Book a call

Daniel & Friends / Glossary / AI agent

AI and automation

AI agent

An AI agent is a system that uses a model to reach a goal step by step: it plans, calls tools and adjusts its approach based on the results.

Daniel Votruba ·


In practice

Give an agent tasks with a clear goal and a checkpoint where a person approves the result.

Read more: AI agents in marketing: what genuinely works in 2026

Related terms

  • MCP (Model Context Protocol): MCP is an open protocol from Anthropic that standardises how AI models connect to tools and data.
  • AI automation: AI automation is the use of models inside working processes, for example sorting enquiries, preparing proposals or reports, to save repetitive work.
  • Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
  • RAG (retrieval-augmented generation): RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them.

More terms in the group AI and automation

Agentic AI · AI costs and limits · Voice cloning · AI crawlers (GPTBot and others) · Vibe coding · AI governance · Vector database · AI personalization · Token · AI safety and alignment · Text-to-video · AI scoring · Text-to-speech (TTS) · AI SDR · Text-to-image · AI search (answer engines) · Temperature · AI slop · System prompt · AI workflow and orchestration · Speech-to-text · Automation platforms (Zapier, Make, n8n) · Small language model (SLM) · C2PA and content provenance (AI watermarks)

Full glossary (590 terms)

Terms in practice

Need help putting them to work?

Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.

Book a call

Enjoyed the article? Share it with friends.