AGENTS · 199 stories

Agents.

Agentic systems, multi-agent architectures, and the infrastructure enabling autonomous AI to act in the world.

199

Stories in section

Time:

Sort

ChatGPT's Mac App Can Now Read and Send Your iMessages, featured image for AI Insiders

Agents / -1175 min ago

ChatGPT's Mac App Can Now Read and Send Your iMessages

By Alessandro Benigni

Claude Desktop's Hidden Parka Feature Would Staff Meetings With Agents, featured image for AI Insiders

Agents / -1175 min ago

Claude Desktop's Hidden Parka Feature Would Staff Meetings With Agents

By Alessandro Benigni

Google Folds Antigravity Into Gemini Enterprise Subscriptions, featured image for AI Insiders

Agents / -1175 min ago

Google Folds Antigravity Into Gemini Enterprise Subscriptions

By Alessandro Benigni

Mistral Gives Models Five Tools to Stop Guessing at Retrieval, featured image for AI Insiders

Agents / -1175 min ago

Mistral Gives Models Five Tools to Stop Guessing at Retrieval

By Alessandro Benigni

Slack Turns Itself Into the Coding Surface Agents Plug Into, featured image for AI Insiders

Agents / -1175 min ago

Slack Turns Itself Into the Coding Surface Agents Plug Into

By Alessandro Benigni

An OpenAI coding agent used curl to cheat on a terminal benchmark, featured image for AI Insiders

Agents / 4 hr ago

An OpenAI coding agent used curl to cheat on a terminal benchmark

By Alessandro Benigni

Binance Opens Its Exchange to AI Trading Agents, Sets Few Limits, featured image for AI Insiders

Agents / 4 hr ago

Binance Opens Its Exchange to AI Trading Agents, Sets Few Limits

By Alessandro Benigni

Cursor Agents Can Now Subscribe to Events Instead of Prompts, featured image for AI Insiders

Agents / 4 hr ago

Cursor Agents Can Now Subscribe to Events Instead of Prompts

By Alessandro Benigni

Replit Launches Free Mode, Eating GPT-5.6's Compute Bill Itself, featured image for AI Insiders

Agents / 4 hr ago

Replit Launches Free Mode, Eating GPT-5.6's Compute Bill Itself

By Alessandro Benigni

Vercel Puts Its Production Agent Inside Slack Threads, featured image for AI Insiders

Agents / 4 hr ago

Vercel Puts Its Production Agent Inside Slack Threads

By Alessandro Benigni

Harvey Gives Legal AI Agents Memory That Persists Across Matters, featured image for AI Insiders

Agents / yesterday

Harvey Gives Legal AI Agents Memory That Persists Across Matters

By Alessandro Benigni

Liquid AI's Coding Agents Passed Every Test, Then Broke at Scale, featured image for AI Insiders

Agents / yesterday

Liquid AI's Coding Agents Passed Every Test, Then Broke at Scale

By Alessandro Benigni

Warp Turns Its Software Factory Pitch Into a Shipping Product, featured image for AI Insiders

Agents / yesterday

Warp Turns Its Software Factory Pitch Into a Shipping Product

By Alessandro Benigni

Cursor Ships Origin to Paid Users Hours Before GitHub Went Dark, featured image for AI Insiders

Agents / 2 days ago

Cursor Ships Origin to Paid Users Hours Before GitHub Went Dark

By Alessandro Benigni

Linear's Own Data Shows CEOs Adopting AI Faster Than Anyone Else, featured image for AI Insiders

Agents / 2 days ago

Linear's Own Data Shows CEOs Adopting AI Faster Than Anyone Else

By Alessandro Benigni

MIT and Harvard Find Multi-Agent Pipelines Fake Their Gains, featured image for AI Insiders

Agents / 2 days ago

MIT and Harvard Find Multi-Agent Pipelines Fake Their Gains

By Alessandro Benigni

Warp's Shared Agent Memory Is a Governance Problem in Disguise, featured image for AI Insiders

Agents / 2 days ago

Warp's Shared Agent Memory Is a Governance Problem in Disguise

By Alessandro Benigni

Files, structured stores, and trained memory tested head to head, featured image for AI Insiders

Agents / 3 days ago

Files, structured stores, and trained memory tested head to head

By Alessandro Benigni

Google adds file-based Custom Agents to Antigravity, IDE next, featured image for AI Insiders

Agents / 3 days ago

Google adds file-based Custom Agents to Antigravity, IDE next

By Alessandro Benigni

Agent Plugins Standard Bundles Skills and MCP, Not Credentials, featured image for AI Insiders

Agents / 6 days ago

Agent Plugins Standard Bundles Skills and MCP, Not Credentials

By Alessandro Benigni

Anthropic tested AI agents sharing a codebase. They wrote malware., featured image for AI Insiders

Agents / 6 days ago

Anthropic tested AI agents sharing a codebase. They wrote malware.

By Alessandro Benigni

Anthropic's Claude Code merges 46% of its own maintenance PRs, featured image for AI Insiders

Agents / 6 days ago

Anthropic's Claude Code merges 46% of its own maintenance PRs

By Alessandro Benigni

Cursor Pre-Builds Cloud Agent Environments to Cut Startup Lag, featured image for AI Insiders

Agents / 6 days ago

Cursor Pre-Builds Cloud Agent Environments to Cut Startup Lag

By Alessandro Benigni

Depth isn't the risk in agent hierarchies. Blast radius is., featured image for AI Insiders

Agents / 6 days ago

Depth isn't the risk in agent hierarchies. Blast radius is.

By Alessandro Benigni

Google turns Sheets rows into interactive apps with Gemini, featured image for AI Insiders

Agents / 6 days ago

Google turns Sheets rows into interactive apps with Gemini

By Alessandro Benigni

Writer's real product isn't Palmyra X6. It's the harness around it., featured image for AI Insiders

Agents / 6 days ago

Writer's real product isn't Palmyra X6. It's the harness around it.

By Alessandro Benigni

A field guide to how much SQL access your agent should get, featured image for AI Insiders

Agents / Aug 14

A field guide to how much SQL access your agent should get

By Alessandro Benigni

Agent adoption's real constraint is verification, not capability, featured image for AI Insiders

Agents / Aug 14

Agent adoption's real constraint is verification, not capability

By Alessandro Benigni

Claude in Chrome turns its side panel into an agent workspace, featured image for AI Insiders

Agents / Aug 14

Claude in Chrome turns its side panel into an agent workspace

By Alessandro Benigni

OpenAI's enterprise data shows a widening gap, in its own metric, featured image for AI Insiders

Agents / Aug 14

OpenAI's enterprise data shows a widening gap, in its own metric

By Alessandro Benigni

Specula's Bug-Hunting Agent Impresses a Reviewer, but Not Fully, featured image for AI Insiders

Agents / Aug 14

Specula's Bug-Hunting Agent Impresses a Reviewer, but Not Fully

By Alessandro Benigni

Three Engineers, Hundreds of PRs: The Review Loop That Makes It Work, featured image for AI Insiders

Agents / Aug 14

Three Engineers, Hundreds of PRs: The Review Loop That Makes It Work

By Alessandro Benigni

App Strings Point to Cursor's Code Review Platform Going Wide, featured image for AI Insiders

Agents / Aug 13

App Strings Point to Cursor's Code Review Platform Going Wide

By Alessandro Benigni

Lovable retires the model picker for an automated router, featured image for AI Insiders

Agents / Aug 13

Lovable retires the model picker for an automated router

By Alessandro Benigni

Manus Tells Users to Back Up Data as Meta Split Proceeds, featured image for AI Insiders

Agents / Aug 13

Manus Tells Users to Back Up Data as Meta Split Proceeds

By Alessandro Benigni

xAI Gives Each Grok Agent Its Own Cloud Computer, featured image for AI Insiders

Agents / Aug 13

xAI Gives Each Grok Agent Its Own Cloud Computer

By Alessandro Benigni

Alibaba's Qwen team ships plug-in multimodal skills for AI agents, featured image for AI Insiders

Agents / Aug 12

Alibaba's Qwen team ships plug-in multimodal skills for AI agents

By Alessandro Benigni

PostHog Argues Agents Need MCP Access and Review Screens, featured image for AI Insiders

Agents / Aug 12

PostHog Argues Agents Need MCP Access and Review Screens

By Alessandro Benigni

The real computer-use market is software with no API at all, featured image for AI Insiders

Agents / Aug 12

The real computer-use market is software with no API at all

By Alessandro Benigni

A Hidden Line of Text in a PDF Can Turn Rovo Against You, featured image for AI Insiders

Agents / Aug 11

A Hidden Line of Text in a PDF Can Turn Rovo Against You

By Alessandro Benigni

Claude Code Makes Auto Mode the Default, Not Just an Option, featured image for AI Insiders

Agents / Aug 11

Claude Code Makes Auto Mode the Default, Not Just an Option

By Alessandro Benigni

Claude Code Sessions Can Now Message Each Other Mid-Task, featured image for AI Insiders

Agents / Aug 11

Claude Code Sessions Can Now Message Each Other Mid-Task

By Alessandro Benigni

Cursor Now Decides Which AI Model Writes Your Code, featured image for AI Insiders

Agents / Aug 11

Cursor Now Decides Which AI Model Writes Your Code

By Alessandro Benigni

LangChain Opens Managed Deep Agents to Public Beta, featured image for AI Insiders

Agents / Aug 11

LangChain Opens Managed Deep Agents to Public Beta

By Alessandro Benigni

Told to book a gym class, an agent attacked the gym's website, featured image for AI Insiders

Agents / Aug 11

Told to book a gym class, an agent attacked the gym's website

By Alessandro Benigni

Amazon, Cursor, Microsoft, OpenAI and Vercel Back One Plugin Format, featured image for AI Insiders

Amazon, Cursor, Microsoft, OpenAI and Vercel Back One Plugin Format

By Alessandro Benigni

An Agent IDE Ships With No Fixed Feature List, Only a Prompt, featured image for AI Insiders

An Agent IDE Ships With No Fixed Feature List, Only a Prompt

By Alessandro Benigni

Cloudflare Strips the Browser Down to What Agents Need, featured image for AI Insiders

Cloudflare Strips the Browser Down to What Agents Need

By Alessandro Benigni

LoopX Adds a Bookkeeping Layer for AI Agent Teams That Run for Days, featured image for AI Insiders

LoopX Adds a Bookkeeping Layer for AI Agent Teams That Run for Days

By Alessandro Benigni

OpenAI Slows Its Own Research After Agents Coordinated Hacks for Weeks, featured image for AI Insiders

OpenAI Slows Its Own Research After Agents Coordinated Hacks for Weeks

By Alessandro Benigni

The Real Reason AI Agents Burn Budget: They Don't Know When to Stop, featured image for AI Insiders

The Real Reason AI Agents Burn Budget: They Don't Know When to Stop

By Alessandro Benigni

Cloudflare's Blueprint Shrinks AI Agent Credentials to Minutes, featured image for AI Insiders

Cloudflare's Blueprint Shrinks AI Agent Credentials to Minutes

By Alessandro Benigni

Google Maps Now Books Your Hotel and Orders Your Dinner, featured image for AI Insiders

Google Maps Now Books Your Hotel and Orders Your Dinner

By Alessandro Benigni

Hark Opens Signups for a Cut-Rate Browser Agent, Handoff, featured image for AI Insiders

Hark Opens Signups for a Cut-Rate Browser Agent, Handoff

By Alessandro Benigni

Meta Ships a Terminal Coding Agent, Aims at Claude Code and Codex, featured image for AI Insiders

Meta Ships a Terminal Coding Agent, Aims at Claude Code and Codex

By Alessandro Benigni

Prime Intellect Ships an Agent That Edits Its Own Toolkit, featured image for AI Insiders

Prime Intellect Ships an Agent That Edits Its Own Toolkit

By Alessandro Benigni

RuntimeWire: OpenAI Agents Reportedly Rebuilt a Shut-Down Coordination Channel, featured image for AI Insiders

RuntimeWire: OpenAI Agents Reportedly Rebuilt a Shut-Down Coordination Channel

By Alessandro Benigni

Zero-Mem strips the LLM out of agent memory, not just answers, featured image for AI Insiders

Zero-Mem strips the LLM out of agent memory, not just answers

By Alessandro Benigni

A Developer Measured Exactly What Codex Sends the Model, featured image for AI Insiders

A Developer Measured Exactly What Codex Sends the Model

By Alessandro Benigni

ChatGPT Work Quietly Merges Seven OpenAI Products Into One, featured image for AI Insiders

ChatGPT Work Quietly Merges Seven OpenAI Products Into One

By Alessandro Benigni

Cloudflare Gives AI Agents Wallets. Liability Is Still Unassigned, featured image for AI Insiders

Cloudflare Gives AI Agents Wallets. Liability Is Still Unassigned

By Alessandro Benigni

Kiro Ships Kiro Crew, a Coding Agent That Outlives the Session, featured image for AI Insiders

Kiro Ships Kiro Crew, a Coding Agent That Outlives the Session

By Alessandro Benigni

Zach Lloyd: agents that show their work beat ones that claim it, featured image for AI Insiders

Zach Lloyd: agents that show their work beat ones that claim it

By Alessandro Benigni

Kiro merged three client agents into one server behind a protocol, featured image for AI Insiders

Kiro merged three client agents into one server behind a protocol

By Alessandro Benigni

MirrorCode Hides the Source Code and Grades Only the Output, featured image for AI Insiders

MirrorCode Hides the Source Code and Grades Only the Output

By Alessandro Benigni

When an agent won't stop rebuilding its own scaffolding, featured image for AI Insiders

When an agent won't stop rebuilding its own scaffolding

By Alessandro Benigni

Mercor and Ramp Benchmark Shows AI Still Fumbles Real Accounting Work, featured image for AI Insiders

Mercor and Ramp Benchmark Shows AI Still Fumbles Real Accounting Work

By Alessandro Benigni

Ramp built its coding-agent benchmark from real shipped PRs, featured image for AI Insiders

Ramp built its coding-agent benchmark from real shipped PRs

By Alessandro Benigni

Braintrust proposes scoring AI agents on trajectory, not answers, featured image for AI Insiders

Braintrust proposes scoring AI agents on trajectory, not answers

By Alessandro Benigni

Cursor's cloud agents now write over half its merged code, featured image for AI Insiders

Cursor's cloud agents now write over half its merged code

By Alessandro Benigni

LangChain trims Deep Agents' fixed overhead by 65 percent, featured image for AI Insiders

Agents / Jul 31

LangChain trims Deep Agents' fixed overhead by 65 percent

By Alessandro Benigni

Miessler splits the AI harness debate into intent and execution, featured image for AI Insiders

Agents / Jul 31

Miessler splits the AI harness debate into intent and execution

By Alessandro Benigni

Perplexity Open-Sources Numbat to Stop AI Agents From Melting Down, featured image for AI Insiders

Agents / Jul 31

Perplexity Open-Sources Numbat to Stop AI Agents From Melting Down

By Alessandro Benigni

camelAI Rebuilds Its Coding Agent Inside a Durable Object, featured image for AI Insiders

Agents / Jul 30

camelAI Rebuilds Its Coding Agent Inside a Durable Object

By Alessandro Benigni

Google gates Gemini's autonomous agents with hooks and budget caps, featured image for AI Insiders

Agents / Jul 30

Google gates Gemini's autonomous agents with hooks and budget caps

By Alessandro Benigni

Hugging Face's Forensic Timeline of the AI Agent Break-In, featured image for AI Insiders

Agents / Jul 30

Hugging Face's Forensic Timeline of the AI Agent Break-In

By Alessandro Benigni

xAI's Grok Build Mode Turns Chat Into a Live App Builder, featured image for AI Insiders

Agents / Jul 30

xAI's Grok Build Mode Turns Chat Into a Live App Builder

By Alessandro Benigni

Agent autonomy is a property of the task, not the model, featured image for AI Insiders

Agents / Jul 29

Agent autonomy is a property of the task, not the model

By Alessandro Benigni

Cogent Built an AI That Chains Enterprise Attacks on Its Own, featured image for AI Insiders

Agents / Jul 29

Cogent Built an AI That Chains Enterprise Attacks on Its Own

By Alessandro Benigni

Anthropic tells prompt engineers to rip out their old rulebooks, featured image for AI Insiders

Agents / Jul 28

Anthropic tells prompt engineers to rip out their old rulebooks

By Alessandro Benigni

METR's new metric prices AI agents against human labor, featured image for AI Insiders

Agents / Jul 28

METR's new metric prices AI agents against human labor

By Alessandro Benigni

One Reordered Tool Can Blow Up Your Coding Agent's Bill, featured image for AI Insiders

Agents / Jul 28

One Reordered Tool Can Blow Up Your Coding Agent's Bill

By Alessandro Benigni

Andrew Ng Open-Sources a Desktop AI Agent With Full File Access, featured image for AI Insiders

Agents / Jul 25

Andrew Ng Open-Sources a Desktop AI Agent With Full File Access

By Alessandro Benigni

Claude's Voice Mode Drops Its Haiku-Only Ceiling, featured image for AI Insiders

Agents / Jul 25

Claude's Voice Mode Drops Its Haiku-Only Ceiling

By Alessandro Benigni

OpenAI opens ChatGPT Health to all US adults, on its own terms, featured image for AI Insiders

Agents / Jul 25

OpenAI opens ChatGPT Health to all US adults, on its own terms

By Alessandro Benigni

OpenAI Wires Full-Duplex Voice Into Codex and ChatGPT Work, featured image for AI Insiders

Agents / Jul 25

OpenAI Wires Full-Duplex Voice Into Codex and ChatGPT Work

By Alessandro Benigni

OpenAI's Presence Puts Guardrails Around Enterprise Agents, featured image for AI Insiders

Agents / Jul 24

OpenAI's Presence Puts Guardrails Around Enterprise Agents

By Alessandro Benigni

Claude Code Desktop Can Now Watch Its Own iOS App Run, featured image for AI Insiders

Agents / Jul 23

Claude Code Desktop Can Now Watch Its Own iOS App Run

By Alessandro Benigni

Cognition Lets Devin Run on Your Own Hardware, Not Its Cloud, featured image for AI Insiders

Agents / Jul 23

Cognition Lets Devin Run on Your Own Hardware, Not Its Cloud

By Alessandro Benigni

The five layers a real web agent needs past Chromium, featured image for AI Insiders

Agents / Jul 23

The five layers a real web agent needs past Chromium

By Alessandro Benigni

Cursor's New Coding Swarm Cuts AI Agent Costs by 87 Percent, featured image for AI Insiders

Agents / Jul 22

Cursor's New Coding Swarm Cuts AI Agent Costs by 87 Percent

By Alessandro Benigni

Moonshot AI launches Kimi Work, a desktop agent for files and browsers, featured image for AI Insiders

Agents / Jul 22

Moonshot AI launches Kimi Work, a desktop agent for files and browsers

By Alessandro Benigni

Claude Code and Codex Handle /goal Differently, and Neither Is Great. Featured image for AI Insiders.

Agents / Jul 21

Claude Code and Codex Handle /goal Differently, and Neither Is Great

By Alessandro Benigni

Moonshot ships Kimi Code, a terminal agent that mirrors Claude Code. Featured image for AI Insiders.

Agents / Jul 21

Moonshot ships Kimi Code, a terminal agent that mirrors Claude Code

By Alessandro Benigni

A New Manual Maps What Coding Agents Actually Do, Not Where Code Sits. Featured image for AI Insiders.

Agents / Jul 18

A New Manual Maps What Coding Agents Actually Do, Not Where Code Sits

By Alessandro Benigni

Anthropic's Playbook for Running Code Migrations With AI Agents. Featured image for AI Insiders.

Agents / Jul 18

Anthropic's Playbook for Running Code Migrations With AI Agents

By Alessandro Benigni

Google Wires Instacart, Canva and YouTube Music Into AI Mode. Featured image for AI Insiders.

Agents / Jul 18

Google Wires Instacart, Canva and YouTube Music Into AI Mode

By Alessandro Benigni

LM Studio launches Bionic, a coding and document agent for open models. Featured image for AI Insiders.

Agents / Jul 18

LM Studio launches Bionic, a coding and document agent for open models

By Alessandro Benigni

OpenAI Sorts Codex Tasks Into Three GPT-5.6 Tiers. Featured image for AI Insiders.

Agents / Jul 18

OpenAI Sorts Codex Tasks Into Three GPT-5.6 Tiers

By Alessandro Benigni

Replit Claims Its Internal AI Agents Tripled Engineer Output. Featured image for AI Insiders.

Agents / Jul 18

Replit Claims Its Internal AI Agents Tripled Engineer Output

By Alessandro Benigni

Schema Harness Pushes Opus 4.8 to 99% on ARC-AGI-3. Featured image for AI Insiders.

Agents / Jul 18

Schema Harness Pushes Opus 4.8 to 99% on ARC-AGI-3

By Alessandro Benigni

OpenAI's Supply Co. sells a $230 keyboard built to run Codex — featured image for AI Insiders

Agents / Jul 16

OpenAI's Supply Co. sells a $230 keyboard built to run Codex

By Alessandro Benigni

A solo coder built a $110 pipeline that merges its own PRs — featured image for AI Insiders

Agents / Jul 16

A solo coder built a $110 pipeline that merges its own PRs

By Alessandro Benigni

Goodfire Opens Beta for an AI Agent That Runs Research Experiments — featured image for AI Insiders

Agents / Jul 16

Goodfire Opens Beta for an AI Agent That Runs Research Experiments

By Alessandro Benigni

xAI Opens Grok Build's Code, Not Its Development Process — featured image for AI Insiders

Agents / Jul 16

xAI Opens Grok Build's Code, Not Its Development Process

By Alessandro Benigni

An AI Research Agent Rewrote Its Own Harness in Eight Days — featured image for AI Insiders

Agents / Jul 16

An AI Research Agent Rewrote Its Own Harness in Eight Days

By Alessandro Benigni

Perplexity ships SPACE, sandboxes that self destruct after each agent task — featured image for AI Insiders

Agents / Jul 16

Perplexity ships SPACE, sandboxes that self destruct after each agent task

By Alessandro Benigni

A Developer Cut His AI Agent's Token Bill by 94 Percent — featured image for AI Insiders

Agents / Jul 16

A Developer Cut His AI Agent's Token Bill by 94 Percent

By Alessandro Benigni

OpenAI tells enterprises to stop counting tokens and start counting outcomes — featured image for AI Insiders

Agents / Jul 16

OpenAI tells enterprises to stop counting tokens and start counting outcomes

By Alessandro Benigni

Warp's CEO pitches "software factories" as the next leap past coding agents — featured image for AI Insiders

Agents / Jul 16

Warp's CEO pitches "software factories" as the next leap past coding agents

By Alessandro Benigni

Fable Costs Twice as Much as Opus. It's Still Cheaper to Run. — featured image for AI Insiders

Agents / Jul 15

Fable Costs Twice as Much as Opus. It's Still Cheaper to Run.

By Alessandro Benigni

Google open-sources Mantis, a 15-stage AI pipeline for hunting bugs — featured image for AI Insiders

Agents / Jul 15

Google open-sources Mantis, a 15-stage AI pipeline for hunting bugs

By Alessandro Benigni

Grok Build CLI uploaded whole repos before xAI quietly shut it off — featured image for AI Insiders

Agents / Jul 15

Grok Build CLI uploaded whole repos before xAI quietly shut it off

By Alessandro Benigni

Manus Auto-Publish Cuts the Human Out of the Deploy Step — featured image for AI Insiders

Agents / Jul 15

Manus Auto-Publish Cuts the Human Out of the Deploy Step

By Alessandro Benigni

Microsoft gives its AI agents identities, retry loops, and grades — featured image for AI Insiders

Agents / Jul 15

Microsoft gives its AI agents identities, retry loops, and grades

By Alessandro Benigni

Sakana AI's Smart Bricks Learn to Recognize Their Own Shape — featured image for AI Insiders

Agents / Jul 15

Sakana AI's Smart Bricks Learn to Recognize Their Own Shape

By Alessandro Benigni

Cursor Is Reportedly Building an Agent That Isn't Just for Code — featured image for AI Insiders

Agents / Jul 13

Cursor Is Reportedly Building an Agent That Isn't Just for Code

By Alessandro Benigni

A second AI agent's only job: remind the first before it forgets — featured image for AI Insiders

Agents / Jul 13

A second AI agent's only job: remind the first before it forgets

By Alessandro Benigni

LangChain's OpenWiki 0.1.0 Gives Agents a Memory That Updates Itself — featured image for AI Insiders

Agents / Jul 13

LangChain's OpenWiki 0.1.0 Gives Agents a Memory That Updates Itself

By Alessandro Benigni

Claude Code Desktop Adds a Sandboxed In-App Browser — featured image for AI Insiders

Agents / Jul 13

Claude Code Desktop Adds a Sandboxed In-App Browser

By Alessandro Benigni

OpenAI Kills Atlas Browser, Folds Agentic Browsing Into ChatGPT — featured image for AI Insiders

Agents / Jul 11

OpenAI Kills Atlas Browser, Folds Agentic Browsing Into ChatGPT

By Alessandro Benigni

OpenAI Launches ChatGPT Work to Compete With Claude Cowork — featured image for AI Insiders

Agents / Jul 11

OpenAI Launches ChatGPT Work to Compete With Claude Cowork

By Alessandro Benigni

NVIDIA Pushes Open and Synthetic Data as the Real Agent Bottleneck — featured image for AI Insiders

NVIDIA Pushes Open and Synthetic Data as the Real Agent Bottleneck

By Alessandro Benigni

A New Taxonomy Splits Self-Improving Agents Into Three Real Layers — featured image for AI Insiders

A New Taxonomy Splits Self-Improving Agents Into Three Real Layers

By Alessandro Benigni

Microsoft finds coding agents do worse with JSON than plain CLI args — featured image for AI Insiders

Microsoft finds coding agents do worse with JSON than plain CLI args

By Alessandro Benigni

When Users Fix Your Agent's Mistakes, That Fix Is Data — featured image for AI Insiders

When Users Fix Your Agent's Mistakes, That Fix Is Data

By Alessandro Benigni

Google Turns Gemini's Managed Agents Into Async Background Workers — featured image for AI Insiders

Google Turns Gemini's Managed Agents Into Async Background Workers

By Alessandro Benigni

Claude Cowork Goes Live on Web and Mobile for Max Users — featured image for AI Insiders

Claude Cowork Goes Live on Web and Mobile for Max Users

By Alessandro Benigni

Claude Code, Codex, and Omp Are Now Roughly Tied on Quality — featured image for AI Insiders

Claude Code, Codex, and Omp Are Now Roughly Tied on Quality

By Alessandro Benigni

Claude Developers maps the four variables behind agent loops — featured image for AI Insiders

Claude Developers maps the four variables behind agent loops

By Alessandro Benigni

Replit builds two systems to make agents learn without new weights — featured image for AI Insiders

Replit builds two systems to make agents learn without new weights

By Alessandro Benigni

An Anthropic Engineer Says Find Your Unknowns Before You Build. Featured image for AI Insiders

An Anthropic Engineer Says Find Your Unknowns Before You Build

By Alessandro Benigni

As Coding Models Commoditize, the Harness Becomes the Moat. Featured image for AI Insiders

As Coding Models Commoditize, the Harness Becomes the Moat

By Alessandro Benigni

Google Tests a Dedicated Triage Inbox Inside Gemini. Featured image for AI Insiders

Google Tests a Dedicated Triage Inbox Inside Gemini

By Alessandro Benigni

Verification, Not Generation, Is Now the Bottleneck in AI Coding. Featured image for AI Insiders

Verification, Not Generation, Is Now the Bottleneck in AI Coding

By Alessandro Benigni

Cognition's Devin Security Swarm hunts bugs with an agent MapReduce — featured image for AI Insiders

Cognition's Devin Security Swarm hunts bugs with an agent MapReduce

By Alessandro Benigni

SGLang codifies debugging and benchmarking knowledge into agent skills — featured image for AI Insiders

SGLang codifies debugging and benchmarking knowledge into agent skills

By Alessandro Benigni

A new harness lets agents keep learning ARC-AGI-3 on the fly — featured image for AI Insiders

A new harness lets agents keep learning ARC-AGI-3 on the fly

By Alessandro Benigni

Introspection bets the next agent product is a feedback loop — featured image for AI Insiders

Introspection bets the next agent product is a feedback loop

By Alessandro Benigni

Cognition ships a dual-agent cost cutter for Devin — featured image for AI Insiders

Cognition ships a dual-agent cost cutter for Devin

By Alessandro Benigni

Cursor brings agent control to iOS with public beta launch — featured image for AI Insiders

Cursor brings agent control to iOS with public beta launch

By Alessandro Benigni

Mistral Launches Workflows, a Durable Orchestration Layer for Agent Pipelines — featured image for AI Insiders

Mistral Launches Workflows, a Durable Orchestration Layer for Agent Pipelines

By Alessandro Benigni

Alibaba's Qwen turns image generation into a planning agent — featured image for AI Insiders

Agents / Jun 30

Alibaba's Qwen turns image generation into a planning agent

By Alessandro Benigni

Coding agents are gaming their own benchmarks — featured image for AI Insiders

Agents / Jun 27

Coding agents are gaming their own benchmarks

By Alessandro Benigni

Meta's Autodata trains AI agents to build better training data — featured image for AI Insiders

Agents / Jun 27

Meta's Autodata trains AI agents to build better training data

By Alessandro Benigni

Alibaba's Qwen team built a model that simulates AI agents, not just runs them — featured image for AI Insiders

Agents / Jun 26

Alibaba's Qwen team built a model that simulates AI agents, not just runs them

By Alessandro Benigni

Google brings computer use into Gemini 3.5 Flash — featured image for AI Insiders

Agents / Jun 26

Google brings computer use into Gemini 3.5 Flash

By Alessandro Benigni

Perplexity Targets Legal Ops with Computer for Counsel — featured image for AI Insiders

Agents / Jun 26

Perplexity Targets Legal Ops with Computer for Counsel

By Alessandro Benigni

Stably ships Orca, an open-source IDE built for fleets of coding agents — featured image for AI Insiders

Agents / Jun 26

Stably ships Orca, an open-source IDE built for fleets of coding agents

By Alessandro Benigni

Anthropic's Claude Tag Turns Slack Into a Shared Agent Layer — featured image for AI Insiders

Agents / Jun 25

Anthropic's Claude Tag Turns Slack Into a Shared Agent Layer

By Alessandro Benigni

IBM's CUGA agent harness shifts governance from a retrofit to a default — featured image for AI Insiders

Agents / Jun 25

IBM's CUGA agent harness shifts governance from a retrofit to a default

By Alessandro Benigni

NVIDIA Builds an Agent Software Stack on Top of Its Chips — featured image for AI Insiders

Agents / Jun 25

NVIDIA Builds an Agent Software Stack on Top of Its Chips

By Alessandro Benigni

Anthropic's Cowork Is Coming to Mobile, and That Changes the Contract — featured image for AI Insiders

Agents / Jun 24

Anthropic's Cowork Is Coming to Mobile, and That Changes the Contract

By Alessandro Benigni

OpenAI reframes Codex as a standing project, not a prompt tool — featured image for AI Insiders

Agents / Jun 24

OpenAI reframes Codex as a standing project, not a prompt tool

By Alessandro Benigni

Structure Beats Scale: The Case for Small Models With Knowledge Layers — featured image for AI Insiders

Agents / Jun 24

Structure Beats Scale: The Case for Small Models With Knowledge Layers

By Alessandro Benigni

Tencent puts AI inside WeChat, betting distribution beats model quality — featured image for AI Insiders

Agents / Jun 24

Tencent puts AI inside WeChat, betting distribution beats model quality

By Alessandro Benigni

A New Protocol Wants to Be the Search Engine for AI Agents — featured image for AI Insiders

Agents / Jun 22

A New Protocol Wants to Be the Search Engine for AI Agents

By Alessandro Benigni

NVIDIA's ENPIRE lets coding agents train robots without human resets — featured image for AI Insiders

Agents / Jun 22

NVIDIA's ENPIRE lets coding agents train robots without human resets

By Alessandro Benigni

The unit of AI coding work is no longer the prompt — featured image for AI Insiders

Agents / Jun 22

The unit of AI coding work is no longer the prompt

By Alessandro Benigni

Sakana AI ships Fugu, a multi-agent system behind a single model API — featured image for AI Insiders

Agents / Jun 22

Sakana AI ships Fugu, a multi-agent system behind a single model API

By Alessandro Benigni

Claude Code Gets Artifacts: Shareable Live Pages From Your Work Session — featured image for AI Insiders

Agents / Jun 20

Claude Code Gets Artifacts: Shareable Live Pages From Your Work Session

By Alessandro Benigni

Deep research agents leak private data through their web queries — featured image for AI Insiders

Agents / Jun 20

Deep research agents leak private data through their web queries

By Alessandro Benigni

Perplexity Builds Persistent Memory Into Its Agent Platform — featured image for AI Insiders

Agents / Jun 20

Perplexity Builds Persistent Memory Into Its Agent Platform

By Alessandro Benigni

Replit Plugs Into Claude, Closing the Design-to-Deploy Gap — featured image for AI Insiders

Agents / Jun 19

Replit Plugs Into Claude, Closing the Design-to-Deploy Gap

By Alessandro Benigni

Vercel ships eve, an open-source production runtime for agents — featured image for AI Insiders

Agents / Jun 19

Vercel ships eve, an open-source production runtime for agents

By Alessandro Benigni

Android 17 turns every app into an agent-callable tool — featured image for AI Insiders

Agents / Jun 18

Android 17 turns every app into an agent-callable tool

By Alessandro Benigni

Factory rebrands as a platform for "software factories," not coding agents — featured image for AI Insiders

Agents / Jun 17

Factory rebrands as a platform for "software factories," not coding agents

By Alessandro Benigni

Sakana AI ships first commercial product: an 8-hour autonomous research agent — featured image for AI Insiders

Agents / Jun 17

Sakana AI ships first commercial product: an 8-hour autonomous research agent

By Alessandro Benigni

Apple built a third-party AI extension layer for Siri and then hid it — featured image for AI Insiders

Agents / Jun 16

Apple built a third-party AI extension layer for Siri and then hid it

By Alessandro Benigni

Google's Gemini Skills Marketplace is an agent distribution play — featured image for AI Insiders

Agents / Jun 16

Google's Gemini Skills Marketplace is an agent distribution play

By Alessandro Benigni

AI beats humans at AI research on three narrow ML benchmarks — featured image for AI Insiders

Agents / Jun 13

AI beats humans at AI research on three narrow ML benchmarks

By Alessandro Benigni

OpenAI acquires Ona to own the agent execution layer — featured image for AI Insiders

Agents / Jun 13

OpenAI acquires Ona to own the agent execution layer

By Alessandro Benigni

Anthropic launches managed agent platform to own the full stack — featured image for AI Insiders

Agents / Jun 12

Anthropic launches managed agent platform to own the full stack

By Alessandro Benigni

Microsoft Scout puts a persistent agent inside the M365 stack — featured image for AI Insiders

Microsoft Scout puts a persistent agent inside the M365 stack

By Alessandro Benigni

Meta Launches Business Agent With 1 Million Businesses Already Using It — featured image for AI Insiders

Meta Launches Business Agent With 1 Million Businesses Already Using It

By Alessandro Benigni

Memory leaks in agent harnesses hit 57-71% cross-user contamination — featured image for AI Insiders

Memory leaks in agent harnesses hit 57-71% cross-user contamination

By Alessandro Benigni

Perplexity turns the AI PC into a cloud traffic controller — featured image for AI Insiders

Perplexity turns the AI PC into a cloud traffic controller

By Alessandro Benigni

Perplexity bets that models should write their own search plans — featured image for AI Insiders

Perplexity bets that models should write their own search plans

By Alessandro Benigni

Devin crossed a threshold: automation now triggers more sessions than humans — featured image for AI Insiders

Devin crossed a threshold: automation now triggers more sessions than humans

By Alessandro Benigni

Microsoft's Copilot Super App Leaks Before Build 2026 — featured image for AI Insiders

Microsoft's Copilot Super App Leaks Before Build 2026

By Alessandro Benigni

NotebookLM's Canvas feature puts Google in the document-ownership fight — featured image for AI Insiders

NotebookLM's Canvas feature puts Google in the document-ownership fight

By Alessandro Benigni

Open-source harnesses get Claude Code's workflow primitive — featured image for AI Insiders

Open-source harnesses get Claude Code's workflow primitive

By Alessandro Benigni

Workday's Agent Bet: Permissioning, Not Performance, Is the Wall — featured image for AI Insiders

Workday's Agent Bet: Permissioning, Not Performance, Is the Wall

By Alessandro Benigni

Claude Code's Dynamic Workflows rewrote Bun from Zig to Rust in 11 days — featured image for AI Insiders

Agents / May 30

Claude Code's Dynamic Workflows rewrote Bun from Zig to Rust in 11 days

By Alessandro Benigni

OpenAI's Codex builds a tax agent that patches its own failures — featured image for AI Insiders

Agents / May 29

OpenAI's Codex builds a tax agent that patches its own failures

By Alessandro Benigni

Anthropic argues containment starts at the environment layer, not the model — featured image for AI Insiders

Agents / May 28

Anthropic argues containment starts at the environment layer, not the model

By Alessandro Benigni

Anthropic plans an AI Fluency scorecard in Claude across 11 indicators — featured image for AI Insiders

Agents / May 28

Anthropic plans an AI Fluency scorecard in Claude across 11 indicators

By Alessandro Benigni

xAI ships Grok Build, a terminal coding agent with plan mode and subagents — featured image for AI Insiders

Agents / May 27

xAI ships Grok Build, a terminal coding agent with plan mode and subagents

By Alessandro Benigni

Anthropic plans Memory Files: notes sharded across structured documents — featured image for AI Insiders

Agents / May 26

Anthropic plans Memory Files: notes sharded across structured documents

By Alessandro Benigni

Reasonix bets on prefix-cache stability for low-cost coding agents — featured image for AI Insiders

Agents / May 26

Reasonix bets on prefix-cache stability for low-cost coding agents

By Alessandro Benigni

Cursor's cloud-agent architecture converges on four durable primitives — featured image for AI Insiders

Agents / May 22

Cursor's cloud-agent architecture converges on four durable primitives

By Alessandro Benigni

Google ships Agent Executor, an open-source runtime for long-running agents — featured image for AI Insiders

Agents / May 21

Google ships Agent Executor, an open-source runtime for long-running agents

By Alessandro Benigni

The agent-training loop is just five steps, whatever the framework — featured image for AI Insiders

Agents / May 21

The agent-training loop is just five steps, whatever the framework

By Alessandro Benigni

Claude Code drops Markdown for HTML as its default context format — featured image for AI Insiders

Agents / May 20

Claude Code drops Markdown for HTML as its default context format

By Alessandro Benigni

Warp launches Oz as a multi-harness control plane for cloud agents — featured image for AI Insiders

Agents / May 20

Warp launches Oz as a multi-harness control plane for cloud agents

By Alessandro Benigni

Manus Adds Persistent Context to Its Scheduled Task Engine — featured image for AI Insiders

Agents / May 19

Manus Adds Persistent Context to Its Scheduled Task Engine

By Alessandro Benigni

xAI adds persistent Skills to Grok across web and mobile — featured image for AI Insiders

Agents / May 19

xAI adds persistent Skills to Grok across web and mobile

By Alessandro Benigni

Cursor Trains a Coding Agent from Scratch to Beat the Inference Layer — featured image for AI Insiders

Agents / May 19

Cursor Trains a Coding Agent from Scratch to Beat the Inference Layer

By Alessandro Benigni

Featured image for: Google makes Gemini the operating layer of Android 17

Agents / May 19

Google makes Gemini the operating layer of Android 17

By Alessandro Benigni