AI Tools news and analysis on Web Pulse: 25189 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
A new AI agent for e-commerce order support, governed by the AgentAz specification, answers order questions and processes routine returns while escalating disputes to humans. The agent is read-only, verifies identity, an…
AgentKit released Account Research Agent, an AI agent that compiles account briefs with verified firmographics, tech stack, triggers, and key people for sales calls. The agent includes an AgentAz governance specification…
A new AI agent called the Action Item Tracking Agent extracts tasks, owners, and due dates from meeting notes without fabricating information. It flags ambiguous ownership or missing dates and requires human confirmation…
Google's AgentKit released an open-source AgentAz specification for a Community Question Triage Agent that categorizes questions, answers clear ones from a knowledge base, and routes spam to moderators. The agent operate…
A new AI contract review agent, governed by the open-source AgentAz specification, reviews clauses against a user's playbook, flags risky terms and omissions with severity and citations, and proposes fallback language. T…
A new AI agent called the Company Policy Q&A Agent answers policy, benefits, and procedure questions strictly from an official handbook with citations, routes sensitive HR matters to a person, and never invents policy or…
A new open-source agent specification called AgentAz aims to reduce alert noise by ranking alerts based on actionability and recommending suppression rules, while never suppressing alerts linked to real incidents or crit…
AgentKit released the Competitive Intelligence Digest Agent, an open-source AI agent that compiles competitor digests from public sources while labeling items as confirmed facts or unverified rumors. The agent includes a…
A new AI agent, the Expense Audit & Compliance Agent, automates line-by-line expense report auditing against company policy, flagging violations and suspicious patterns while auto-approving clean reports. The agent is go…
A new Form-to-JSON Extraction Agent uses an AgentAz governance specification to extract form data into schema-valid JSON, scoring confidence per field and flagging ambiguous or missing fields for human review. The agent …
AgentKit released a Compliance Control Monitoring Agent that tests internal controls against supporting evidence and flags failures without auto-attesting. The agent is governed by an open-source AgentAz specification de…
A new content repurposing agent, governed by the open-source AgentAz specification, transforms a single source into multiple formats while preserving facts and brand voice. The agent operates under strict trust and autho…
A new open-source AI incident response agent, AgentAz, has been released under Apache-2.0, designed to autonomously handle low-risk remediation steps while escalating high-risk actions to human engineers. The agent opera…
A new AI-powered SOC alert triage agent, governed by the open-source AgentAz specification, enriches, correlates, scores, and recommends dispositions for raw security alerts. It reduces alert fatigue by deduplicating inc…
A Princeton team's CoALA framework defines four types of memory for AI agents—working, semantic, procedural, and episodic—and Claude Code implements each as plain files and commands rather than a vector database, with ep…
Library authors can ship AI agent skills inside NuGet packages, automatically installing them when developers add the library. This approach, demonstrated by the StructId and Mockly libraries, improves AI coding agent pe…
A new AI agent called Campaign Brief Builder Agent turns user inputs into structured marketing campaign briefs, flagging missing information and assumptions for human review. The agent is governed by an open-source Agent…
A developer released Codeflowmap, an open-source tool that maps a codebase's dependency and call graph to surface read, write, and auth paths between files and functions. It can annotate files using local or remote AI mo…
LiveKit released two end-of-turn detection models that process speech directly instead of relying on transcripts, fusing semantic and acoustic understanding. The v1 model achieves top results across 14 languages and runs…
A Hacker News user asks the community for recommendations on benchmarks to evaluate different agent harnesses, noting that Terminal Bench does not align with their experience.