Technique
Tool calling
Letting a model request a function call (search, code, an API) and use the result.
What should you learn before Tool calling?
- Deep learningMachine learning with many-layered neural networks.
- Tokens and tokenizationSplitting text into the units a language model reads and is billed by.
- TransformersThe attention-based neural network architecture behind modern language models.
- Large language models (LLMs)Transformer models trained on large amounts of text to predict the next token.
What to learn after Tool calling
- AI agentsAn agent is a model calling tools in a loop.
Connections to other concepts
- Related
- MCP
Read and watch: Tool calling explained
Practise Tool calling
- Intermediate Generative AI Interview Questions2 questions on Tool calling