Function calling (tool use)

Function calling lets a language model request that your code run a defined tool, such as a database query, and use the result.

Written by Reflective Data experts · updated Oct 5, 2026

You describe the tools and their inputs; the model decides when to call them and with what arguments; your system executes them safely and returns the output. It is how assistants become agents.

Validate arguments and restrict permissions: the model is not a trusted caller.

Agent harness AI agent Model Context Protocol (MCP)

// how we can help

We build company brains, agent harnesses and AI bots on top of data you can trust. AI services → · The data platform behind it

Model drift

Model drift is when an AI or machine learning system gets worse over time because the…

context-window.md

Context window

The context window is the amount of text a language model can consider at once, including…

multi-agent-system.md

Multi-agent system

A multi-agent system uses several AI agents with different roles that collaborate on a task.

vector-database.md

Vector database

A vector database stores embeddings and quickly finds the ones most similar to a query.

ai-observability.md

AI observability

AI observability is tracking what an AI system does in production: inputs, outputs, tool calls, cost,…

ai-governance.md

AI governance

AI governance is the set of policies, roles and controls that make sure AI is used…

← full analytics dictionary