The Multiverse School

You'll learn to build prompts and agentic applications with Python, master context engineering techniques, and develop advanced AI integration skills for technical applications.

- Effective persona targeting - AI-assisted campaign design - Scenario.io or ComfyUI for creative generation (with non-AI alternatives!) - Automated Creative Production - Reply Bots - Sock Puppet Account Fundamentals

- How to build agents using the ReACT pattern (Reason, Act, Observe) - Request-response agents with Claude Agent SDK and OpenAI Agents SDK - RAG implementation with FAISS and pgvector for retrieval - Building your own minimal agent framework (~140 lines of code) - Multi-agent coordination patterns (sequential, parallel, hierarchical) - Framework comparison: Autogen, LangGraph, OpenAI Swarm - When to use agents vs. simple prompts and common pitfalls

-Segmentación efectiva de personas objetivo -Diseño de campañas asistido por IA -Scenario.io o ComfyUI para generación creativa (¡con alternativas sin IA!) -Producción creativa automatizada -Bots de respuesta -Fundamentos de cuentas de títere (sock puppet

You'll configure an AI assistant with persistent memory and preferences, then put it through critical thinking boot camp. Learn to write prompts with specific evaluative criteria that get consistent results, practice divergent thinking exercises to offset AI's tendency to narrow creativity, and question your own assumptions about story, character, and style. Build a complete story framework using the Story Circle method, develop distinct character voices, and create a Director system that orchestrates multiple AI agents like a creative team. Master the art of managing artificial collaborators - knowing when to trust their output, when to push back, and how to maintain your unique creative voice. By the end, you'll have working character agents that can write full scenes in your style, plus the critical thinking frameworks to keep improving them. Perfect for writers who want AI superpowers without becoming generic.

- How to automate the entire SDLC with AI agents - Techniques for making AI agents feel natural in your workflow - Moving beyond test generation to full process automation - Strategies for shipping well-tuned processes instead of org charts - How to avoid common pitfalls when integrating AI into development

- Scope down issues to actionable data - Identify decision-makers and civic structures - Package data into clear one-pagers - Craft distinct pitches for officials and media - Use AI tools for data analysis - Map coalitions and organize turnout - Plan sustainable 90-day campaigns

- Working Meshtastic mesh network (bring a friend or multiple nodes - mesh networking requires 2+ devices) - Local WiFi-hosted information hub - Solar-powered field node prototype - Resilience blueprint for scaling from garden to commune to neighborhood **Note:** Building a mesh network requires multiple nodes. We recommend either bringing a friend to the workshop or purchasing 2+ Meshtastic devices.

- How to build agents using the ReACT pattern (Reason, Act, Observe) - Request-response agents with Claude Agent SDK and OpenAI Agents SDK - RAG implementation with FAISS and pgvector for retrieval - Building your own minimal agent framework (~140 lines of code) - Multi-agent coordination patterns (sequential, parallel, hierarchical) - Framework comparison: Autogen, LangGraph, OpenAI Swarm - When to use agents vs. simple prompts and common pitfalls

You'll learn to build prompts and agentic applications with Python, master context engineering techniques, and develop advanced AI integration skills for technical applications.

- Write effective system prompts for regularized outputs or tool use - Design and implement agents capable of using, creating, and managing tools - Develop agents with autonomous action capabilities, including scheduling and event-triggered responses - Utilize open-source tool hubs designed for Large Language Models - Manage and economically host large vector stores - Construct self-improving agents that can evolve their prompts - Create and manage swarms of agents collaborating on complex goals - Design meta-swarms and information hierarchies for advanced agent collaboration and secrecy - Evaluate and create benchmarks for LLM performance analysis