AI agent
KI-Agent
An LLM that can take actions: it plans, calls tools, looks at the results and decides the next step until a goal is reached.
01In short
An LLM that can take actions: it plans, calls tools, looks at the results and decides the next step until a goal is reached.
In productionEvery tool an agent can call is a permission. Scope it, log it, review it.
02Video
slot · videoAI agent in 90 secondsadd: GUIDES['ai-agent'].video
03Guide
slot · guide
A step-by-step guide for “AI agent” goes here. Suggested outline:
- What it is — in one paragraph
- Why it matters in production
- How to do it — 3 to 7 steps
- Pitfalls we see in the field
04Checklist
slot · checklist
Four to eight things a team can tick before go-live.
05FAQ
slot · FAQ
The three questions clients actually ask about “AI agent”.
06Related terms
AgentsTool callingA model’s ability to request a defined action — query a database, send an email, call an API — with structured arguments that your code executes.SecurityLeast privilegeGive a system only the permissions its task needs — read-only unless writing is the job.AgentsHuman-in-the-loopA person reviews or approves at defined points before the system acts.
Where we help · Build