Agentic AI
Articles about using small language models as specialized agents in agentic workflows.
Demo
Building a Local Agent for Email Classification Using distil labs & n8n
A 0.6B email classifier that auto-labels Gmail locally. 93% accuracy from 154 seed examples. Runs on localhost via Ollama + n8n.
ClassificationAgentic AI
Read more →
Demo
GitAra: How We Trained a 3B Function-Calling Git Agent for Local Use
A 3B function-calling model that turns plain English into git commands. Matches the 120B teacher at 92% accuracy — 25x smaller, runs locally via Ollama.
Tool CallingAgentic AI
Read more →
Guide
Small Expert Agents From 10 Examples
How the distil labs platform turns a prompt and a few dozen examples into a small, accurate expert agent — 50-400x smaller than LLMs.
Agentic AIClassification
Read more →
Guide
Small Models, Big Wins: Using Custom SLMs in Agentic AI
Agentic systems don't need an LLM everywhere. When to use SLMs vs LLMs, common use cases, and the decision framework.
Agentic AI
Read more →