One search. Connected ideas.
Find the lesson, understand the concept, and prepare your answer.
13 results shown · grouped by type
Lessons5
Once facts are validated, the rules engine evaluates the current workflow state and chooses the permitted next step.
A workflow can be represented as a graph:
Another useful architectural distinction is between a workflow engine and the application that uses it.
My biggest learning is that AI understanding and business control should be separate concerns.
A multi-turn workflow needs a reliable memory of what has happened. That is different from merely sending the whole chat history back to an LLM.
Interview questions5
Once facts are validated, the rules engine evaluates the current workflow state and chooses the permitted next step.
A workflow can be represented as a graph:
A multi-turn workflow needs a reliable memory of what has happened. That is different from merely sending the whole chat history back to an LLM.
Another useful architectural distinction is between a workflow engine and the application that uses it.
My biggest learning is that AI understanding and business control should be separate concerns.
Modules3
Deterministic AI Workflows learning module
Deterministic AI Workflows learning module
Deterministic AI Workflows learning module