Agentic workflow
An agentic workflow is a software process in which one or more LLM-driven agents drive the work, making decisions and invoking tools at each step rather than following a hardcoded script. Agentic workflows replace deterministic pipelines for tasks too varied for explicit programming but too repetitive for human handling.
The category covers a wide range: a code-review bot that decides whether to approve a PR, a customer-support agent that resolves a ticket through a knowledge base, a data-analysis assistant that builds a dashboard from a natural-language brief. The defining property is that the agent decides the steps at runtime based on the input and intermediate results, rather than executing a predetermined script. The right adoption pattern is to start with high-determinism workflows (the agent has narrow latitude) and expand autonomy where the historical accuracy supports it. Observability and human-in-the-loop checkpoints are universal requirements for production agentic workflows.
Related terms
- Autonomous agent
An autonomous agent is an AI system that pursues a goal over multiple steps with minimal human intervention — deciding what actions to take, executing them via tools, observing results, and iterating until the goal is achieved or judged unreachable.
- Multi-agent system
A multi-agent system uses multiple LLM-driven agents working together — typically with role specialisation (planner, executor, critic) or domain specialisation (researcher, coder, writer).
- Tool use (LLM agent)
Tool use is the LLM-agent pattern in which the model has access to a defined set of tools — read file, search web, run code, query API — and decides which to invoke and with what arguments based on the user's request and the current state.