The UI consistently exposes source attribution beneath answers: 5 visible examples show a "Sources referenced in this response" block, and the examples name the underlying file with counts such as 1/1, 1/2, and 1/3.

✓ Workedno artifactTest date not recordedCustomGPT
What was measured
Citation & source

Does it show which document the answer came from?

capability

What was given, what came back

Input — what we sent
No input — this is a capability finding
The observation is about the tool itself rather than one test input, so there is nothing to show on this side by design.
Output — unretouched
No output artifact
The verdict rests on the tester's written observation alone — no file was captured for this cell.
Provenance
Observation
50f4937d-3c24-4064-98f2-fd733296c20f
Evidence run
0b3c9935-df2f-4975-b5d4-cf2524c79671
Study
Build a Website Chatbot That Answers Questions From Your Knowledge Base
Research task
86b9jm3eg
Tested at
not recorded
Source
first-party
Evidence state
observed
Proof shown
no artifact
Cost / latency
not captured
Repeat run
not captured
Tester
not captured

The last three rows are honest blanks, not placeholders — our capture has no field for them yet.

Query this
get_evidence({
  tool: "customgpt"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 0 other tools
measured on Citation & source

No other tool was measured on this criterion for this input.

Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com