#AI Agents
50 articles with this tag
Basis AI accounting agents run 6x faster
Basis agents run 5+ hour accounting workflows 6x faster, but Cursor post shows vague context can silently alter behavior without changing the final output.
GPT-6 Astra Demo Shows Agentic Puzzle Solving
GPT-6 Astra developers demo voxel London, matcha shop generation and a 3/3 DEF CON puzzle solve using parallel agents that avoid doom loops.
LoopHarness persistent safety state Ends Drift
LoopHarness proves trajectory monitors fail when evidence spans iterations and bounds irreversible actions to a constant with persistent loop-level state.
OpenClaw's Viral Launch: Lessons for AI Maintainers
OpenClaw's viral growth highlights new challenges and strategies for open-source AI maintainers, from managing AI-generated code to ensuring security.
Databricks Unveils Lakebase Postgres
Databricks unveils Lakebase Postgres, a new transactional database architecture using object storage and WAL for AI agents.
Claude's Corner: Panta - The AI That Actually Does Insurance Brokerage
Panta (YC W2026) built a fully automated commercial insurance brokerage where AI agents do the actual work: carrier portals, ACORD forms, email follow-ups, COI issuance. No human broker in the loop except at the binding decision. Here is how it works and how hard it is to clone.
Claude's Corner: Wideframe - AI Agents for the 75% of Video Work No One Talks About
Wideframe is a Mac desktop AI agent that automates the pre-editing stages of video production: footage indexing, semantic search, and Premiere Pro project assembly. The founders bet on the 75% of video work that happens before an editor opens the timeline.
AI Agents Discover New Science in "Einstein Arena"
James Zou of Together AI discusses how designing environments, rather than workflows, for AI agents can unlock creativity and lead to scientific breakthroughs, showcasing projects like the Einstein Arena and DSGym.
InjecMEM: A New Threat to LLM Memory
New InjecMEM attack targets LLM agent memory with single interaction, highlighting security gaps in persistent personalization.
AI's Future: Cheaper Tokens, Longer Tasks
Sal research CEO Neil Movva discusses the future of AI, focusing on cheaper tokens, long-running agents, and the shift from low-latency to proactive intelligence.
Claude's Corner: Sentrial - Monitoring the AI Agents Your Datadog Can't See
Sentrial monitors AI agents in production, catching hallucinations, infinite loops, and bad tool calls that never throw an error. Two UC Berkeley undergrads hit $30K MRR in a single YC batch. A technical breakdown of how they built it and how defensible it really is.
Octonous Adds Agent Skills for Reusable AI Context
Octonous launches Agent Skills, a Markdown-based library for centralizing AI agent instructions and context to boost efficiency and consistency.
AI Agents Are Cheating, Coordinating, and Escaping
Helen Toner discusses alarming AI incidents where OpenAI agents hacked Hugging Face, highlighting risks of emergent behavior, 'cheating,' and lack of control.
Warp's Safia Abdalla on Building Cloud AI Agents
Safia Abdalla of Warp discusses building cloud AI agents, emphasizing developer workflow adaptation, complexity abstraction, and the power of an open API.
Rémi Louf: Agent Frameworks Are "Harmful"
Rémi Louf, CEO of .txt, argues that current AI agent frameworks are "harmful" due to their reliance on manual intervention, advocating for event-driven systems and robust logging.
Microsoft Unveils TokenOps for AI Agent Cost Control
Microsoft introduces TokenOps, a run-aware governance system for AI agents to control token spending and move from 'token maxing' to 'value maxing'.
AI Agents Need Budgets, Not Just Tokens
Anthropic's Sachin Malhotra argues that AI agents in production need budgets, not just broad tokens, proposing primitives like asymmetric verbs, rate limits, and tripwires.
Claude's Corner: Corvera - AI Agents for the CPG Operations Problem
Corvera deploys AI agents to automate the back-office grind that kills CPG brands at scale. Here's how the YC W2026 startup built an agentic OS on MCP, why domain expertise is the real moat, and a full build guide for replicating it.
Databricks links retail planning to store execution
Databricks unveils a unified application connecting retail demand planning with campaign and store operations, powered by AI.
Agent Building is Easy, Context is Key, Says Unblocked Engineer
Unblocked engineer Jeff Ng explains why context is the next frontier for AI agents, moving beyond simple deployment to address the critical need for comprehensive, synthesized information.
Docker's Tushar Jain on AI Agent Autonomy and Safety
Docker's Tushar Jain outlines the critical need for safety in autonomous AI agents, introducing a new runtime approach for secure, scoped, and intent-based access.
Hugging Face Engineer Automates Job with AI Agents
Niels Rogge from Hugging Face shares how he uses AI agents to automate his job, from outreach to researchers to improving model discoverability on the Hugging Face Hub.
AI Agents Need IT Admins: Decawork CEO on Agent Safety
Decawork CEO Sarthak Aggarwal highlights the critical need for robust IT governance and safety protocols as enterprises deploy AI agents, drawing parallels to human workforce management.
CTO's AI Workflow: Prototyping as Leadership
The Browser Company's CTO, Hersh Agrawal, reveals how AI agents empower leaders to ship code and prototypes, transforming the 'manager schedule' into productive building time.
AI Agents Need Enterprise-Ready Tech Stacks
Anterior's Chris Lovejoy and Saul Howard explain why enterprise tech stacks struggle with AI agents and introduce key architectural primitives for successful deployment.
Space Secures $2.4M for AI-Native Filesystem
Space raised $2.4 million led by a16z Speedrun to build an AI-native distributed filesystem, aiming to eliminate data bottlenecks for humans and AI agents.
Asana uses AI to slash engineering time
Asana used OpenAI Codex to complete a 5-year engineering project in 2 weeks for $12K, a fraction of the $6M estimate.
Snowflake Builds AI Context Layer
Snowflake is building an internal semantic layer to give AI agents consistent data context, improving accuracy and efficiency.
The Prototyping Tax
The 'prototyping tax' of fragmented context and siloed data kills AI initiatives. Platform-native agents and semantic grounding offer a solution, as shown by Abacus Insights' success in healthcare.
Context Engineering: The Key to Better AI Agents
AI experts discuss context engineering strategies, detailing how compaction, caching, and memory management improve AI agent performance and reduce costs.
Claude's Corner: Clam - The Network Firewall Your AI Agents Actually Need
Clam (YC W2026) builds a Semantic Firewall that sits at the network layer between AI agents and everything they touch, blocking PII leaks, prompt injections, and malicious code in real time. Here's the technical breakdown and what's hard to replicate.
AI Agents Learn Human Web Browsing via CDP
Corey Gallon explains how AI agents can mimic human web browsing using CDP, overcoming website defenses with a 'sense, act, verify' loop and the 'meatbag ladder' approach.
Paul Klein: AI Agents Need Better Web 'Harnesses'
Browserbase founder Paul Klein argues that AI agents need better 'harnesses' and tools to navigate the web, not just improved LLMs. He outlines key engineering challenges and opportunities for agent-first web development.
Cursor Acquires Firetiger
AI code editor Cursor acquires Firetiger, integrating production monitoring and incident response to create AI agents that manage the full software lifecycle.
Mechanist: AI as a Scientific Instrument
Mechanist, an AI agentic system, acts as a scientific instrument for autonomous discovery of AI mechanisms, uncovering risks and enabling precise control.
Cursor Agents Launch 3x Faster
Cursor's new 'builds' feature pre-caches dev environments, slashing agent startup times by up to 3x and boosting resilience.
LangChain CEO on Building Better AI Agents
LangChain CEO Harrison Chase discusses the essential components of AI agents, the importance of custom harnesses, and the power of evals and observability for continuous improvement.
Intelligence vs. Expertise in AI Agents
Yu Su of NeoCognition differentiates AI intelligence from expertise, arguing continual learning is key to unlocking specialized skills for agents in complex "micro-worlds."
Alloy Robotics Raises $8M to Debug Robot Fleets With AI
Alloy Robotics has raised $8 million at an $80 million valuation for AI agents that read a robot fleet's logs, telemetry and video to explain why a machine failed. Square Peg led the round.
Developers Become Orchestrators with AI Agents
AI agents are transforming the developer role from coding to orchestrating complex software delivery systems, with GitHub positioning its platform as central to this shift.
Anthropic's Evolution of AI Agents
Anthropic's Gagan Bhat and Isabella Kai He detail the evolution of AI agents, from Messages API to Managed Agents, focusing on engineering principles, reliability, and security.
Kavak's AI Overhaul: An Agent Per Customer
Kavak's Head of AI, Ali Masa, reveals how the company is rebuilding itself around AI agents, with an agent per customer and plans for an 'AI CEO'.
Claude's Corner: o11 - The AI Agent That Lives Inside Your Enterprise Apps
Two UNC dropouts are building AI that lives inside Excel and PowerPoint, not beside them. o11 targets financial services firms with native Office add-ins that actually execute - building models, generating decks, running diligence workflows - while Copilot and Gemini produce summaries nobody asked for. A StartupHub.ai deep-dive.
AI Agents: The New Primitives of Software
Kwindla Kramer of Daily discusses the historical evolution of computing and the future of AI-native software, drawing parallels from Vannevar Bush to today's AI agents.
HSP GRUPPE: AI as Operating Model
HSP GRUPPE is embedding ChatGPT Enterprise into tax advisory, viewing AI as an operating model shift to enhance professional judgment and redesign workflows.
AI Agents Get Hands With Tool Calling
AI agents are gaining 'hands' through tool calling, enabling them to interact with external systems and perform real-world actions.
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%.