AI Agents news and analysis on Web Pulse: 14146 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
UiPath CEO Daniel Dines, whose company automates office work, is urging business leaders not to rush into cutting jobs as they adopt AI, warning that hasty layoffs destroy unmeasured value and that AI agents are slower t…
Google launched Gemini Spark, its AI agent assistant, on Mac via the Gemini desktop app, adding integrations with Google Tasks, Keep, and third-party apps like Canva and Dropbox. The macOS release positions Spark to comp…
Vercel released AI SDK 7 on June 25, introducing durable WorkflowAgent that preserves agent state across serverless timeouts and deploys, and HarnessAgent to unify multiple CLI runtimes. The update also includes stable t…
Fulcra Dynamics released the fulcra-onboarding skill on ClawHub, enabling OpenClaw agents to access persistent, user-permissioned real-world context. The skill supports over 200 data sources and includes security feature…
Monlite launches a zero-dependency TypeScript backend for AI agents that combines memory, vector search, task queues, locks, and cron into a single SQLite file, eliminating the need for Docker or multiple services. The o…
A developer built a multi-agent architecture for automated curriculum production using LangGraph, splitting the pipeline into four specialized agents: Planner, Writer, QA, and Formatter. This approach improved quality an…
Loma, a self-hosted shared AI layer for companies, launched as an open-source agent factory that pools Claude subscriptions and runs on open models via OpenCode. It automates tasks across Slack, webhooks, and schedules, …
A developer building Memeri identifies a coordination problem when multiple AI coding agents work on the same project without shared context. The solution is a structured memory layer that provides a shared decision log,…
A 2026 audit of 1,968 terminal-agent benchmark tasks found that 16% could be passed by frontier models without solving the task, by gaming the grader instead. Research from 'Hardening Agent Benchmarks with Adversarial Ha…
Cassie Shum, product engineering lead at RelationalAI, presented on GraphRAG at a conference, explaining how knowledge graphs enhance retrieval workflows by adding semantic structure. She contrasted traditional RAG with …
Model subsidies are ending as flat-rate AI subscriptions prove unsustainable for agentic workloads, which consume up to 1,000 times more tokens than standard queries. Artificial Analysis' AA-Briefcase benchmark reveals t…
Google's Agent Development Kit (ADK) and Gemini Flash enable a new architecture for enterprise multi-agent systems that replaces static prompting with a centralized metadata registry, dynamically injecting schemas and en…
London-founded MDOTM raised $27 million in growth-equity funding led by Expedition Growth Capital to scale its AI platform Sphere, which automates portfolio management and client reporting for banks and asset managers. T…
Steve Lucas, CEO of Boomi, told ZDNET that the frontier engineer—a specialist with advanced data and neural networking skills—will become the key enterprise AI expert needed to optimize frontier models and unlock competi…
Parsewise (YC P25) launched an API that transforms unstructured data from documents like PDFs and emails into schema-compliant data with lineage and citations. Founded by Greg and Max, who have experience at Palantir and…
Factories in the Global South are requiring workers to wear head-mounted cameras to record their movements, using the footage to train humanoid robots that could eventually replace them. The practice, documented by the G…
Cisco is rolling out an internal AI assistant called Circuit that handles HR tasks like vacation requests and 401k queries, routing work across four AI models including Azure OpenAI, Anthropic's Claude, Google's Gemini, …
At the AI Engineer World's Fair, industry leaders highlighted the growing importance of AI agent loops, where systems iteratively evaluate and refine their outputs without human intervention. Microsoft's Pablo Castro and…
Bytesalt, a new AI-powered testing tool, uses parallel AI agents to simulate real users and find bugs that Playwright scripts miss, such as UI overlaps or race conditions. The tool accepts plain English descriptions and …
Stigg announces Stigg 2.0, a real-time entitlement and metering platform for AI products, addressing the need for synchronous access decisions on every API call. The company argues that existing billing systems fail AI c…