From prompts to agents
Build AI systems that use tools, search for information, and complete multi-step tasks autonomously.
This advanced pathway covers the edge of where practical AI has gotten to. It's about giving language models the ability to use tools and work autonomously on complex tasks.
We start with tool use - teaching AI to call functions, query databases, and interact with external systems. Then we move to agents, which as Simon Wilison puts it are LLMs calling tools in a loop to achieve a goal.
We use these techniques everyday in our work. They're hard! And it's hard to put them together in a pathway that feels useful. We've tried to focus on practical patterns that work reliably in production, but - as you'll probably know if you're looking at this pathway - things are changing quickly.
This pathway assumes you are comfortable with Python, APIs, and have completed the "API Loops" pathway or have equivalent experience.
Before you start
- •Completed "API Loops and Programmatic AI" pathway or equivalent experience
- •Comfortable with Python including async/await patterns
- •Understanding of REST APIs and JSON
- •Experience with at least one LLM API (OpenAI, Anthropic)
- •Willingness to debug and iterate on complex systems
What you will achieve
- ✓Build AI systems that use external tools and data sources
- ✓Create autonomous workflows that complete multi-step tasks
- ✓Deploy user-facing AI applications
- ✓Understand the current frontier and limitations of AI agents
Learning path
Tool use foundations
Give AI the ability to call functions, query data, and interact with external systems.
Estimated time: 4-6 hours
After this stage, you will be able to:
- ✓Implement function calling with Claude or GPT
- ✓Build AI assistants that query live data
- ✓Combine multiple tools in a single conversation
Autonomous workflows
Chain AI capabilities together into workflows that run without human intervention.
Estimated time: 4-6 hours
After this stage, you will be able to:
- ✓Build end-to-end automated workflows
- ✓Chain different AI models for different tasks
- ✓Handle errors and edge cases in autonomous systems
User-Facing applications
Build AI-powered applications that your team or service users can interact with.
Estimated time: 5-7 hours
After this stage, you will be able to:
- ✓Deploy AI interfaces for non-technical users
- ✓Ground AI responses in your actual content
- ✓Build reliable production systems
Advanced patterns
Sophisticated techniques for complex real-world problems.
Estimated time: 4-6 hours
After this stage, you will be able to:
- ✓Handle complex multi-document analysis
- ✓Use AI for strategic and analytical thinking
- ✓Build predictive systems that inform decisions
Multi-document analysis and comparison
AI as strategic thinking partner
Predictive routing based on complex inputs