Daily Roundup

The chief of staff agent Sep 2025 • Claude Agent SDK Agent Patterns Build multi-agent systems with subagents, hooks, output styles, and plan mode features.

This cookbook article introduces the Claude Agent SDK for building multi-agent systems, using a Chief of Staff agent for a startup as the primary example. It demonstrates key features including persistent memory via CLAUDE.md files, bash tool execution for Python scripts, and coordination of specialized subagents. The article progressively builds a comprehensive agent system that aggregates insights from multiple domains to provide executive summaries and actionable recommendations for a CEO managing a $10M Series A startup.

Memory & context management with Claude Sonnet 4.6 May 2025 • Tools Agent Patterns Build AI agents with persistent memory using Claude's memory tool and context editing.

This cookbook demonstrates how to build AI agents with persistent memory using Claude's memory tool and context editing capabilities. It addresses challenges of long-running agents losing learned patterns between sessions and context window overflow by implementing cross-conversation learning and automatic context management. The guide covers practical implementations for use cases like code review assistants, research assistants, and customer support bots, with setup instructions and best practices for memory security and organization.

The observability agent Sep 2025 • Claude Agent SDK Agent Patterns Connect agents to external systems via MCP servers for GitHub monitoring and CI workflows.

This cookbook demonstrates how to connect Claude agents to external systems using MCP (Model Context Protocol) servers for GitHub monitoring and CI workflows. The guide covers integrating Git and GitHub MCP servers to enable agents to interact with repositories, manage workflows, and perform observability tasks. By leveraging MCP servers, agents gain access to specialized tools for Git operations, GitHub platform integration, and CI/CD monitoring without relying on command-line interfaces.

Giving Claude a crop tool for better image analysis Give Claude a crop tool to zoom into image regions for detailed analysis of charts, documents, and diagrams.

This cookbook demonstrates how to build a crop tool for Claude to analyze images with greater detail by zooming into specific regions. The tool uses normalized coordinates (0-1) to let Claude request cropped sections of charts, documents, and diagrams without needing to know pixel dimensions. An agentic loop handles tool calls iteratively until Claude provides a final answer, enabling precise analysis of small text, chart comparisons, and technical details.

Introduction to Claude Skills Create documents, analyze data, automate workflows with Claude's Excel, PowerPoint, PDF skills.

This guide introduces Claude Skills, specialized capability packages that enable document creation, data analysis, and workflow automation through Excel, PowerPoint, and PDF generation. Skills use a three-tier progressive loading model (metadata → full instructions → linked files) to optimize token usage and efficiency. The tutorial covers environment setup, API configuration, skill discovery, and practical quick-start examples for Excel, PowerPoint, and PDF workflows.

Low latency voice assistant with ElevenLabs Nov 2025 • Integrations Build a low-latency voice assistant using ElevenLabs for speech-to-text and text-to-speech combined with Claude.

This cookbook demonstrates building a low-latency voice assistant by combining ElevenLabs (speech-to-text and text-to-speech) with Claude for intelligent responses. The guide covers installation, API setup, and crucially, latency optimization techniques including Claude's streaming API and sentence-by-sentence TTS synthesis. Performance measurements show streaming reduces perceived latency by ~31% compared to non-streaming approaches, with TTS first-chunk delivery in 0.39 seconds.

WebMCP - Why is awesome & How to use it

WebMCP is a powerful tool for AI agent development that enables seamless integration between AI models and web services. This tutorial covers the setup process and practical applications of WebMCP, demonstrating how to leverage it for building intelligent agents. The content includes resources for getting started and exploring related tools like Superdesign for enhanced AI-powered design workflows.

AI Jason

Your tools are now interactive in Claude

Claude now supports interactive tools that allow users to manage external applications directly within the chat interface. Users can perform actions like managing Asana projects, drafting Slack messages, and building charts without leaving Claude. This integration streamlines workflows by bringing tool functionality into the conversational AI environment, reducing context switching and improving productivity.

Anthropic

Claude Code & MCPs built my $145K marketing machine

Cody Schneider, growth engineer and co-founder of Graph, demonstrates how Claude Code and Model Context Protocols (MCPs) were leveraged to build a $145K marketing automation system. The session covers practical go-to-market (GTM) strategies, hands-on implementation of AI-powered tools, and real-world applications of Claude for marketing automation and growth engineering.

Greg Isenberg

Claude Code built me a $273/Day online directory

This video explores how to use Claude Code to build AI-powered online directories that generate revenue. Frey Chu demonstrates practical techniques for leveraging Claude's coding capabilities to create automated directory systems, covering the technical implementation, monetization strategies, and scaling approaches that resulted in $273/day earnings.

Greg Isenberg

Tell HN: I'm 60 years old. Claude Code has re-ignited a passion

A 60-year-old developer shares how Claude Code has reignited their passion for programming, reminiscent of formative moments with technologies like ASP, COM, and VB6. The tool has restored the excitement and drive they felt in their younger years, inspiring late-night coding sessions and renewed enthusiasm despite being on the cusp of retirement.

shannoncc

Automate PDFs and Never Fill Them Out Again

This tutorial demonstrates how to automate PDF form filling using Manus AI, eliminating the need for manual data entry. The video showcases practical techniques for integrating AI-powered automation into PDF workflows, offering 500 credits to get started with Manus. The content focuses on streamlining repetitive form-filling tasks through intelligent automation.

DarrenNeese

Usage & cost Admin API cookbook Aug 2025 • Observability Programmatically access and analyze your Claude API usage and cost data via Admin API.

The Usage & Cost Admin API cookbook provides a practical guide for programmatically accessing Claude API usage and cost data through Anthropic's Admin API. It enables token-level monitoring across models and workspaces, detailed cost breakdowns by service type, and cache efficiency analysis. The guide includes security best practices, API endpoint documentation, and Python code examples for tracking consumption patterns, attributing expenses, and generating financial reports.

Manus AI llega a GoHighlevel (🔥Novedades!)

This content announces the integration of Manus AI with GoHighLevel, a popular CRM and marketing automation platform. The video highlights new features and capabilities that this integration brings to GoHighLevel users. The creator invites viewers to join a free WhatsApp group for GoHighLevel users. This represents an expansion of Manus AI's ecosystem and provides new automation opportunities for marketing professionals.

GoHighLevel En Español

Tool search with embeddings Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery.

This cookbook demonstrates how to scale Claude applications from dozens to thousands of tools using semantic embeddings for dynamic tool discovery. Instead of front-loading all tool definitions (which consumes context and increases latency), the approach provides Claude with a single tool_search tool that returns relevant capabilities on demand, reducing context usage by 90%+. The guide walks through implementing client-side semantic search using SentenceTransformer embeddings to match user queries with appropriate tools from large libraries, making it practical for production applications managing extensive tool ecosystems.

Speculative prompt caching May 2025 • Responses Reduce time-to-first-token by warming cache speculatively while users formulate their queries.

Speculative prompt caching is a technique that reduces time-to-first-token (TTFT) by warming up Claude's cache while users are still formulating their queries. Instead of waiting until a user submits their question to load context into the cache, the system begins cache warming immediately when the user starts typing. This cookbook demonstrates the pattern using SQLite source code as example context, showing how to implement it with the Anthropic Python SDK using async operations and prompt caching controls.

Automatic context compaction Manage context limits in long-running agentic workflows by automatically compressing conversation history.

This cookbook demonstrates automatic context compaction for managing token limits in long-running agentic workflows. It shows how the Claude Agent Python SDK can automatically compress conversation history when token usage exceeds a threshold, enabling tasks to continue beyond the 200k token context limit. The example uses a customer service agent processing support tickets, where each ticket requires multiple tool calls that accumulate in conversation history. By implementing context compaction with the compaction_control parameter, agents can maintain focus and efficiency across many iterations without manual context management.

How I Use Obsidian + Claude Code to Run My Life

Vin demonstrates a comprehensive personal knowledge management and automation system using Obsidian and Claude Code. The setup integrates note-taking, task management, and AI-powered code generation to streamline daily workflows and life organization. This hands-on walkthrough shows practical techniques for leveraging AI agents within a personal productivity ecosystem.

Greg Isenberg

Session memory compaction Jan 2026 • Agent Patterns Responses Manage long-running Claude conversations with instant session memory compaction using background threading and prompt caching.

This cookbook teaches developers how to manage long-running Claude conversations by implementing session memory compaction using background threading and prompt caching. Rather than waiting for context limits to be exceeded (reactive approach), the pattern enables instant compaction by proactively building summaries in the background. The guide covers writing effective session memory prompts, implementing background threading for zero-latency compaction, and applying prompt caching to reduce costs by ~80%. It includes Python code examples demonstrating both traditional (slow) and instant (fast) compaction strategies for conversational applications.

Parallel tool calls on Claude 3.7 Sonnet Mar 2025 • Tools Enable parallel tool calls on Claude 3.7 Sonnet using batch tool meta-pattern workaround.

Claude 3.7 Sonnet may not make parallel tool calls by default even when enabled. This cookbook demonstrates a workaround using a "batch tool" meta-pattern that wraps multiple tool invocations, encouraging the model to call multiple tools simultaneously in a single response. By introducing a batch_tool that accepts an array of tool invocations, developers can improve latency and efficiency by processing multiple tool calls in parallel rather than sequentially.

Extended thinking Feb 2025 • Thinking Use Claude's extended thinking for transparent step-by-step reasoning with budget management.

This cookbook demonstrates Claude 3.7 Sonnet's extended thinking feature, which provides transparent step-by-step reasoning with budget management. Extended thinking enables Claude to show its internal reasoning process through thinking content blocks before delivering final answers. The guide covers setup, basic examples, streaming with thinking, token counting, redacted thinking, and error handling with practical Python code examples.

"okay, but I want Gemini3 to perform 10x for my specific use case" - Here is how

This content discusses strategies for optimizing Gemini 3 performance for specific use cases, achieving 10x improvements. It references prompt engineering best practices and introduces the Superdesign agent as a tool for implementation. The video likely covers techniques for tailoring large language models to particular applications through effective prompting and agent-based workflows.

AI Jason

Building custom Skills for Claude Oct 2025 • Skills Create, deploy, and manage custom skills extending Claude with specialized organizational workflows.

This cookbook guide teaches developers how to create, deploy, and manage custom skills for Claude that extend its capabilities with organization-specific workflows and domain knowledge. Custom skills are specialized expertise packages bundled as markdown files, scripts, and resources that codify organizational knowledge, ensure consistency, and automate complex workflows while maintaining privacy. The guide covers skill architecture, SKILL.md requirements, progressive disclosure for token optimization, and provides utility functions for skill management including creation, listing, and deletion.

Introducing Claude Opus 4.6

Claude Opus 4.6 represents a significant upgrade to Anthropic's flagship model, featuring improved planning capabilities, extended task focus, and enhanced autonomous operation. The model demonstrates smarter reasoning and better ability to maintain context over longer interactions. This upgrade positions Claude Opus 4.6 as a more capable AI assistant for complex, multi-step workflows and autonomous agent development.

Anthropic

[Repo] modelcontextprotocol/access: Infrastructure as Code for MCP access management

The modelcontextprotocol/access repository provides Infrastructure as Code (IaC) tooling for managing access control in Model Context Protocol (MCP) environments. Written in TypeScript, it enables declarative configuration and management of MCP access policies and permissions. This project facilitates secure, scalable access management for MCP-based AI agent platforms through code-driven infrastructure patterns.