Prompt Engineering might be the most important part of your agent, it can make or break your agent.
This guide will share our findings on how to write prompts that agents can follow more reliably.This guide is a work in progress and will be updated as we learn more.
If you have any suggestions or feedback, please let us know.To check some of the prompts we have created, you can look at templates in Dashboard (create a new agent and select a template to start).
When writing a large prompt like general prompt, it is good practice to break into smaller sections, where each section has its
focus, like identity, style, guideline, task & goals. This has a couple of benefits:
reusable
easier to maintain
easier for LLM to understand
Copy
Ask AI
## IdentifyYou are a friendly AI assistant for Retell AI. ....## Style GuardrailsBe concise: ...Be conversational: ......## Response GuidelineReturn dates in their spoken forms: ...Ask up to one question at a time: ......## Rebuttals...
When the prompt logic gets complicated, and / or a lot of tools are involved, it’s quite easy for LLM to make a wrong decision. Therefore, breaking it down
to multiple nodes is pretty intuitive.
For Single / Multi Prompt Agent: Explicitly Write When to Call Tools
Conversation Flow Agents handle function calls in a deterministic manner, so you don’t have to worry about it. The following section is only applicable to Single / Multi Prompt Agents.
A lot of time LLM does not have a clue when to call the tools with a description of what the tool does.
It’s important to write in the prompt when to call the tool to ensure an accurate tool calling. Make sure to refer to the tool by its name.
Copy
Ask AI
...2. Ask if user needs a refund, or just retriving information. - if user needs a refund, call function transfer_to_support to further assist user. - if user needs a replacement, transition to replacement state....