Fact-checking
Every answer, checked against its source.
A confidently wrong answer is the most expensive thing an LLM produces: a wrong number in a report, a fabricated fact to a customer, a decision made on invented data. The proxy fact-checks every response on the wire – before your app shows it to anyone.
The answer, marked up with what was caught.
Fact-checking that just says “suspicious” is useless to an editor or an engineer. Every finding here is specific: the exact figure that drifted from the source, the arithmetic that does not add up, the trend stated backwards, the claim the material cannot support – each tagged with which layer caught it.
Deterministic findings come from recomputation, not opinion. Judge findings quote the claim. The same report your reviewers see in the dashboard is recorded on the request, so an audit six months later shows exactly what was checked and what was found.
July revenue: $2.4M · August revenue: $1.8M · Prior quarter total: $4.6M
Combined July–August revenue was $4.5M1, and August alone reached $1.9M2. That’s up 14%3 on the prior quarter – the strongest stretch since the firm was founded in 17984.
- 1 Deterministic Arithmetic – 2.4 + 1.8 = 4.2 – the model said 4.5.
- 2 Deterministic Altered figure – August is $1.8M in the source, not $1.9M.
- 3 Deterministic Contradiction – “up 14%” but $4.6M → $4.2M is a decrease.
- 4 Judge Unsupported claim – “Founded in 1798” appears nowhere in the source.
An honest “I don’t know” or a clearly hedged estimate is never flagged – only unhedged certainty the source can’t support.
“Hallucination” is not one thing, so the proxy attacks it in layers – starting with checks that cost nothing and escalating only when a claim actually needs judgment or outside evidence.
Numeric grounding
zero model cost
Recomputes every arithmetic claim, flags figures that drift from the source, and catches directional contradictions – “up 12%” when the numbers went down. It runs inline, with no extra model round-trip.
Fact & consistency check
one guard-model call
A guard model catches what arithmetic can’t: internal contradictions, claims false by common world knowledge, and overconfident extrapolation. An honest “I don’t know” is never punished – only unhedged certainty without support.
Check against a source of truth
opt-in, priced per run
When a claim needs outside verification, ground it against an independent source – each sub-call metered into the request and the run.
- → RAG – your vector store (pgvector)
- → Web search – live results via Bright Data
- → Consilium – a second model as a critic
- → Private data (MCP) – check a claim against a private source Soon
Re-checked on every revision.
Research and reporting rarely fail at publication – they fail at revision. New data lands, sections get rewritten, and a stale figure or an edit-introduced contradiction slips into version three. Because every pass through the proxy is verified against current sources, re-checking an updated report is not a special workflow. It is just the next request.
Fact-checking for research & editorial →Verification beats model tier.
Each new frontier model tends to cost more than the last – and even frontier models are not 100% safe on hallucinations. Checking the output is what actually closes the gap, whichever model produced it. That is what makes a cost-effective model safe to run: the guarantees come from the checks, not the tier.
Pricing →How is this different from asking another LLM to review the answer?
The first layer is not an LLM at all: it recomputes arithmetic, matches every figure to the source, and checks stated directions against the underlying values – deterministically. Judges and retrieval only run on top of that, so the foundation of the verdict can never itself hallucinate.
Can it fix a wrong answer, not just flag it?
Where a safe fix exists, yes. In FIX mode wrong arithmetic is repaired in place before your app receives the response. Findings with no single safe rewrite – contradictions, unsupported claims – are flagged with the evidence, and PREVENT mode blocks them outright.
What happens when a report is updated?
Every revision that passes through the proxy is verified against its current sources, exactly like a first draft. Re-checking on update is the normal path – which is how stale figures and edit-introduced contradictions get caught before version three ships.
Does it punish the model for saying “I don’t know”?
The opposite. The fact-check judge is instructed to reward honesty: a hedged estimate or an explicit “I don’t know” is never flagged. Only unhedged certainty the source cannot support is.
What does fact-checking cost per request?
The deterministic pass adds no model tokens. Each opt-in layer – judge, RAG, web search, consilium – is metered, and every guard sub-call is priced into the request, so the dashboard shows the measured cost of checking on your own traffic.
Fact-check your own traffic.
Run in FIX mode and read the grounding reports – see what your models get wrong before you decide what to block.