During the design process, the AI planning agent assists the thunk owner/admin to create and modify a thunk. There are six phases of the design process:
Initial specification of intent
Intelligent planning of prototype
Advanced configuration options
Iterative adaptation
Intelligent tuning
Lockdown for production
Initial specification of intent
The owner/admin uses concise natural language instructions to initially describe the desired workflow. This launches AI agent tasks to generate an appropriate workflow plan and appropriate state management data structures.
When you open the “Data” view of the thunk (click on it in the left control pane in the Run section), you will see a familiar tabular view of all the running workflow instances. If you move the mouse over the column headers, you will see a properties menu (“three vertical dots”) which allows you to view the Column Properties. This is where you can see and change the definition of each state property, you can add new columns, and you can delete existing columns.
While the initial state is defined automatically as part of workflow planning, the thunk owner can modify and refine the state definition as described in the section on Workflow State.
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.
Intelligent planning of prototype
The AI planning agent guides the owner/admin through various stages of more detail until an initial working thunk is created.
When a thunk owner creates a new thunk, they provide initial high-level planning instructions. Guided by these instructions, their AI planning agent builds out a workflow plan that has a sequence of steps to execute the process. While the AI planning assistant automates the creation of the workflow plan, the thunk owner can always change any aspect of the plan.
Advanced configuration options
Iterative adaptation
Intelligent tuning
Lockdown for production
There are various additional design options
The owner/admin may describe content folders to build. This launches AI agent tasks to automatically construct and initialize the content folders, and create the appropriate retrieval indexes.
The owner/admin may describe custom AI tools to build. These requests also launch AI agent tasks to automatically build the tools.
The owner may establish connections to external business applications, import AI tool libraries, and modify the various settings that control AI agent behavior.
The owner/admin may add and manage human agents and end users who have access to the thunk.
At any time during the design phase, the owner/admin can interact with the AI planning agent, providing instructions or seeking guidance.
Usually, the design phase of a thunk involves iterative authoring, testing, and evaluation -- all of which are natively supported in the Thunk.AI platform.