Agents state claims their context does not support, and the trace of a wrong answer looks identical to a right one.
A confident wrong answer traces identically to a right one. Evaluate every run for groundedness against the agent's sources, and hallucinations surface as failed verdicts instead of user complaints.
Rarely nonsense. Usually competence: fluent, specific, and wrong.
A customer asks about returns outside the window, retrieval finds nothing relevant, and the agent generates a plausible policy. The customer now has the wrong terms in writing.
A booking API times out and the agent, mid-conversation, reports success anyway. Nothing was booked, and the failure surfaces days later as a person the system let down.
No error was thrown and no log line turned red. A hallucinated answer traces identically to a correct one, which is why nobody knew until a user did.
After one visible incident, staff double-check every agent answer and adoption stalls. A failure rate of a few percent sounds small until it is multiplied by daily volume, and on member data, legal, or financial topics each wrong answer carries liability.
Trace hallucinated runs back to the moment the claim appeared and the causes rank consistently.
The most common cause. The agent needed information, retrieval returned nothing or the wrong passage, and the model filled the gap, because generation always produces something.
Most prompts say what to do; few say what to do when the context does not contain the answer. Without an explicit instruction to say so, refusal loses to fabrication.
An empty result read as success, an error payload read as data, a partial result read as the whole answer. The fabrication happens at the interpretation step and compounds through everything downstream.
Long sessions push early constraints out of the window, and the agent answers from the conversation's drift rather than its facts. The model itself is the last cause to suspect, and usually the first to be blamed.
Reading transcripts finds the failures you already expected. Prefactor evaluates every run instead.
Every run recorded with the context the agent had. Retrieved documents, tool results, and the final answer land in one record as the run happens, per agent and per version.
Every claim checked against the agent's sources. Each run is evaluated for groundedness against the context it had and the job it was given. An unsupported claim fails the run, however fluent the answer.
The rate, per agent and per version. Failed verdicts roll up into a hallucination rate, so a regression after a prompt or model change shows as a trend that alerts, not a complaint that arrives weeks later.
A failed verdict is the start. The loop keeps the answer from shipping and the cause from returning.
Hold the answer before it ships. Runs on sensitive topics, member data, legal, financial, can be held for review before the user sees the answer, and a failed verdict routes to a person while it is one run, not a pattern.
Fix the cause the record points to. A failed run shows what was in context at the moment of the unsupported claim: a retrieval gap, a silent tool error, a prompt with no instruction for missing answers. Each caught case becomes a regression test.
Changes ship against the evidence. Prompt and model changes run against the growing set of caught cases, and the live rate per version shows whether the fix held. A change that moves the rate up is a failed deploy, on record.
A support agent quoted a 60-day refund window; the policy says 30. The run completed cleanly, but the groundedness verdict failed it: the claim had no source in the retrieved policy. The answer was held, a reviewer sent the correct terms, and the retrieval gap behind it was patched and added to the test set. Illustrative, but this is the standard shape of a caught hallucination.
Wrong answers are what stall adoption. A hallucination rate that falls, and stays fallen, is what brings users back.
See the solution →Heads of AIA rate per agent and per version, so "are the agents okay" is answered with a trend, not an anecdote.
See the solution →Security & governanceSensitive-topic runs held for review before the answer ships, with a record of every verdict for the questions that follow an incident.
See the solution →Book a demo and we will evaluate runs like yours for groundedness: every claim checked against its sources, a rate per agent and per version, and sensitive answers held for review.
Prefactor helps teams observe, evaluate, and improve their AI agents in production, across every framework and provider.