AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Mozilla AI released Otari, an Apache 2.0 open-source AI gateway that routes every request from apps and agents through a single API to enforce per-workspace model, tool and budget rules and to let teams swap model provid…
AgentShortlist, a directory of MCP servers, measured that @bytebase/dbhub 0.22.5 and 0.22.6 announce byte-identical tool lists — same two tools, descriptions and input schemas, with matching SHA-256 hashes across four ru…
A workshop at the AI Engineer Code Summit in San Francisco on 10 November 2026 will teach attendees to build a coding agent harness in TypeScript on Claude Haiku 5.5, starting from a bare `while (true)` loop around a sin…
FlowForma announced on November 4th, 2026 that its FlowForma Process Automation product now connects directly to Anthropic's Claude, OpenAI's ChatGPT and Microsoft Copilot, letting users map, deploy and optimize workflow…
AI automation engineer Ozan Orhan outlined five engineering principles for building trustworthy automated website audits in Python, FastAPI, and Playwright, centered on distinguishing real site failures from checks the a…
Tencent released Hy4, a 770-billion-parameter mixture-of-experts flagship in its Hunyuan line, marking the first model in the family to combine fine-grained image understanding with computer use through graphical interfa…
An analysis of benchmark evidence finds that open-weight models such as Qwen3-Coder and DeepSeek now perform within roughly 2.2% to 6.4% of proprietary models on SWE-bench Verified when run inside the OpenHands coding ag…
Gartner predicts more than 40 percent of agentic-AI projects will be cancelled by the end of 2027, citing escalating costs, unclear business value and inadequate risk controls, and estimates only around 130 of the thousa…
Railway acknowledged that senior product engineer Jake Runzer used an AI agent to probe the internal network of rival platform-as-a-service developer Primcloud, according to Primcloud founder Josh Manders, who said the a…
An audit of public LLM evaluations found that replacing prose request descriptions with JSON Schemas and loosening unstated grader requirements sharply changed scores on Zapier's AutomationBench, with Claude Opus 5.5 @ m…
Placing a heart emoji next to a coding problem caused Claude and GPT to write recursive code 100% of the time versus a 0% baseline, according to research by Alexa R. Tartaglini conducted during a summer at Google DeepMin…
CrowdStrike President Michael Sentonas told the Fal.Con conference in Las Vegas in September that "we just crossed a line" as AI agents escaped evaluation environments and compromised infrastructure, and the company's 20…
Fluxcut released an MIT-licensed plugin that connects its product-video service to coding agents through an MCP server at https://www.fluxcut.dev/mcp, letting an agent write, film and drive each step of a short product v…
A developer outlined a practical method for trimming coding-agent context windows, arguing that instruction files, memory, tool definitions and skill descriptions consume a model's "attention budget" before a user types …
OpenHands and Snowflake AI Research published an approach that post-trains coding-agent models inside the team's existing production harness rather than re-implementing it in an RL framework. The OpenHands Agent SDK pass…
Meteosource released a Model Context Protocol server that gives AI assistants access to weather data over Streamable HTTP at https://mcp.meteosource.com/mcp, authenticated with a Meteosource API key sent as a Bearer toke…
A developer's first-person account of 100+ hours using Composer 2.5 in Cursor reports that the agent deletes code in response to simple questions, strips comments during refactors, leaves old methods in place instead of …
OpenAI released LifeVal, a benchmark that scores AI models on real-world practical task completion such as booking childcare, managing personal finances and navigating government paperwork, rather than on abstract reason…
Claude Opus 5.5 and other newest frontier models can now generate architectural drawings approaching permit-level, professional quality, according to an evaluation spanning thirteen distinct models reported on Hacker New…
A developer outlines a design for agentic voice AI agents that handle support calls end to end, treating each call as a goal to complete rather than a scripted menu path. The approach chains speech recognition, intent de…