anoman
Platform · Response Faithfulness

Know when your AI is making things up

Faithfulness scores whether a model's answer actually follows from the source you gave it — so you catch hallucinations and ungrounded claims before they reach a customer. Calibrated on English and Bahasa Indonesia.

What it is

A groundedness verdict on every answer

Retrieval-augmented and agent answers fail in a specific way: they sound confident but assert things the source never said. Faithfulness runs a multilingual natural-language-inference model that scores how well a response is entailed by its provided context, and returns a clear verdict. It measures groundedness against your source — it is not a general fact-checker — and it needs no extra LLM call, so it's cheap enough to run on every response.

The output

Three verdicts you can act on

Grounded

Every claim in the answer is supported by the source. Safe to serve.

Uncertain

The answer is partially supported or ambiguous — a good threshold to log, review, or ask for a citation.

Ungrounded

The answer asserts claims the source doesn't support — a likely hallucination. Flag, block, or regenerate.

Expected output

What a check actually returns

Source you provide

Anoman processes Indonesian customer data in Jakarta and bills in Rupiah. The free tier includes 500,000 weighted tokens per month.

Model answer

On the free tier you get 500,000 weighted tokens per month, and your data is processed in Jakarta.

Grounded — every claim traces to the source.

Model answer

The free tier includes 5 million tokens and your data is processed in Singapore.

Ungrounded — “5 million” and “Singapore” are not supported by the source (the unsupported spans are surfaced).

How it works

A real model, calibrated for the region

The signal is a multilingual NLI model that scores entailment between the source and the response — not a keyword match and not a mock. It's calibrated on an English + Bahasa Indonesia evaluation set (AUC 0.97 English, 0.999 Bahasa). It runs on the same in-region infrastructure as the gateway, so nothing leaves the region to score it, and it adds no provider cost.

Where you get it

Try it free, then run it on your traffic

Free tester — no signup

Paste a source and an answer and see the verdict live, in the browser. Nothing is stored.

Open the faithfulness tester →

On every response

As an opt-in signal on your own traffic — surfaced in your dashboard, scored in-region, with the raw score kept internal and a coarse band shown to you.

See the guardrail platform →

Catch hallucinations across every model, in every language

The same groundedness signal — on your own traffic, with data kept in-region and billed in Rupiah.