← All agent examples
Test your Q&A answers against a question set
Upload or paste a CSV of questions with the answers you expect. For each question the agent retrieves passages from your knowledge base, answers from them, and has a judge score the answer for correctness against your expected answer and for faithfulness to the passages. You get a summary of the failures to fix in your documents or prompts.
Engineering and IT
Customer support
evaluation
test set
Q&A testing
RAG evaluation
answer quality
regression test
judge
knowledge base
CSV
loop
How it starts
When you run it.
Accepts files: Questions and expected answers as CSV (optional, or paste them)
What it needs
- Document source — The documents your Q&A answers from. Upload files to it after the agent is created.
- Knowledge base under test — The knowledge base whose answers are tested.
Steps
Read the question set
Prompt Call
Test each question
For Each
For each item:
Retrieve passages
Retrieval
Answer the question
Prompt Call
Judge the answer
Prompt Call
Keep the result
Item Value
Summarize the failures
Prompt Call
Show the test report
Display Result