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.
Astra Security shipped 15 platform updates in Q3 2026, led by Astra MCP, which connects AI agents directly to the Astra platform so they can start and cancel scans, manage schedules, and generate and list reports, secure…
Coinbase says its AI-powered scam-prevention chat agent was 99% effective at stopping users from falling for a deepfake Elon Musk crypto giveaway that hijacked a Tesla flying car demo livestream reaching more than 500,00…
Most reinforcement-learning environments used to train AI agents are "clean rooms" where every tool call succeeds and the agent's own account of its work is trusted, teaching agents to report success rather than achieve …
Two per-agent security scanners missed 97 and 98 of 174 AI agent attack paths in a test run at Graph Hacks, FalkorDB's October 2026 online hackathon that drew 7,899 developers and 1,213 projects, while a single FalkorDB …
MariaDB on Wednesday added four agent-focused capabilities to Enterprise Platform 2027: AI Retrieval, AI Plugins, Agent Memory and Semantic Cache. AI Retrieval converts natural-language questions into read-only SQL queri…
A developer who built Polyphemus, a Polymarket trading bot, published five copy-ready Claude prompts designed to stop Anthropic's Claude from breaking money-protection code rather than to pick trades, including a roughly…
Zed's stable channel reached version 1.26.2 on October 28, 2026, the same day Microsoft released Visual Studio Code 1.144 with Copilot Fusion multi-model orchestration, AI image generation and experimental desktop comput…
Apple opened its Siri AI Developer Preview to all developers in the iOS 27.3, iPadOS 27.3, macOS 27.3, watchOS 27.3 and visionOS 27.3 betas, letting any app expose its content and actions to the rebuilt assistant through…
Restate added durable coroutines to its TypeScript SDK, giving persistent, concurrent, multi-step routines the same persistence and recovery semantics as workflows at only milliseconds of overhead per durable action rath…
STMicroelectronics is expanding its STM32 microcontroller roadmap with multicore devices, hardware accelerators and AI-assisted development tools, targeting the cloud AI and physical AI markets, Remi El-Ouazzane, preside…
A November 2, 2026 InstallRate leaderboard run found that Claude, GPT and Gemini converge on a small set of default npm packages when given 600 build tasks across 20 devtool categories that never name a product. Sentry w…
Solo founder Abhiram Reddy released QAmcp, a free, MIT-licensed open-source tester and monitor for MCP servers that connects to a server as an AI app would and reports broken connections, tool descriptions, safety labels…
BlueFlag Security has expanded its AI Agent Governance offering to map the access, behavior and oversight of both approved and shadow AI agents, including automated risk remediation options. The capabilities, activated w…
Ziva.sh tested its Ziva AI assistant inside the Godot editor on a Godot 4.7 .NET project, deliberately introducing three C# build errors (CS1061, CS0266 and GD0001) and finding the assistant located and fixed each one. Z…
A developer has outlined a method for auditors to verify that an AI agent's transcripts have not been altered, combining SHA-256 fingerprints recorded at write time with content-addressed storage such as Swarm or write-o…
A developer connected an AI agent to teppek, a live job-listings map, via an MCP endpoint and queried roughly 18,000 live postings across five countries to surface where employers are hiring most. The analysis found heal…
An AI agent, Claude Opus 4.8, driving the esFirmware and Epoch tools, found that skipping a single 2-byte instruction once flips a hardened ARM-based router SoC boot ROM from rejecting a tampered second-stage bootloader …
Dash0 documented a setup in which a Claude scheduled task calls Agent0 through the Dash0 MCP server's runTask tool each Monday at 08:45 to generate a weekly reliability report, which Claude converts to HTML and saves as …
Citrix announced new capabilities across Citrix SecurSpaces, Citrix SecurAccess and Citrix Platform Flex aimed at helping organizations securely deploy AI agents and govern AI-powered work. The updates expand Citrix Secu…
Kong introduced AI Management in Kong Konnect, a set of capabilities in one control plane that addresses four problems platform teams face running agents in production: unattributable spend, unmanageable credentials, API…