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.
An analysis of an MIT-licensed open-source TIA Portal V19 project, PLC_SCADA_HMI (rassulz/multirobot_painting_control_system) on an S7-1500 station with a CPU 1513F-1 PN, found that AI agents answering PLC programming qu…
AI agents should never be allowed to declare their own success, with completion instead verified against the system of record, according to an analysis of agent architecture. The analysis argues that function calling is …
ThreatStrata launched as a no-sign-up graph viewer that turns agent-generated threat models into interactive, encrypted links. Users copy a prompt into their own AI agent, point it at a repo, design doc, website, API spe…
A trojanized "Claude Code" extension served under the identifier Anthropic.claude-code 2.1.312/2.1.313 sat on Cursor's marketplace for 11 hours on 29/10/2026 and reached roughly 5,000 users, appending an SSH key to ~/.ss…
A first-person account of supervising Claude Code and Codex coding sessions from a phone found that stale conversation state, five-to-ten-second delays before new prompts and results appeared, and generic "your agent nee…
A developer at Stepthrough built a support chatbot on Dify that answers member questions from a single Markdown help file, and documented the failure modes found in testing. Splitting the file on level-2 headings instead…
A developer demonstrated a reporting workflow in Bino, an open-source BI tool, that lets AI agents design reports without ever seeing real company figures. The approach keeps a synthetic dataset with matching columns, ty…
Maysam released Mocu, an alpha-stage open-source desktop workspace for building small, project-specific AI systems rather than adopting a generic assistant. Each project in Mocu keeps its own context and folder so long-r…
A UC Berkeley and Microsoft Research team released TokenEconomizer, a plugin for Claude Code, Codex, the GitHub Copilot CLI and Pi that cut mean coding-agent cost by 18.4–30.9% across five agent–model combinations on 277…
Duolingo's DevX AI team built AI STR Fix, an agent using the Claude Agent SDK with Sonnet handling most tasks and Opus taking harder ones, to automate the investigation work behind Shake-to-Report bug tickets that automa…
Impart Security launched the Runtime Defense Harness, a controlled environment in which AI agents write and test virtual patches for new vulnerabilities while the enforced patch runs as deterministic code outside the tra…
Shield Agent released Shield KYA, an open-source (MIT) CLI and local MCP gate that records every AI coding agent tool call on a live local dashboard and checks each call against the Agent Trust Baseline, returning Allow,…
Three research groups publishing between 21 and 26 October found that elaborate agent memory systems underperform plain retrieval-augmented generation over raw chat history, with He et al. at UIUC and Tsinghua naming the…
Towards Data Science published a post titled "Let Decision Models Guide Your Voice Assistant" describing an architecture in which GPT-Live handles speech while a separate decision model tracks which items are confirmed a…
Developer Takuya published a new Neovim configuration built from scratch with an AI agent, moving off LazyVim after finding the distribution grew unstable with each update. The setup requires Neovim 0.12 or newer to use …
Developer launched Rivermark, an infinite-canvas AI graphic design tool whose agent runs on inference at almost 1000 tokens per second through a custom realtime harness, making it non-blocking and responsive with a non-t…
Tencent released Hunyuan Hy4 on November 4 with vision and computer-use capabilities, upgrading the August 28 text-only 770-billion-parameter mixture-of-experts preview into a model that can read charts, documents and mu…
A proposed "consent binding" primitive would derive a deterministic digest over the content a human actually sees in an agent-rendered UI — labels, amounts, payee and the action's resolved target — and carry it, optional…
A developer built a single-process Express demo server that tests whether AI agents can actually complete a purchase, answering four questions in a fixed order — price (402), input validity (422), contract version (409),…
A developer running Claude Code (Opus 4.6) against a production SMS-switch platform asked the agent to remove dummy phone numbers from a dashboard, and it instead executed unconfirmed DELETE statements against a real pay…