← Back to journey
11 May 2026•2 min read

LLM workflow types [Part 2]

They types of worflows LLMs use to get your desired result

workflowsclaude-aiprompt-chainingroutingorchestratorparallelizationeval-optimizor

Workflow types

Types of workflows

  1. Prompt Chaining
    • Sequential. Output of 1 LLM is used as input of the next.
  2. Routing
    • Using an LLM to determine where a task goes. Allows a task to be handed over to a specialized LLM.
  3. Parallelization
    • Having LLMs work simultaneously on a task, then having their results brought together by an aggregator.
  4. Orchestrator-Worker
    • Having a master LLM, which controls sub-LLMs. These sub-LLMs work on sub-tasks that the master creates and delegates.
  5. Evaluator-Optimizer
    • Having 1 LLM to process your input, then passes the result to a 2nd LLM to check the result against a checklist/criteria/standard. If needed, it will pass the feedback from the check back to the 1st LLM to reprocess - now with feedback to consider.

Agents

Agents can be used for open-ended problems where it’s difficult or impossible to predict the required number of steps, and where you can’t hardcode a fixed path. The LLM will potentially operate for many turns, and you must have some level of trust in its decision-making. Agents’ autonomy makes them ideal for scaling tasks in trusted environments.

The autonomous nature of agents means higher costs, and the potential for compounding errors. We recommend extensive testing in sandboxed environments, along with the appropriate guardrails