#agents
31 posts tagged agents.
CLAUDE.md that scales: @imports, per-folder rules and what actually loads
In a growing project, CLAUDE.md swells and every line loads into every session. @path imports keep it organised, rules in .claude/rules with a paths field load only when Claude reads a matching file, and /context all shows what really made it in.
Claude Code hooks: PreToolUse guards and three recipes that pay off
A rule in CLAUDE.md is advice Claude can miss. A hook is your own command that Claude Code runs at a set moment, every time. How a PreToolUse hook blocks an edit with exit code 2, three recipes worth adding today, and the boundary people forget.
Subagents, workflows or agent teams: how to choose in Claude Code
Claude Code has three ways to split work between workers: subagents, dynamic workflows and agent teams. The real difference is who holds the plan. Three questions, asked in order, tell you which one a task needs — and every step up costs more tokens.
Claude Code worktrees: run parallel sessions without collisions
Two Claude Code sessions in one folder edit the same files and trip over each other. claude --worktree gives each session its own working copy on its own branch. Here is how to prepare a project, the trap with unpushed commits, and how to bring the work back.
How Agent Distraction Impacts AI Coding Efficiency
Learn how obsolete TODOs and bug references in codebases distract AI agents, increasing costs and delays in coding tasks.
Google Play Services LiteRT Boosts GPU Speed and Reduces App Size
LiteRT in Google Play Services now offers faster GPU inference and smaller app sizes, making it easier to run custom ML models on Android.
Build Generative UI Apps with A2UI and CopilotKit Agents
Learn how A2UI and CopilotKit Agents enable dynamic, interactive interfaces for AI-driven applications.
How Agents CLI Helps You Catch and Fix AI Agent Regressions
Learn how Agents CLI's evaluation tools help you systematically improve your AI agents by catching regressions and measuring changes.
A2UI gets faster with swappable formats and decision models
A2UI now lets you choose how models generate UI layouts, with new formats that cut latency by up to 80x for common screens.
Agents CLI Adds Framework Flexibility with Extension System
Google's Agents CLI introduces an Extension System that lets developers use any agent framework, from ADK to LangChain, without forking the tool.
API Gateway adds streaming for real-time and AI APIs
Google Cloud's API Gateway now supports streaming endpoints, letting you serve real-time and AI APIs without splitting your infrastructure.
The Claude Code practicum on GitHub: 14 hands-on tasks with automatic checks
A free, open practicum for the Claude Code: Pro Level course: 14 tasks on a small real project that you do in your own terminal with the real Claude Code, while npm run check tells you what passed. Finish all 14 and you get a code for the Claude Code Practitioner badge.
What Amp's AI Agents Mean for Beginners Building Software
Amp's AI agents, powered by OpenAI models, are expanding what beginners can achieve in software development, from planning to design and beyond.
What Asana's 76x Cost Cut with GPT-6.1 Sol Means for Beginners Building AI
Asana optimized its browser agent workflow using GPT-6.1 Sol, cutting costs by 76x and speeding up runs 5x. Learn what this means for beginners building AI.
What Google's Ambient Quality Agent Means for Beginners Building AI
Google's Ambient Quality Agent (AQuA) helps diagnose production issues in AI agents, making it easier for beginners to maintain and improve their software.
How to Choose and Use GPT-6 Models for Building Software with AI
Learn how to select the right GPT-6 model for your project, optimize prompts, and manage long-running tasks effectively.
What GPT-6.1 Sol Means for Beginners Building AI Agents
GPT-6.1 Sol brings near-Astra performance at a fraction of the cost, making powerful AI agents more accessible for beginners.
What Google Cloud API Gateway's MCP Support Means for Beginners
Google Cloud API Gateway now lets you expose existing REST APIs as MCP tools without running separate servers. Here's what changes for beginners building AI agents.
Better Prompt Caching in GPT-6: What It Means for Beginners Building AI Agents
OpenAI's improved prompt caching in GPT-6 reduces costs and speeds up responses for AI agents handling complex tasks. Here's what beginners need to know.
What Agent Anomaly Detection Means for Beginners Building AI Agents
Agent Anomaly Detection adds a safety layer for AI agents, flagging risky behavior without slowing them down.
What Google's ADK for Kotlin 1.0 Means for Beginners Building AI Agents
Google's ADK for Kotlin 1.0 simplifies building AI agents for Android and server-side applications, making it easier for beginners to create production-ready AI tools.
How to Evaluate and Improve AI Coding Agents Effectively
Learn how to move beyond end-to-end benchmarks and use behavioral evaluations to iteratively improve AI coding agents.
How GPT-6 Astra Helps Devin Test Its Own Code
Cognition uses GPT-6 Astra to automate testing and improve code review efficiency in its Devin software engineering agent.
OpenAI's Zero Data Retention changes how you build private AI apps
OpenAI now keeps no record of your API requests unless you opt in, with new safeguards that spot risks across conversations without storing content.
How Google’s Agent Development Kit Secures AI Agents for Beginners
Learn how Google’s Agent Development Kit helps you build secure AI agents with zero-trust architecture, even as a beginner.
Why Go is the best language for AI-assisted coding
Google explains why Go's design makes it uniquely suited for working with AI coding assistants - and what that means for beginners.
Google Cloud API Gateway Adds Model Routing for AI Applications
Google Cloud API Gateway now supports model routing, allowing developers to dynamically route AI requests to different models without hardcoding endpoints.
Claude Managed Agents now run in your own sandbox and connect to private networks
Self-hosted sandboxes and MCP tunnels let Claude agents work securely with your private data and services—here's what changes for builders.
MCP Stateless Updates Make AI Agents Scale Better
Google's MCP stateless updates remove session bottlenecks, making AI agents more scalable and easier to deploy in production.
Agent Plugins standardize how AI coding tools share components
A new open format packages AI agent skills and tools together without locking them to one platform.
Claude Code artifacts turn AI sessions into shareable web pages
Claude Code can now package your AI coding sessions as live web pages that update automatically, making collaboration easier.