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.
Box announced Box Context Retrieval, a search engine built on Nvidia's Nemotron models that sits between an AI tool's question and a company's documents, and Box Architect, a workflow builder that generates automated AI-…
A developer published a standard-library-only Python script, preflight.py, that scans git-staged files for secrets and high-entropy strings before they are assembled into an agent prompt, scoring findings by severity and…
A tutorial published with a five-minute video shows developers how to build a working AI "harness" in 26 lines of free, open-source Python using PraisonAI, the open-source agent framework from MervinPraison, to stop a mo…
Snowflake unveiled Business Ontology, a data governance tool that gives AI agents access to approved business definitions to reduce inconsistent answers, expected to enter public preview soon as part of Snowflake Horizon…
A developer built Gatekeeper, a four-agent system on the open-source Switch platform that intercepts a coding agent's package installs and other risky actions in team chat before they execute, asking a dedicated verifier…
Match Group CEO Spencer Rascoff wrote in a New York Times op-ed published November 4 that AI agents are barred from Tinder and Hinge, saying the company has "put in place guardrails meant to prevent the use of AI agents …
A November 4, 2026 arXiv paper (q-fin.CP, 2611.06607) describes Autonomous Quant Researcher, an open-source LLM research loop for quantitative finance in which the model proposes strict declarative JSON changes and only …
Zura launched Revline, an open-source, Apache 2.0 agentic video editor that loads an agent with 100+ tools to analyze footage and make edits without manual timeline work. Revline analyzes footage using Deepgram, Gemini a…
Developer John Robinson released macvoice, an open-source tool that gives Claude Code a hands-free voice mode running entirely on a MacBook, with listening, voice-activity detection, transcription and speech synthesis ta…
Cyberhaven launched Agentic Data Security (ADS), a product the company says lets CISOs, data security teams, insider risk teams and AI governance leaders monitor what every AI agent does with company data, who the agent …
JetBrains shipped PyCharm 2026.3, which bundles JetBrains Air, a new layer for agentic development that lets developers run, track, and verify multi-agent workflows inside the IDE. Air supports Claude Agent, Codex, Gemin…
Isoform released an open-source Mac app that observes a user's activity on the computer, stores memory on disk, and routes model work to the user's own Claude Code, Codex, or Ollama rather than shipping its own model. Th…
Inngest co-founder and CEO Tony Holdstock-Brown reported that server timeouts or dropped connections appeared in 41% of affected accounts running long-running agents, compared with 15% for LLM API errors, arguing the mod…
SaaStr's AI agent, 10K, ran an email deliverability bake-off across three vendors and more than 500,000 emails, finding a challenger vendor delivered 50.5% unique opens versus 21.0% for the incumbent in a matched split o…
DeepSeek has opened the web search infrastructure behind its models to developers with two new endpoints, a Search API that returns up to 50 ranked results per response and a Fetch API that returns a public page's main c…
Zep announced Zep Agent Skills, a production service that compiles an agent's verified runs into versioned SKILL.md procedures in the open Agent Skills format, with each step linked back to the run events it came from. I…
JetBrains detailed in the second post of its developer diary series how its production-grade Air Context RAG system for semantic code search stores and retrieves millions of code vectors, combining approximate nearest-ne…
A Stanford University paper posted to arXiv on November 2, 2026 (arXiv:2611.02633) found that frontier AI models reached the best team deal in only 14% of conflict scenarios with a pressuring teammate, versus 100% workin…
Kong AI Gateway can attach SSO (OIDC) identities, gateway keys and cost-center tags to every LLM request so organizations can charge model spend back to teams without pushing user identities into AWS, Azure or Google Clo…
Supermicro announced on November 5th, 2026 a KV cache solution built with IBM and NVIDIA that the companies say delivered up to 56x faster first tokens in joint testing with reused long context at 130,000-token prompts. …