What is a hallucination in an AI agent?

A hallucination is an agent stating something its sources don’t support.

In a trace it usually looks unremarkable. The agent retrieves a chunk, cites it, and reports a value that chunk doesn’t contain. The tool call returned 200, the LLM span closed OK, and nothing structural in the run marks it as a failure. Finding it means reading the output against the context it was given.

Which stage broke, retrieval or generation, is what faithfulness, groundedness, and context presence separate. Why the model does it at all is a different question.

keep reading

More on this.

Why do AI agents hallucinate?A language model generates the most probable next word, not a verified one, so it produces fluent text whether or not anything backs it, unless something forces it to check.answer →Why does an AI model make up an answer instead of saying it doesn't know?Because the tests it's graded on score a confident guess the same as a right answer, and score 'I don't know' as a guaranteed loss, so guessing wins.answer →Why does a wrong answer often look just as confident as a right one?Nothing about how an answer reads reveals where it came from; a number pulled from the wrong source is written in the same fluent, certain sentence as one pulled from the right one.answer →Everything on hallucinationsThe definition, and every question answered under hallucinations.concept →

Two ways to run Tessary.

Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.

Tessary Cloud

We host it for you. Send your first trace with nothing to deploy and no model key.

what's includedper organization
traces
10,000 per calendar month
stored trace data
1 GB
retention
30 days
model credit
$10, one-time, for triage and root-cause analysis
credit card
not required
start for free

Self-hosted Tessary

Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.

Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md

docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y