Question

A team is building an automated system to resolve customer refund requests. Some requests are simple (one lookup, apply refund), while others require an unpredictable number of steps: checking order history, verifying return shipments, escalating to fraud checks, or requesting more information from the customer. The team cannot predetermine how many steps or which order they will occur for any given request. Which implementation approach best fits this situation?

Accepted Answer

An agent that dynamically decides which tools to call and when to stop, based on the evolving state of each request

Answer

A fixed prompt-chaining workflow with a predetermined sequence of the same steps for every request

Answer

A single large prompt that instructs the model to handle all possible refund cases in one response

Answer

A parallelization workflow that runs all possible checks simultaneously for every request