AI logic controls many aspects of the behavior of a thunk.
Every step in a workflow has AI logic.
Assignment of steps to human agents can be based on AI logic.
Inbound requests via webhooks or email are processed using AI logic.
Custom AI tools are defined using AI logic.
Intelligent properties in content folders are defined using AI logic.
The logic in every one of these cases is defined using AI Instructions. Most people are familar with the concept of natural language prompts used to instruct an AI system. At the simplest level, an AI Instruction in Thunk.AI might be considered a “prompt”, but it has further structure and detail in order to steer and control the AI agents effectively.
In general, we would expect AI Instructions to start out high-level and brief when a thunk is initially created. As the prototype proceeds through testing and refinement, it is common that the AI instructions become more detailed and more restrictive. When a thunk moves into production mode, AI Instructions should be as “locked down” as possible to maximize reliability and minimize errors.
Directions
The directions are natural language prompts that describe the problem to be solved and how it should be solved. This section is required. The directions could have different levels of specificity. For example, here are a few different ways in which directions can be provided for a workflow step that needs to find the open working hours for a specific coffee shop.
“Find the open working hours for the shop”
“Find the open working hours for the shop. Check the operating procedure documents to find out how to do this.”
“Do a web search to find the open working hours for the shop”
“Use a Google places search to find the open working hours for the shop”
Each of these is a valid way to provide directions to an AI agent. Each has a different level of specificity and detail. There is usually a strong correlation between greater specificity and greater reliability.
The directions do not have to just include text. It is quite common to include links to relevant files (eg: “look at this spreadsheet file … to map expenses to internal accounting categories”)
Examples
AI Instructions can optionally include positive (what to do) and negative (what not to do) examples. AI agents are very good at following patterns, so the examples serve as patterns to share with the AI agent.
This is particularly useful for situations where an example is much easier to provide than a textual description:
When you need to provide an example of an input file
When you need to provide an example of an input file, annotated to indicate important sections or details
When you need to describe a desired result format.
Workflow State
Tool Configuration
Execution Settings