Agent Evals: A 5-Step Framework From LangChain's LangSmith Team
Agent evals start with 10 to 20 traced examples, not a benchmark. LangChain's five-step framework for offline, online and LLM-judge evals, and its limits.
Context Rot: How Deep Agents Keeps Long-Running Agents Focused
Context rot degrades long-running agents as tool output piles up. How LangChain's Deep Agents offloads, summarizes and isolates context, and what to tune.
Anthropic Scion: Why Agents Outgrew Git at 30,000 Merges a Day
Anthropic Scion replaced git after merges rose from 2,500 to 30,000 a day. How its always-online design works, and what agent-heavy teams should borrow.
LangSmith AI Search: Finding Agent Failures by Behavior
LangSmith AI Search finds agent traces by behavior, such as false claims of success, using a model that reads each trace. How it works and where it falls short.
OpenAI Decisions API: Free Output Tokens, Hosted-Only Weights
OpenAI's Decisions API bills only input tokens for yes/no, choice, and score outputs. How it stacks up against Jev and open-weight agentic AI decision models.
Simon Willison's Case for Default Hard Budget Caps on Every AI API
Soft alerts let you wake up to a $10,000 bill. Simon Willison argues hard budget caps should be the default on every AI API, with uncapped use as an opt-in.
Claude Code Gets a Plugin System: Mods Are JavaScript Middleware That Run Inside the Tool
Anthropic's Claude Code Mods are JavaScript middleware that intercept tool calls, add panels, and create commands. They run unsandboxed, with your permissions.
Suno Speech: Generate Spoken Audio with AI-Matched Background Music in a Single Prompt
Suno Speech generates spoken audio and matching background music from one prompt. It's in beta with accent issues; poems and bedtime stories are the main uses.
Unity Releases Official Plugins for Claude Code and OpenAI Codex to Fix AI Agents' Reliance on Outdated Tutorials
Unity's official Claude Code plugin (via npm) and OpenAI Codex plugin (31 skills covering UI, URP, audio, physics, multiplayer, and more) address a root cause of AI agent mistakes in game development: reliance on forum posts and tutorials written for older engine versions that compile but don't work as intended. Both require Unity 6.
Your Agentic AI Passes All Its Tests. But Do You Know How It Got There?
Graham Clay's framework for evaluating agentic AI tools separates three types of evidence — activity records, permission histories, and deliverables — to distinguish between agents that genuinely completed a task and those that completed it with unplanned human intervention.
How to Test SQS Resilience Before an Outage Does It for You
AWS architecture blog walks through a four-phase fault injection experiment for SQS-dependent applications using AWS Fault Injection Service. The technique validates whether circuit breakers, retry logic, and fallback storage actually work under real access failures — not just theoretical ones.
Meta Dropped AI Usage From Engineer Reviews After Costs Headed Toward Billions
Meta built a performance system that measured engineer AI token consumption. Engineers immediately gamed it with bulk token consumption. Executives called internal AI costs 'heading toward billions.' Meta removed the metric.
Alibaba's Qwen-Drive Can Tell You Why It Braked — The Explanation Just Might Not Be True
Qwen-Drive 1.0 is an open-source autonomous driving model that generates natural language explanations for its decisions. Its own researchers found those explanations don't reliably match the actual decisions.
ROCm 10.0: AMD's Open AI Stack Now Reaches 90% of H100 Performance
AMD's ROCm 10.0 ships with a new CLI, agentic AI integrations, and an autonomous optimizer. The MI355X now hits 90-95% of H100 throughput at 15-40% lower hardware cost.
GPT-6 Astra Prompting: OpenAI's Slop Blocklist and Action Rules
OpenAI published specific prompting tips for GPT-6 Astra: a slop blocklist, action-bias instructions, and debugging guidance for stalled agents.
Gemini's Agentic Video Mode Cuts Token Usage by 88% — Here's What Changed
Google's agent-based video analysis lets Gemini 3.7 Flash selectively sample frames rather than scan at fixed rates, dropping token costs 66% while slightly improving benchmark accuracy.
Only Believe What You Can Validate: A Verification Framework for Agentic AI
Microsoft's Julia Kordick argues that agentic AI outputs require systematic verification — not expert spot-checks — and maps exactly how to build that into modernization workflows.
AI Agents Have No Sense of Time — And They Don't Know It
Research shows Claude overestimates task time by 3× and Codex by 6–10×. Both scored themselves 70% successful on tasks they completed at 7–14%. Here's what that means for production deployments.
Agentic AI Overwhelmed CI — Test Selection Cut P95 Queue Time by 92%
When coding agents pushed one project to 500K lines, the CI queue ballooned to 7.5 hours. Intelligent test selection — not more runners — was the fix.
AI Coding Agent Benchmarks Have a Refactoring Blind Spot — A New Test Exposes It
Most AI coding agent benchmarks measure isolated bug fixes and small feature additions. A new benchmark specifically targets large-scale refactoring, exposing a capability gap that production deployments feel but evaluations miss.
Mojo Is Now Open Source — What It Means for GPU Programming
Mojo's compiler and toolchain went Apache 2.0 on August 18, fulfilling a promise made since May 2023 and opening GPU-optimized Python-syntax programming to community development.
Search APIs for AI Agents: The First Head-to-Head Benchmark Has a Clear Winner
Artificial Analysis ran 25 iterations across 1,700 questions to compare 7 search APIs for agentic use. Parallel topped at 75/100, but the most surprising finding was about cost and speed.
Anthropic Costs 4.4× More Per Token on Vercel — Developers Keep Paying Anyway
Anthropic captured 65% of Vercel's AI Gateway spending with just 30% of the token volume. The premium is documented, the gap is widening, and developers are choosing it anyway.
AI Rewrites Don't Preserve Meaning — and That Changes How You Should Use Them
Sophie Alpert's principle: every AI rephrase changes what you said. The engineering policy implication is more specific than 'use AI carefully.'
Backflip AI: From 3D Scan to Editable CAD Model in Minutes
Backflip AI converts mesh files and 3D scans into parametric CAD models — not triangle meshes — making the $30M-funded platform the fastest path from physical part to editable design file.
Claude Code Sessions Can Now Talk to Each Other Across Terminals
Anthropic's new cross-session messaging turns isolated Claude Code instances into a coordinated team — local sessions share context automatically, remote sessions route through Anthropic's servers.
Agent Protocol: The Open Standard for AI Plugin Packaging
Amazon, Cursor, Microsoft, OpenAI, and Vercel released Agent Protocol — a unified spec for AI agent plugin packaging that ends the per-platform rebuild cycle.
Claude Code: Fastest Agent Framework, but Nearly 3× the Cost of Rivals
A Composio benchmark across four agent frameworks reveals Claude Code dominates on speed at 122 seconds per task — but costs 2.7× more per successful task than OpenCode.
FLUX 3 Video: Black Forest Labs Claims Top Elo Score at $0.06 Per Second
FLUX 3 Video is now generally available via API with a 1,135 Elo score, 14-language lip sync, native audio, and full HD output — all included from $0.06 per second.
AAFlow: The Agentic AI Workflow Paper That Solves the Data Serialization Bottleneck
AAFlow proposes a zero-copy data plane for agentic AI pipelines using Apache Arrow and Cylon, delivering up to 4.64x pipeline speedup. Here's what it means for production AI workflow design.
LLM 0.32: Simon Willison's CLI Now Surfaces Model Reasoning and Connects to MCP Servers
LLM 0.32 adds visible reasoning traces, server-side tools for OpenAI and Anthropic, OpenAI Responses API compatibility, and a Git-like content-addressable log. Here's what changed and why it matters for agentic workflows.
Claude Opus 5: From Color Blocks to Full 3D Games
Claude Opus 5 turns a single prompt into a playable 3D game with physics and music, no external assets, revealing a real per-build compute cost.
Stateless MCP: Why the Protocol Dropped Session IDs
The 2026-07-28 MCP spec update replaced two-request session handshakes with a single stateless call — simplifying how agentic tools scale.
How to Add a Custom MCP Server to Claude and ChatGPT
A step-by-step look at connecting a custom MCP server to Claude and ChatGPT's chat interfaces — and where ChatGPT's setup gets far more involved.
The Framework for Picking the Right AI Tool, Not Just Any Chatbot
Ethan Mollick's decision framework sorts AI tools by stakes and autonomy, not brand loyalty — and it explains why 'just use ChatGPT for everything' is bad advice.
AI Coding Tutors Raise Grades. A New Survey Says They're Lowering Skill.
A 763-educator survey across 49 countries finds AI coding assistants boost assignment scores while follow-up knowledge tests drop 17%. Here's what's actually being measured.
Nativ Turns Any Apple Silicon Mac Into a Local AI Server
Prince Canuma's open-source Nativ app finds AI models already cached on your Mac and serves them locally for chat and coding agents — no cloud, no account.
Inside Claude Code: Why Anthropic Cut Its System Prompt 80% on Purpose
A fireside chat with the Claude Code team reveals an 80% system-prompt cut, an auto-mode permission classifier, and the internal-adoption rule behind every feature ship.
VulnHunter: An AI Security Agent That Disproves Its Own Findings
Capital One open-sources VulnHunter: an agentic AI code security tool built on Claude that falsifies its own vulnerability findings before surfacing them to developers.
OpenAI's $230 Codex Micro: When AI Agents Get a Physical Control Surface
OpenAI's first hardware product is a macropad that puts agent status on RGB keys and agent actions on a joystick. Here's what it signals about how developers will work with coding agents.
The Father of Modern RL Is Betting Generative AI Can't Learn. His New Lab Will Try to Prove It.
Richard Sutton — 2024 Turing Award winner, reinforcement learning pioneer — founded Oak Lab in Toronto to build agents that learn continuously from experience, not from static datasets.
Claude Code's New Browser Turns the AI Into a Web-Aware Coding Agent
Anthropic's built-in browser for Claude Code lets the AI read pages, click elements, and type — without requiring logged-in sessions or a separate automation stack.
How 64 Claude Agents Rewrote Bun From Zig to Rust in 11 Days
64 parallel Claude Fable 5 instances rewrote Bun's 1M+ line codebase in 11 days for $165K — compressing a year of engineering work. What this means for AI-assisted migration.
Gemini API Adds MCP and Background Execution: What Changes for Agent Builders
Google Deepmind's Gemini API Managed Agents now support background execution and remote MCP server connections—removing the two most common blockers for production agent deployment.
Five Fable 5 Prompting Techniques That Fix What Vague Prompts Break
An Anthropic developer's framework for getting better Fable 5 output starts with finding your own knowledge gaps before writing the prompt — not refining the prompt itself.
Anthropic Cut Claude Code's System Prompt by 80% — Because More Instructions Made It Worse
Anthropic reduced Claude Code's system prompt by 80% when switching to Fable 5. The reason inverts a common assumption: more capable models perform worse with more instructions.
Anthropic Claude Science: AI Workbench Built for Scientific Research
Anthropic launched Claude Science — a specialized AI workbench with 60+ preconfigured skills for genomics, proteomics, and cheminformatics, with a built-in citation verification agent.
shot-scraper video: Your AI Coding Agent Can Now Record Its Own Work
shot-scraper 1.10 adds a storyboard.yml-driven video recorder that lets coding agents autonomously document web app workflows — turning agent output into watchable, reviewable demos.
Ornith-1.0: Open-Weights Self-Scaffolding LLMs That Handle Agentic Coding Natively
DeepReinforce's Ornith-1.0 brings self-scaffolding to open-weights models from 9B to 397B — MIT licensed, built on Gemma 4 and Qwen 3.5, with state-of-the-art coding benchmark results.
Claude Code's Verification Gap: When Agents Run Code Without Looking
Security researchers caught Claude Code executing a hidden DNS payload without user preview — handing attackers full machine access via a GitHub link.
Akrites: Closing Open-Source Security's 5% Patch-Rate Problem Before AI Attacks Hit
Akrites: the Linux Foundation's answer to open-source security's 5% patch rate — before AI-powered attackers exploit every unaddressed flaw in critical dependencies.
Gemini 3.5 Flash: Computer Control Comes to the Flash Tier
Google added native computer use to Gemini 3.5 Flash, scoring 78.4 on OSWorld and matching Claude Sonnet 4.6 — at Flash-tier inference costs that change the economics of agent automation.
Cursor's Stack Bet: The Git Platform May Matter More Than the AI Model
Cursor revealed a self-trained AI model, the Origin Git platform for AI-agent-scale repository access, and a mobile agent manager — a pivot from IDE to full coding platform.
Vibe-Coding Due Diligence: Why AI Agent Plugins Are Your Next Supply Chain Risk
Developers install AI coding agent plugins from unmanaged GitHub repos and Slack messages with zero provenance tracking. JFrog's new Agent Plugins Repositories make the case for treating them like any other software dependency.
Cloudflare's Temporary Workers: Disposable Infrastructure for AI Agents
Cloudflare's new temporary deployment feature spins up a Workers project for 60 minutes with no account required. It solves a real friction problem in agentic AI workflows that need ephemeral execution environments.
OpenAI Codex Record & Replay: One Demo Becomes a Reusable Automation
Codex's new Record & Replay feature converts a single task demonstration into a reusable skill — a step toward agents that learn workflows from observation rather than explicit instruction.
Claude Code Artifacts: Turning Coding Sessions into Live Team Pages
Anthropic's Claude Code now generates shareable, auto-updating web pages from coding sessions — PR walkthroughs, incident timelines, and architecture reviews delivered as live artifacts to organization members.
Agentic AI Is Solving the Coding Problem and Creating the Review Problem
LinearB's 2026 data shows agentic AI PRs wait 5.3x longer in the review queue than unassisted ones. Feature branch throughput jumped 59% while main-branch success rates fell. The bottleneck moved from writing code to deciding whether code is safe to merge.
Xiaomi's MiMo Code Benchmarks Past Claude Code on Terminal Bench — as Open Source
Xiaomi released MiMo Code on June 10 — an open-source agentic coding agent built on a 1T-parameter MoE model. Terminal-Bench 2.0: 86.7% vs Claude Code's 65.4%. Past 200 steps, it posts a 65%+ win rate in human A/B testing with 576 developers. The self-reported benchmark caveat applies.
AI Coding Agents Find the Right File — But Cover Only 14–19% of the Critical Lines
The SWE-Explore benchmark reveals a structural gap in how AI coding agents explore repositories: correct file navigation masks dangerously shallow line-level coverage of the code that actually matters.
Agentic AI's Production Data Problem: Why the Manual Model Breaks
When AI agents write to live databases faster than any review process can catch, procedural safeguards fail. Here's the isolation pattern cloud-native teams are adopting.
Agentic AI Solved the Coding Problem—and Exposed Everything Else
Agentic AI has made coding fast. The exposed problems—requirements, integration, accountability—were always the real bottleneck. Now they're visible.
Perplexity's Search as Code: AI Models Now Write Their Own Search Pipelines
Perplexity Search as Code lets AI models generate custom Python search workflows instead of calling fixed APIs — delivering 85% fewer tokens and leading competitors on 4 of 5 benchmarks.
Sandboxes and Worktrees: The Secure Agentic AI Dev Setup That Actually Works
Mike McQuaid, Homebrew's lead maintainer, runs AI coding agents in sandboxed unprivileged accounts with git worktrees. His setup closes the majority of agentic risk vectors without slowing down velocity.
Amazon's Kirorank: What Happens When You Gamify AI Adoption
Amazon's AI leaderboard taught developers to run pointless tasks to climb rankings. The Kirorank incident is a precise map of how to measure the wrong thing at AI scale.
Linus Torvalds: '99% AI Code' Claims Make Him Angry — Here's Why He's Right
At Open Source Summit 2026, Linus Torvalds dismissed the '99% of code is AI' narrative with a precise analogy. His argument is the most useful framing yet for what AI actually changes in software development.
Coding Agents: George Hotz's Case for Why They Create Dangerous Technical Debt
George Hotz argues coding agents will generate one of software's costliest technical debt crises — and his six months testing tinygrad shows why.
OpenAI Appshots: Any Active Mac Window Becomes Codex Context With Two Keys
Press both Command keys on Mac to send any open window — including text below the scroll — directly to Codex. What the workflow shift means for developers.
Grok Build: xAI Enters the AI Coding Agent Race at $99/Month
xAI's first terminal coding agent ships with 8 parallel subagents and a 2M token context window. At $299/month list, here's what you actually get.
Amazon SageMaker: Agentic Workflows Now Handle Model Customization
AWS's SageMaker now lets developers describe a use case in plain language — a Kiro AI agent handles data prep, training, and model deployment end-to-end.
VS Code Was Quietly Tagging Your Commits as Copilot-Assisted — Even With AI Off
Microsoft inserted Co-Authored-by Copilot into VS Code commits without consent, including for developers with AI features disabled — raising copyright and enterprise AI policy risks.
GitHub Copilot Token Billing: What the June 2026 Change Means for Engineering Teams
GitHub Copilot moves from premium request counts to token-based billing in June 2026. Here's what changes, what doesn't, and how agentic use cases change the cost calculus.
The $60B Cursor Question: Why SpaceX Is Betting on an AI Coding Tool It Doesn't Own Yet
SpaceX's reported $60B acquisition offer for Cursor — with a $10B breakup fee — is the most concrete signal yet of how much enterprise AI coding infrastructure is worth to compute-heavy operators.
Google A2UI: A Generative UI Standard for AI Agents Across Every Framework
Google's A2UI v0.9 lets AI agents generate UI components at runtime across React, Flutter, Lit, and Angular — a framework-agnostic standard that integrates with A2A 1.0, AG2, and Vercel's json-renderer.
Coding Agent Architecture: The Six Components That Actually Matter
The model isn't the differentiator in a coding agent — the harness is. Six components that separate working coding agents from unreliable ones.
Cursor 3 Killed the IDE Layout: What an Agent-First Interface Actually Looks Like
Cursor 3 replaces the traditional IDE with a parallel agent fleet interface — and it signals where every serious coding environment is headed in 2026.
Claude Code Channels: Anthropic's Always-On Agent Is Now in Your Pocket
Claude Code v2.1.80 gains a channels feature routing CI alerts, chat messages, and webhooks into active sessions via Telegram or Discord — no developer at the terminal required.
Markdown for Agents: Designing Content for the Autonomous Web
Why the future of the web isn't for human eyes, but for agentic consumption via Markdown.
The Octoverse Paradox: How AI Compatibility is the New Standard for Developer Choice
Analysis of GitHub's Octoverse data revealing the shift from human-centric to AI-compatible technology stacks.
The Agentic Deep Dive #1: The 'Trust but Verify' Protocol
How to implement high-reliability research agents using LangGraph Critic nodes and cross-model verification.
Agentic CI: The Future of Repository Automation in 2026
Exploring GitHub's new Agentic Workflows and how Continuous AI is transforming DevOps into a series of autonomous, reasoning-driven tasks.
Agentic Engineering: Moving Beyond Chat with the Copilot CLI
A technical analysis of the shift from chat-based AI to CLI-driven agentic workflows in the modern development stack.
The Battle for 2026: Agentic Research vs. Manual Analysis
A data-backed comparison between manual information gathering and the modern Agentic Stack.
The Agentic Interface: Redefining Human-Software Interaction
Why the future of software isn't a UI, but a collaborative dialogue with autonomous entities.