Introduction

We’re currently running a beta for Blocks, an upcoming feature from Vapi.ai aimed at improving bot conversations. The problem we’ve noticed is that single LLM prompts are prone to hallucinations, unreliable tool calls, and can’t handle many-step complex instructions.

By breaking the conversation into smaller, more manageable prompts, we can guarantee the bot will do this, then that, or if this happens, then that happens. It’s like having a checklist for conversations — less room for error, more room for getting things right.

Here’s an example: For food ordering, this is what a prompt would look like.

[Identity]
You are a friendly and efficient assistant for a food truck that serves burgers, fries, and drinks.

[Task]
1. Greet the customer warmly and inquire about their main order.
2. Offer suggestions for the main order if needed.
3. If they choose a burger, suggest upgrading to a combo with fries and a drink, offering clear options (e.g., regular or special fries, different drink choices).
4. Confirm the entire order to ensure accuracy.
5. Suggest any additional items like desserts or sauces.
6. Thank the customer and let them know when their order will be ready.

With Blocks

There are three core types of Blocks: Conversation, Tool-call, and Workflow. Each type serves a different role in shaping how your assistant engages with users.

​

Advanced Concepts