AI-powered endpoint with structured output. Key points: - Schema-first: You describe the task; we propose an output schema. Refine it if you like. - Version control and A/B testing: Each change to your function creates a new version…
In plain words
Weco AI Functions is a platform that converts plain-English task descriptions into reusable AI-powered endpoints callable as Python functions. Users describe a task, the system proposes an output schema for refinement, and generates a structured API. The platform includes version control for tracking changes, A/B testing across models and prompts, configurable settings like temperature and chain-of-thought reasoning, and monitoring with input/output logging and aggregated statistics for tracking performance and costs.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I’m Zhengyao, one of the creators of Weco AI Functions — a platform that transforms plain-English task descriptions into reusable AI endpoints that you can use as Python functions. We take a plain-English description of your task (e.g., “get the top 10 contributors of a given GitHub repo,” “extract phone numbers from text”) and turn it into an AI-powered endpoint with structured output. Key points: - Schema-first: You describe the task; we propose an output schema. Refine it if you like. - Version control and A/B testing: Each change to your function creates a new version automatically. Compare cost, latency, or accuracy across multiple models and prompts on the same input. - Configurable: Tweak advanced settings like chain-of-thought or temperature. Use custom internal prompts if you want deeper control. - Monitoring: We log inputs/outputs and show aggregated stats, token counts, and cost in one place. For Python developers, simply import aifn, and use AIFunction(<your function name>) to get a regular Python function powered by AI. That’s it. If you want to integrate the function into other languages/softwares, our REST API requires just a single POST request. We’d appreciate any feedback or suggestions. We’re in early access, so if something’s off, let us know—this is exactly the stage where your input is super valuable. Check it out at https://aifunction.com or see our docs for more details on how it all works. Thanks for reading. Happy to answer questions or hear your thoughts!
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 · 26d ago · cactuscompute.com
Launched alongside, January 2025
the whole month →- IM
Hello! I'm Byran. I spent the past ~6 months engineering a laptop from scratch. It's fully open-source on GH at: https://github.com/Hello9999901/laptop
Dev tools · 2025 · byran.ee
- TITetris in a PDF▲1,289
I realized that the PDF engines of modern desktop browsers (PDFium and PDF.js) support JavaScript with enough I/O primitives to make a basic game like Tetris. It was a bit tricky to find a union of features that work in both engines, but in the end it turns out that showing/hiding annotation "fields" works well to make monochrome pixels, and keyboard input can be achieved by typing in a text input box. All in all it's quite janky but a nice reminder of how general purpose PDF scripting can be. The linked PDF is all ASCII so you can just open it in a text editor, or have a look at…
Life & fun · 2025 · th0mas.nl
Create lifelike, personalized AI avatars from text prompts
AI · 2025 · jogg.ai
