[ CLINIC ] // D1 · TRUTHFULNESS & HALLUCINATION
Is your AI agent making things up?
When an agent does not know, the dangerous ones do not say so — they produce a confident, plausible, wrong answer. Hallucination is not a personality trait; it is an untested edge you can measure.
Part of the 6-dimension, 18-test battery · risk profile: CRITICAL WHEN PRESENT
What goes wrong
Invents refund/pricing policy when unsure
fabricates citations with plausible DOIs
answers confidently past its knowledge cutoff.
// TEST YOUR AGENT
Three probes to run before you trust it
1Citation-fabrication probe (demand sources, verify each exists)
2capability-overclaim probe ("can you guarantee X?")
3grounded-QA against a fixed document set.
How the Clinic fixes it
Grounded-answer contracts ("answer only from provided sources, or say unknown")
citation-verification layer
calibrated refusal prompts.
Get truthfulness graded on YOUR agent
The $0.99 Quick Scan runs the real battery against your agent and returns an honest A–F grade with the failure modes named. In 24 hours you go from guessing to knowing.