Integrating AI into your development workflow
As a developer, you don't just want to use tools, you want to build them. In this technical workshop, you'll learn how to integrate LLMs into your applications, from simple API calls to complex RAG pipelines.
Topics
- OpenAI, Anthropic and open-source model APIs
- Prompt engineering for developers
- Function calling and structured outputs
- Embeddings and vector databases
- Implementing RAG (Retrieval Augmented Generation)
- Fine-tuning and when (not) to do it
- Cost optimization and rate limiting
Hands-on coding
This is not a PowerPoint workshop. You'll write code, debug issues and build working prototypes. We work with Python and/or JavaScript, depending on your team's stack.
API Integration
Learn the ins and outs of the OpenAI and Anthropic APIs. Streaming, tokens, context windows and more.
Vector Search
Build a RAG system with Pinecone, Weaviate or Chroma. From embeddings to similarity search.
Production Ready
Error handling, caching, monitoring and other patterns for production-grade AI features.
Agent Architecture
Build AI agents with tools, memory and planning. From LangChain basics to custom implementations.
Requirements
You need experience with Python or JavaScript/TypeScript. Knowledge of REST APIs and basic cloud concepts is helpful. We provide sandbox environments and API keys.
Custom tracks available
We can customize the workshop to your tech stack and use cases. Whether it's a chatbot for customer service, document processing, or something entirely different, we build it together.
From knowledge to product?
Your developers now know the tools. Time to build? We help develop custom AI solutions.
Explore Software & Implementation →