Microsoft has released Microsoft-Decision-1, a decision model for routing, classification, verification and agent control. Microsoft-Decision-1 is a decision-scoring model that returns a calibrated probability for each fixed answer option instead of generated text. It is post-trained from Alibaba’s Qwen3.5-9B and available now in Microsoft Foundry and OpenRouter. . TL;DR What is a decision model? A […] The post Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model appeared first on MarkTechPost .
Hi, I'm a former SDET and now solo dev of VoiceGremlin, a tool for automated tests against AI that answer phones. You pass the API a phone number and a test case like "Verify that the agent does X." It calls your voice agent, tests the thing by having the bots talk to each other, and uses LLM-as-judge to provide a pass/fail for your pipeline. State: Fully working, free trial, no card needed. Try it out and please give me feedback, especially if you run in to problems. Goal: I built VoiceGremlin with the explicit goal of being Mailosaur for phone agents. We paid for Mailosaur at work because the alternative (having our automated tests interact programmatically with our corporate Outlook server) was doable, but very painful, both technically and organizationally. The lesson I learned was "doable, but painful" is a good sign of a SaaS opportunity. Well, getting an automated test to call a phone number is also painful. Telephony providers are tough to get onboarded as vendors. Using your own STT/TTS means a lot of bandwidth moving through wherever you run your test automation from. It's tricky to get the LLM-to-LLM prompts dialed in enough to avoid flaky tests. Etc. Process: It took about 45 days to build, with half of that being businessy stuff like implementing Stripe and my feeble attempts at marketing, and the other half being experimenting with different telephony providers and features, testing different models, prompt tweaking, and fraud/abuse prevention. Design goal: Do one thing, do it well, and get out of the way. There's no ambition to manage your test cases for you, host your voice agents, or add upsell features. Stack: The dependencies are Supabase (DB and authentication), Netlify (static storage and API routing), Digitalocean (the server component that makes the calls), Telnyx (easier to work with than Twilio IMO), Stripe, Openrouter, Cloudflare (captcha on signup). Oh, and I host my private git in Keybase, the greatest tool nobody uses. Thanks! Comments URL: https://news.ycombinator.com/item?id=49995804 Points: 1 # Comments: 0
In 2023 most people doubted that there could be more than 1 or 2 frontier model labs. Now there are dozens.... and Stripe just bought the best known one for $7B.
Hi there :-) New on HN, first time posting. Past year, around December, I started experimenting with making ChatGPT and Claude generate source code in LDraw language. This LDraw is literally an "assembly" language, a low-level programming language that describes how to assemble LEGO pieces together into models, one placement instruction at a time. When executed by specific tools, like e.g. LDView, LeoCAD, Studio... these instructions become LEGO CAD models, that can be interacted with, modified, etc. Or, in other words: one LDraw source file in .mpd or .ldr format is equivalent to one LEGO CAD model. So, the idea I had was: if I manage for maybe ChatGPT or Claude to generate high-quality LDraw source files... then, they would actually be generating high-quality LEGO CAD models, right? Then, after months of iterations and trying one thing after the other... it worked!!! Long story short: using GPT-6 Astra and Opus 5.5, I've managed to create a python toolset, instructions, and docs for agents in general. Now, these can be used by them to generate LDraw models. I've packed it all as a dockerized web app for others to try and experiment, with several providers (and agents) to choose from: OpenAI, Claude and OpenRouter. I'd really appreciate feedback and comments, let's see where this goes =) Comments URL: https://news.ycombinator.com/item?id=49937916 Points: 9 # Comments: 2
Hi HN - long-time lurker (since 2012!), first time poster. Pizza Bot is a self-hosted desktop app for Mac, Windows, and Linux that runs AI agents in the background and exposes them through an email-like UI. Finished work shows up in Unread, and anything waiting on your approval shows up in Action. It's Apache 2.0-licensed, there's no signup and no telemetry, and you bring your own model provider: Anthropic, Amazon Bedrock, Google Gemini, OpenAI, OpenRouter, or a local model through Ollama. There are builds on the releases page, or you can run it from source. Pizza Bot started as an internal passion project I worked on with a small team at Amazon. The whole thing came out of my frustration at having to manually log CRM activities through a browser form. I built a simple REST API called "JoeBot" that connected to my authenticated browser session over CDP and filled out the form for me using Playwright. Then I hacked up a quick Obsidian plugin so I could trigger it from my local notes (no AI and no MCP servers involved). This caught on quickly. My fellow AWS Solutions Architect Igor Fil joined up with me, and we rebranded the project as "Pizza Bot," named after Amazon's two-pizza teams. We started seeing what other automations we could build. We found a GraphQL API we could query and hacked up some "recipes" to pull data out of the CRM to help with meeting prep. That worked great, and it was right around the time MCP servers seemed to be taking off, so we decided to expose Pizza Bot as an MCP server instead, so it would be available to AI tools through natural language. This was a decent solution for technical users, but the Account Managers who live inside our CRM system wanted something too. We decided to rebuild Pizza Bot as an Electron desktop app modeled after an email inbox, so it would be familiar to non-technical users and would run on both Mac and Windows. We also bundled internal MCP servers as OCI images and hosted them in Amazon ECR as an "addon marketplace" so users could install them with one click without having to set up Amazon developer tooling. The project took off organically and expanded outside of AWS into the wider Amazon organization globally. More than 2,000 people ended up using it for meeting prep, email drafting, Slack summaries, CRM logging, prioritizing their day, and web research. Once apps like Claude Cowork and Amazon's own Quick Desktop came out, we realized the real growth opportunity was outside of Amazon. Rather than try to rip out the Amazon-specific integrations, we rebuilt Pizza Bot once more as an open source project. We leaned on coding agents heavily, which is the only reason a team our size could pull off a full rewrite. I'm pleased to say it's finally public, and we're hoping to bring in community members and see where it goes. We'd like to do for knowledge workers what Claude Code and Codex have done for programmers. A couple of things to know up front. Most of what made Pizza Bot useful on day one inside Amazon came from that internal catalog of skills and MCP servers for Amazon's own systems, and none of it could come out with the app. So it ships thinner than the version those 2,000 people used, and building that catalog back up for tools other people actually use is where we need the most help. It's also a community project and not an AWS service, so there's no support or SLA behind it. The Windows and Linux builds aren't signed yet either. On the technical side, Pizza Bot is a server and a client. The desktop app bundles both, or you can point a client at a remote backend; personally, I self-host the server on my home network and reach it from my phone over Tailscale. The server owns the thread lifecycle and checkpoints state with DeepAgents and LangGraph, and clients rehydrate from it as needed, so you can disconnect mid-run and pick the thread back up from another client. Approval pauses outlive the session that created them and collect in an Action filter, so you can answer an hour later from a different device. The agent you talk to has a sandboxed QuickJS interpreter that can reach your filesystem only if you grant it a folder, but its main job is to delegate. Each subagent is a 1:1 mapping of a Skill, and an Activity bar shows that subagent and the tool calls it's making as it works. Memory is opt-in and stored as plain markdown files on your machine. Every tool call is explicit, including looking up a memory - we err on the side of transparency to reduce surprises. Tools come from MCP servers, and skills are ordinary SKILL.md files with a per-tool approval policy, so existing skills that don't require a code interpreter should still work. What I'd most like to hear about is where the app itself gets in your way, the kind of problem you can't fix by writing a skill or an MCP server. I'm around today to answer questions! Comments URL: https://news.ycombinator.com/item?id=49713894 Points: 15 # Comments: 5
We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accepted, but not that an LLM changed only what the developer authorised. We present CAPRI, a contract-aware repair workflow in which Isabelle checks the proof and an independent checker enforces a machine-readable edit contract. Prompts, proposals, candidate repositories, diagnostics, verdicts, and hashes are retained for audit. We evaluate five workflows on twelve failed proofs from four developments, with three replicates per task and condition, giving 180 runs and 138 valid repairs. Of 144 terminal candidates accepted by Isabelle, six had modified protected text; all arose in iterative workflows that could edit a complete theory. A proof-body-only interface produced 29/36 valid repairs and no contract violations, compared with 31/36 for the corresponding full-theory workflow. One-shot repair produced 22/36, while a later prospectively frozen iterative workflow produced 32/36; these figures compare complete workflows rather than individual mechanisms. A separate post hoc OpenRouter campaign found no improvement in the designated Luna comparisons. A Sol configuration with matched demonstrations produced 33/36 repairs, compared with 29/36 in the frozen OpenAI Responses condition, but the difference was not statistically significant in a one-sided exact McNemar test ($p=0.0625$).