Gemini Decision 1 lands on Vercel AI Gateway
Vercel added Google's Gemini Decision 1 to AI Gateway. The model returns booleans, choices and scores for routing, policy checks and ranking, without generating output tokens.
AI industry news for people who build software: model launches, coding agents, app builders, APIs and pricing, with primary sources.
Vercel added Google's Gemini Decision 1 to AI Gateway. The model returns booleans, choices and scores for routing, policy checks and ranking, without generating output tokens.
browser-use 1.0.4 batches old screenshot pruning so provider prompt caches survive, dropping model cost per task on BU Bench v2.1 from $0.434 to $0.208.
Google AI Edge Gallery now runs speech recognition and text-to-speech fully on device, with an Android ML Kit path and a cross-platform MediaPipe and LiteRT path.
AWS's guide shows three ways to route OpenAI Codex model requests through Amazon Bedrock, from a native IAM pilot to a managed AgentCore Gateway or an LLM gateway.
A GitHub skill for Claude Code and Codex walks an AI agent through building a playable browser 3D action game, with a 33MB single-file demo included.
cinecode, an MIT-licensed Python repo with 2,446 stars after 11 days, has an AI coding agent write the script, build every frame in code and export an MP4.
A nine-day-old MIT-licensed React library offers 44 pure-SVG charts, plus a JSON Schema, CLI and MCP server that let AI agents validate specs and render them to images.
Claude Agent SDK v0.3.323 landed on 12 November with two alpha host APIs, an opt-out for subagent progress summaries, and fixes for policy reads, permissions and session forking.
Browser Use's 1.0.4rc1 batches screenshot pruning so the agent stops breaking the provider prompt cache, and adds a Chromium fallback for BU_NAME callers.
Replit Agent now buys business supplies through Link and Visa, with checkout held for your approval, and runs Google Ads for Pro users worldwide.
Google Cloud has made an Anthropic-managed Claude deployment option generally available, running alongside the Google-managed option at the same models and pricing.
Cursor's Agent SDK keeps an agent in a directory of files, tests which tools it calls with evals, and deploys it on Cursor's infrastructure or your own.