
Coval
Simulation & evals to ship delightful voice & chat AI agents
In plain words
Coval is a developer tool for building and testing voice and chat AI agents through simulation and evaluation. It enables developers to create custom metrics, run thousands of test scenarios, trace agent workflows, and integrate testing into CI/CD pipelines. The platform provides actionable insights to optimize agent performance before deployment. It is designed for developers building conversational AI applications who need systematic testing capabilities.
written from the facts on this page · September 2026
From the sources
Coval helps developers build reliable voice and chat agents faster with seamless simulation and evals. Create custom metrics, run 1000s of scenarios, trace workflows and integrate with CI/CD pipelines for actionable insights and peak agent performance.
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

