What shipped & dropped across AI labs, today.

Claude Blog2d ago

Choosing a Claude model and effort level in Claude Code

Claude Code has two settings that shape results: which Claude model you use and the effort level. Learn what each one actually controls and how to choose.

Claude Blog3d ago

A field guide to Claude Fable 5: Finding your unknowns

Practical patterns for agentic coding with Claude Fable: how to find your unknowns before, during, and after implementation, from the team at Anthropic.

Claude Blog9d ago

Getting started with loops

Practical guidance on progressing from turn-based to goal-based, time-based, and proactive loops.

OpenAI9d ago

Core dump epidemiology: fixing an 18-year-old bug

OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.

Claude Blog15d ago

Building effective human-agent teams

The way we work with AI is evolving from a single-player to a multiplayer experience, where humans and agents work together as a team to achieve shared goals. We share examples of this new way of working in action.

Claude Blog15d ago

Agent identity in Claude Tag: a new access model for autonomous, team-wide AI

How Claude Tag’s agent identity access model works, and best practices for configuring it in your team’s workspace.

OpenAI27d ago

How Preply combines AI and human tutors to personalize learning

Preply uses OpenAI to launch AI-generated lesson summaries, providing personalised feedback and language learning exercises.

Claude Blog34d ago

The Claude Cowork product guide

We share how to get started with Claude Cowork, from setting up the tool to kicking off your first task.

Claude Blog36d ago

Best practices for getting started with Claude Cowork

When to use Claude Cowork instead of Claude Code or chat, how to decide what workflows to delegate, and concrete steps to get started.

Claude Blog36d ago

Lessons from building Claude Code: How we use skills

What we learned building and scaling hundreds of skills internally at Anthropic.

Claude Blog36d ago

How Anthropic enables self-service data analytics with Claude

Tips and approaches to maximizing Claude’s ability to drive self-serve data insights

OpenAI41d ago

A shared playbook for trustworthy third party evaluations

OpenAI shares guidance on third-party AI evaluations, covering how to assess model capabilities, safeguards, and validity for frontier systems.

Claude Blog44d ago

Code w/ Claude London 2026: Rethinking how we build

Couldn't make it to London? Check out our Code w/ Claude London event recap and watch our session recordings.

Claude Blog55d ago

Deploying Claude across the legal industry

A practical guide to using Claude for legal professionals, covering Claude products, connectors, practice-area plugins, and a three-phase adoption roadmap.

OpenAI55d ago

Building a safe, effective sandbox to enable Codex on Windows

Learn how OpenAI built a safe, effective sandbox to enable Codex on Windows with controlled file access and network limits.

Claude Blog56d ago

The founder's playbook: Building an AI-native startup

We share how AI-native founders are using Claude at every stage of the startup journey, with practical exercises, frameworks, and prompts.

Claude Blog57d ago

Best practices for computer and browser use with Claude

Practical guidance for developers building computer and browser use integrations with the Claude model family.

Google AI for Developers58d ago

Build Long-running AI agents that pause, resume, and never lose context with ADK

How to transition from stateless chatbots to production-grade agents capable of managing long-running enterprise workflows, such as HR onboarding, that span days or weeks. It introduces the Agent Development Kit (ADK) and its architectural shifts, specifically using durable state machines and persistent session storage to ensure an agent never loses context during "idle time" or server restarts. By leveraging event-driven webhooks and multi-agent delegation, the tutorial demonstrates how to build resilient systems that "sleep" during pauses and wake up to resume complex tasks with high reasoning accuracy.

Claude Blog65d ago

Deploying Claude across financial services

In this guide, we share how financial services firms are using Claude to compress their most time-consuming work, including customer examples and a practical adoption roadmap.

Google DeepMind69d ago

Uniting biological toolkits for a new approach to ALS