#AI Agents
50 articles with this tag
Cloudflare adds WriteGuard for AI agent safety
Cloudflare introduces WriteGuard, a new feature for its MCP server portals, offering fine-grained controls and auditing for AI agents to prevent misuse.
Cloudflare Agents Gain Observability
Cloudflare Agents now offer detailed observability, allowing developers to trace AI agent behavior, model calls, and token usage for improved development.
Cloudflare Agents Debug Workers Locally
Cloudflare now allows AI agents to debug Cloudflare Workers locally using automatic OpenTelemetry tracing, speeding up development.
Cloudflare Cuts GitHub Issues to Zero
Cloudflare used AI agents to build an automated issue triage system for its Astro project, cutting open issues by over 85%.
Databricks Revamps Retail Reports with GenAI
Databricks proposes a generative AI-powered 'Monday Morning Report' to transform retail and CPG planning from data arguments to decisive action.
CoreWeave Launches AI Sandboxes
CoreWeave Sandboxes offers secure, isolated environments for AI reinforcement learning, agent tool use, and model evaluation, accessible on-cluster or serverless.
@cloudflare/computer: Agents get PCs
Cloudflare's @cloudflare/computer library offers AI agents a virtual computer, moving beyond containers for scalable, efficient execution.
AI Agents Poised to Reshape E-commerce and Advertising
ARK's Nicholas Grus and Varshika Prasanna discuss the shift to an 'agentic era' in AI, transforming e-commerce and advertising with AI agents, and projecting significant revenue growth.
Claude's Corner: MochaCare - The Startup Running Home Care Agencies So Their Owners Don't Have To
MochaCare takes hiring, scheduling, and client intake off home care agency owners' plates using AI agents backed by 24/7 human oversight. In the $432B home care market, where 70% of caregivers churn annually and 30,000+ fragmented agencies are drowning in ops, this could be the infrastructure layer the industry has been missing.
Rayan Garg on Why Long Horizon AI Agents Need Better Verifiers
Rayan Garg from Theta Software explains why long horizon AI agent benchmarks need accurate environment design and final-state verifiers.
Databricks Aims for Agentic Media Buying Scale
Databricks unveils an architecture for scalable agentic media buying, focusing on state, trust, and observability beyond just AI models.
AI Agents Stall on Core AI Research
Frontier AI agents can automate AI research engineering but fail to make substantial progress on core research questions, according to new shadow evaluations.
AI Agents Remake Energy Finance
AI agents are accelerating energy finance decisions, making context and control paramount for managing volatility and margin.
Databricks AI Agents Take on Production Lines
Databricks introduces AI agents for manufacturing, enabling real-time decision-making on production lines by unifying data and ensuring human oversight.
AI Agents Tackle Payment Declines with Event Sourcing
Divakar Kumar of FlyersSoft proposes using AI agents with event-sourced systems to diagnose complex payment declines, moving beyond simple fraud detection.
Freehand Secures $75M for AI Supply Chain
Freehand secured $75 million in a funding round to scale its autonomous AI agents managing supply chain spend for Fortune 500 companies.
OpenAI's Akshay Nathan on ChatGPT's 'Everything App' Vision
OpenAI's Akshay Nathan discusses the company's vision for ChatGPT as a 'super app,' the evolution of AI tools, and the democratization of powerful capabilities.
Claude's Corner: Moda - What Comes After Agent Tracing
Moda is the continual learning layer for deployed AI agents: it diagnoses root causes across six failure families, generates concrete fixes, and validates them against historical runs before you ship. A YC W2026 startup closing the loop between production failures and shipped improvements.
HubSpot Absorbs Agent.ai into CRM Core
HubSpot is retiring Dharmesh Shah's Agent.ai, integrating its core vision into HubSpot Agent Builder and Agent Hub for native CRM AI agent creation.
Sam Altman: "Never a Better Time to Do a Startup"
OpenAI CEO Sam Altman told Startup School 2026 that "Never a Better Time to Do a Startup," citing AI advancements and the need for ambitious founders.
Cisco on AI Security: Agents, Costs, and China
Cisco's Jeetu Patel discusses AI agent security risks, the dual concerns of cybersecurity and token costs, and the US's need to invest in open-source AI.
Board CFO: AI Agents Accelerate, Not Replace, Enterprise Planning
Board CFO Gordon Pothier discusses how AI agents are augmenting enterprise planning, the focus on ROI, and the company's strategy for sustainable growth.
Uber Eats Uses AI Agents to Enhance Food Photos at Scale
Uber Eats' computer vision team details their AI agent system for enhancing food photos, focusing on closed-loop feedback and continuous learning.
Google Experts Share AI Agent Evaluation Best Practices
Google's Preetika Bhateja & Daniel Bump share essential strategies for building effective AI agent evaluation systems, from initial 'vibing' to scaling with LLM judges.
Arize CEO: AI Agents Will Automate Software Fixes
Arize CEO Jason Lopatecki discusses how AI agents are set to revolutionize software observability and debugging, enabling autonomous fixes and continuous self-improvement.
Verifiable Agent Authorization via Zero-Knowledge Proofs
This paper introduces Cryptographically Verifiable Agent Authorization (CVA) using zk-SNARKs, addressing a critical gap in securing autonomous AI agents.
AI Agents in the Real World: Successes and Failures
Andon Labs co-founder Lukas Petersson discusses the challenges of testing AI agents in real-world scenarios, from running businesses to DJing radio stations, highlighting emergent misbehavior and the need for better evaluation methods.
OpenWorker AI: Your Desktop Co-Worker
Andrew Ng and Rohit Prasad launch OpenWorker AI, an open-source desktop agent delivering finished work and prioritizing data privacy.
Neo4j: AI on Lakehouse with Context in Shapes
Neo4j's Zach Blumenfeld explores how AI agents can overcome data context limitations using graph representations, focusing on warehouse and document data.
AI Agents Will Redesign Enterprise Work, Says Wonderful Exec
Barak Kaufman of Wonderful discusses how AI agents, powered by OpenAI, are enabling enterprises to transform operations and rethink work for 2026 and beyond.
Agentic AI: The Next Frontier
Agentic AI represents a new wave of artificial intelligence capable of autonomous goal achievement, planning, and execution.
AI Assistants Need Graph Memory, Not Just More Tokens
Stephen Chin of Neo4j discusses how graph databases offer superior memory solutions for AI assistants compared to traditional file storage or vector databases.
AI Agents Evolve: From Harnesses to Autonomous Claws
Mastra CEO Sam Bhagwat discusses the evolution of AI agents from LLMs to autonomous 'Claws,' the shift to cloud-based systems, and the inevitable market shakeout.
OpenAI AI Agents Breached Hugging Face
OpenAI and Hugging Face collaborate after advanced AI agents breached infrastructure during a security evaluation, exploiting a zero-day vulnerability.
Databricks Lakehouse: The AI Context Layer
Databricks' Data Hub creates a governed AI context layer by unifying R&D data, prioritizing context coverage as a quality metric for both human and AI users.
HeyGen: HTML is the Key for AI Video Agents
James Russo of HeyGen argues that HTML is the ideal native language for AI agents to create high-quality videos, introducing the HyperFrames framework.
Agent Architectures Have a 6-Month Half-Life
Dan Farrelly of Ingest argues that AI agent architectures have a 6-month half-life, advocating for a decoupled, execution-focused layer for sustainable development.
Snyk Tackles Agentic Development Security
Snyk's Ezra Tanzer discusses the critical security challenges in agentic development, focusing on securing agent outputs, supply chains, and behavior.
AI Agents Need 'Where Are Your Agents?' PSA, Says Keycard Exec
Kim Maida of Keycard discusses the security risks of over-privileged AI agents and introduces token exchange (RFC 8693) as a solution.
AI Agent Swarms Rethink Model Economics
Cursor's new AI agent swarm architecture dramatically cuts costs and boosts efficiency by pairing smart planners with cheaper workers, reshaping AI deployment economics.
AI Agents Need Verification, Says Sonar CEO Tariq Shaukat
Sonar CEO Tariq Shaukat argues that for enterprises to harness AI coding agents effectively, verification must be integrated into the development process, not treated as an afterthought.
LLM Reliability: Control Flow Over Prompting
Ornella Bahidika and Joel Allou from Microsoft discuss 'harness engineering' for AI agents, advocating for code-driven control flow over LLM-driven decision-making to ensure reliability.
Tesla ML Engineer on Enterprise Agent Problems
Ishita Daga, ML Engineer at Tesla, reveals the core structural problems plaguing enterprise AI agents: ambiguity, staleness, and preference, and proposes solutions.
AI GTM Agents: Knowing Buyers Before They Message
Position Squared's Sajjan Kanukolanu details how AI-native GTM architectures can help sales teams understand buyers better, overcoming common pitfalls.
Alitheia bio's Froglet: Agents Need Verifiable Receipts
Armanas Povilionis of Alitheia bio introduces Froglet, a protocol designed to enable verifiable transactions and collaboration between AI agents, addressing the limitations of current tool-centric automation.
Skills Are the New SDKs: Rethinking AI Agents
Elvin Aghammadzada of DataRobot argues that 'skills' are the new SDKs for AI agents, addressing context engineering challenges and the shift from 'friction' to 'fluency' moats.
Ravi Madabhushi: Agents Break Human-Centric Auth
ScaleGrid's Ravi Madabhushi explains why human-centric authentication models fail AI agents, leading to security risks and the need for fine-grained, auditable access controls.
Agents Need Receipts, Not More Tool Calls
Armanas Povilionis of Alithea Bio argues that AI agents need direct knowledge retrieval ('receipts') over excessive tool calls for greater efficiency.
Agents Need a Save Button: Kitaru's Replay Capability
ZenML's Hamza Tahir discusses Kitaru, a tool enabling 'what if' scenarios for AI agents by replaying past executions with modified parameters.
AI Agents Need Feature Flags for Safety, Says Engineer
Backend engineer Sachin Gupta argues AI agents need specialized feature flags beyond traditional tools to manage their complex behaviors and mitigate risks.