AI agents — Page 2

4 Patterns the Best AI Agents Actually Share

Flinn AI's Mardu Swanepoel studied Harvey, Cursor, Manus, and Claude to find what top agents share. The answer: focus, transparency, personalization, reversibility.

Two people in split-screen view with text reading "EVERY LAYER. IT'S ALL AGENTS." overlaid at the top in white and red…

When AI Agents Attack Your Own Infrastructure

When AI Agents Attack Your Own Infrastructure

OpenAI's data platform lead Emma reveals why AI agent adoption creates a hidden infrastructure crisis—and what platform teams can do before it buries them.

Two men in professional attire at an AI Engineer Europe event, with Google DeepMind branding and "Agentic Panel" text…

Inside Google DeepMind's Messy Reality of AI Agents at Scale

Inside Google DeepMind's Messy Reality of AI Agents at Scale

Google DeepMind engineers have worse token quotas than paying customers. KP Sawhney and Ian Ballantyne reveal what running AI agents at Google scale actually looks like.

Man in Argentina jersey gestures while discussing chaos in agent town, with crime statistics displayed on screen beside him

What AI Town Experiments Actually Teach Us About Agents

What AI Town Experiments Actually Teach Us About Agents

Emergence AI's 15-day virtual town experiment revealed wildly different AI behaviors—and the real lesson has nothing to do with which model is "best."

Google I/O session speaker presenting on AI agent development, with microphone visible in professional setting

Six Protocols That Make AI Agents Actually Work

Rachel "Rach" Kovacs2 months ago

Six Protocols That Make AI Agents Actually Work

Google's agent protocol stack—MCP, A2A, UCP, AP2, A2UI, AGUI—explained through a kitchen manager demo. What each protocol does and when to reach for it.

Man in beanie at desk pointing to "Senior Partner" nameplate with red X over "Junior Partner" sign, bookshelves behind him,…

Stop Prompting. Start Questioning Your AI Agent

AI. Rachel "Rach" Kovacs2 months ago

Stop Prompting. Start Questioning Your AI Agent

AI strategy creator Nate B Jones says prompt engineering is dead. His 'AI Question Method' has real merit—but there's a data privacy conversation he's skipping entirely.

Light green background with geometric network diagrams on the left, event details for London, UK keynote on the right,…

Anthropic's Claude Keynote: A New Era for Developers

Dev Kapoor2 months ago

AI. Dev Kapoor2 months ago

Anthropic's Claude Keynote: A New Era for Developers

Anthropic's Code with Claude London keynote revealed major platform shifts—from advisor strategies to managed agents. Here's what it means for developers building on Claude.

Two people discuss AI protocols against a digital background with code, with "think series" branding and "MCP VS ADK" text…

MCP and ADK: Two Tools, Two Jobs, One Stack

Samira Barnes2 months ago

MCP and ADK: Two Tools, Two Jobs, One Stack

MCP handles how AI agents talk to the world. ADK handles how they think. IBM's Cedric Clyburn and Anna Gutowska break down why you likely need both.

Two men in a tech presentation setting with AI workflow diagrams behind them, discussing long-running agents and persistent…

AI Agents Running for Hours—and Who's Accountable

AI. Samira Barnes2 months ago

AI Agents Running for Hours—and Who's Accountable

Anthropic's Prabaker and Wilson reveal the engineering behind long-running AI agents—and raise accountability questions regulators haven't caught up to yet.

Man in dark shirt against neon-lit background with "think series" branding and blue neon "LAST MILE" sign, alongside text…

AI Agents Break Zero Trust at the Last Mile

AI Agents Break Zero Trust at the Last Mile

AI agents reason brilliantly but authenticate badly. Grant Miller explains why agentic systems shatter zero trust at the legacy integration point—and what fixes it.

When Your AI Agent Acts Without Asking You First

When Your AI Agent Acts Without Asking You First

Browser Use founder Magnus Müller says the real barrier to AI agents isn't technical—it's the interface. And the agent that prompts *you* might be the future.

Bold yellow "ZERO HUMANS" text with robot network diagram showing interconnected AI agents, credit cards, and a rejected…

Paperclip Wants to Turn AI Agents Into a Company

Paperclip Wants to Turn AI Agents Into a Company

Paperclip hit 64K GitHub stars by promising to fix multi-agent chaos with org charts, budgets, and audit logs. Here's what that actually looks like in practice.

Retro-styled illustration of developers and an AI robot at computers with code displays, set against a dark background with…

HTML vs Markdown: The Format War Reshaping AI Work

HTML vs Markdown: The Format War Reshaping AI Work

An Anthropic engineer's viral essay arguing for HTML over Markdown in AI agent workflows raises real questions about how we're changing what work even means.

Woman presenting on AI agents with Alyx and Arize logos visible, showing before/after comparison of conversation context…

Why AI Agents Fail: Lessons in Context Management

Why AI Agents Fail: Lessons in Context Management

Arize's Sally-Ann DeLucia spent a year learning context management the hard way. What broke, what held, and what even Claude Code couldn't solve.

DeepSeek V4: Build Apps and AI Agents for Free

DeepSeek V4: Build Apps and AI Agents for Free

DeepSeek V4 lets non-coders build apps and run AI agents for free. Here's what actually works, what breaks, and what the hype leaves out.

The Hidden Layer Wasting Your AI Workflow Time

The Hidden Layer Wasting Your AI Workflow Time

Prompts, skills, plugins, MCPs—most AI users conflate them all. Here's what each one actually does and why the distinction matters for real work.

Bold yellow "NO MORE CHAOS" text with blue glowing arrow and digital brain illustration, green checkmark icon indicating…

Can Harness Engineering Fix AI Agent Chaos?

Can Harness Engineering Fix AI Agent Chaos?

Archon promises to turn chaotic AI coding agents into deterministic systems via harness engineering. Here's what that actually means—and what it doesn't solve.

A layered OS architecture diagram showing Identity, Knowledge, Workers, and Automation components, with the right side…

Why Your AI Agents Aren't Working (Yet)