P6 Create the Evaluation Suite

← Demo D3

NOTE: This phase evaluates the performance of the LLM output. Its not required to get the demo working. I might add it later.

In this phase 6 you will

• xxxx

For details see:

• Speedrun (the original demo documentation)
  • Section “Evaluate your agent”
• #614_.docx

The following diagram shows what you create:

P4

TOC:

• xxxxx

26.0902 (v1 26.0831)