Routing Workflow - Stop over-engineering your AI automation: Episode 2
AI Agents are the talk of the town, and rightly so. They are incredible for unpredictable tasks. But for 80% of business automation, you're overcomplicating it. A simple, efficient LLM workflow is often the faster, cheaper, and more reliable answer.
There are times, and most of the times, where a simple automated workflow can do the trick in much lesser of cost & complexity. This series is intended to help you understand if your task fits any of the workflow template, rather than an AI agent.
Define your problem
Do you require a workflow which accepts a complex task, and then on the basis of the task, it understands which LLM can actually accomplish this task? If you need different LLMs for different tasks, and want to route the tasks accordingly, you can use this workflow.
Routing Workflow
Here your LLM acts as a router, which can understand the user request, and route it to the right kind of LLM or agent, that can answer your query.
When to use Prompt Chaining
This is the best way to create a workflow which can act upon various kinds of inputs coming in from the user. This kind of workflow is recommended where tasks are complex and are better handled by specific LLMs or a classification mode.
Some use cases
- Directing customer queries
- Routing easy questions to different LLMs to save costs
- Creating a personal assistant that can handle varied tasks by routing them to the right LLM.