---
title: "EMBER: Check every claim in a document | Aicadium"
description: EMBER checks every claim in a document against credible external evidence, marks how much you can rely on it, and tells you what to fix.
---

[![Aicadium](https://landing.aicadium.ai/hubfs/Aicadium_blue_logo.svg)](https://landing.aicadium.ai/?hsLang=en) [Get in touch](https://landing.aicadium.ai/contact?hsLang=en)

EMBER: Documents you can stand behind

15 min read

What we believe

[What we believe 1](https://landing.aicadium.ai/every-claim-checked#believe) [The framework 2](https://landing.aicadium.ai/every-claim-checked#framework) [In action 3](https://landing.aicadium.ai/every-claim-checked#in-action) [Predictions 4](https://landing.aicadium.ai/every-claim-checked#predictions) [Why now 5](https://landing.aicadium.ai/every-claim-checked#why-now) [The series 6](https://landing.aicadium.ai/every-claim-checked#series)

[![Aicadium](https://landing.aicadium.ai/hubfs/Aicadium_blue_logo.svg)](https://aicadium.ai/)

- Company
  
    - [About us](https://aicadium.ai/company/)
    - [Our story](https://aicadium.ai/company/#our-story)
    - [Life at Aicadium](https://aicadium.ai/company/#life-at-aicadium)
    - [Leadership team](https://aicadium.ai/company/#leadership-team)
    - [Our people](https://aicadium.ai/company/#our-people)
    - [Careers](https://aicadium.ai/company/#join-us)
- [Projects](https://landing.aicadium.ai/ai-transformation-projects?hsLang=en)
- Resources
  
    - [All resources](https://aicadium.ai/resources/)
    - [Blog](https://aicadium.ai/resources/articles/)
    - [Use cases](https://aicadium.ai/resources/use-cases/)
    - [Downloadables](https://aicadium.ai/resources/downloadables/)
    - [Newsroom](https://aicadium.ai/resources/in-the-news/)
    - [Videos](https://aicadium.ai/resources/videos/)
- [Contact](https://aicadium.ai/contact/)

For every claim that travels from a report into a decision

# You become accountable for a claim the moment you use it.

A completed document doesn't mean an accurate document. Confident prose, correct grammar, tidy citations and a credible-sounding source or author can lead to more trust in a document than warranted. **EMBER** checks each claim against credible external evidence, ranked by how authoritative it is, then marks every claim with how much you can rely on it and tells you what to do about the ones that fall short.

The numbers behind the problem

## **AI makes content easy to create.** Even when generation outpaces review, accountability stays with whoever publishes it.

1 in 4

citations generated by GPT-4 contained substantive errors, and a further 18% did not exist at all

A genuine-looking reference is not proof of a true claim. The source can exist and still not say what the document says it says.

[Walters and Wilder, Scientific Reports, 2023 (636 references across 42 topics)](https://www.nature.com/articles/s41598-023-41032-5)

66%

of AI users rely on its output without evaluating accuracy

More than half say AI has already caused them to make mistakes at work. The check is being skipped at the point where it would cost the least.

 

[University of Melbourne and KPMG, Trust, attitudes and use of AI: a global study 2025 (48,000 people, 47 countries)](https://kpmg.com/xx/en/our-insights/ai-and-technology/trust-attitudes-and-use-of-ai.html)

88%

of organisations now use AI regularly in at least one business function, up from 78% a year earlier

AI is already in the reports, decks and memos moving through your organisation. The question is no longer whether it is there, but whether anyone has checked what it produced.

[McKinsey, The State of AI 2025 (1,993 respondents, 105 countries)](https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai-2025)

What we believe

## Three convictions about the documents organisations publish and rely on.

CONVICTION I

### A finished document is not a checked document.

Fluent prose and a tidy reference list show the writer was confident. They show nothing about whether the claims hold, whether you wrote the document or someone handed it to you.

CONVICTION II

### Reading is not verifying.

A careful reader can catch a claim that sounds wrong.  Catching wrong claims that seem right on the surface takes close scrutiny, time, and effort, which makes them often fall through the gap. Once a document is published or relied on, the organisation bears responsibility for every claim in it, whether or not anyone saw the evidence.

CONVICTION III

### The risk moves with the claim, not with the author.

A statistic travels from a report into a deck, and from the deck into a decision. Each time it moves, the person using it inherits the risk, and almost never the evidence. The only check that closes that gap is one anyone in the chain can run, and anyone can read.

The framework

## The claim-level verification that makes a document **defensible.**

**EMBER stands for** **Evidence Mapping and Benchmarking of Existing Research.**   
A user hands a document to EMBER, and it determines what the document claims, checks each claim against sources outside the document, and returns the original text with a marker outlining for every claim what's supported or not and why, and how to remediate it.  EMBER shares its trust infrastructure with [SPARK](https://landing.aicadium.ai/ai-research-you-can-trust?hsLang=en).

The difference is the input: SPARK verifies research as it writes it, EMBER verifies a document that already exists.

E

Evidence

Every claim is tested against sources the document did not choose.

M

Mapping

Each verdict sits on the exact sentence it applies to.

B

Benchmarking

Claims are held to a fixed, documented standard, not a reader's instinct.

E

Existing

Checks the document you have. It does not write a new one.

R

Research

Any report, memo, guide or deck that makes verifiable claims.

Five things for documents you can trust

## Don't just read the report. Check the receipts.

Most documents expect the reader to take the author's word for it. EMBER holds each claim up against credible external evidence, ranked by how authoritative it is, so the verdict rests on the strength of the sources rather than the confidence of the writer. Five checks run on every document.

01

"What is this document actually asserting?"

Claim Extraction

EMBER extracts every verifiable factual claim and quotes the exact words it came from. Each claim is checked once, even if the document repeats it. Opinions, framing and statements that cannot be tested are left unmarked. If a passage has no marker, it makes no claim that can be checked.

02

"Does credible evidence back this up?"

External Grounding

EMBER checks each claim in three ways. It looks at the source the document cites, to see if it says what the document says it does. It then looks for independent evidence, giving more weight to primary documents and official data than to commentary. If nothing outside the document can be found, it informs the reader.

03

"How do I read it at a glance?"

Four Trust Tiers

Each marker is one of four tiers. A tier describes the claim's relationship to the evidence, not the author.

**Verified**: independent sources support the claim as written.   
**Caution**: support exists but is thin, or the framing needs a caveat.   
**Contested**: credible sources disagree with the claim or with each other.   
**Unverified**: no external evidence found, so the claim rests on the document's own word.

04

"Does the cited source say what the document says it does?"

Citation Fidelity

Where the document cites a source, EMBER checks whether that source supports the sentence it is attached to. A real reference can still be miscited, broken or weakly sourced. These are flagged separately, so a claim can be true and still carry a citation problem.

05

"What do I do about it?"

Remediation Brief

A prioritised list of what to fix and how. Each item names the claim, what is wrong, what to do about it, and how much effort the fix will take. Factual errors get a correction. Disputed framing gets a clarification. Unverified claims get a request for the source. The sorting is already done, so the list can be worked through as it stands.

EMBER in action

## See EMBER run, and what comes back.

See It Run

Read The Report

### From a document to a verdict on every claim.

- 1**Hand over the document to EMBER**Upload the document and ask EMBER to ingest it. It becomes a text file with every word kept verbatim, and every link and footnote recovered.
- 2**Type the trigger phrase.**In a fresh chat, "EMBER Verify on \[document\]" is the entire instruction.
- 3**EMBER returns two files.**Every run returns the HTML report you read and a fact file that records every claim, verdict and score.
- 4**Read the report.**Click any marker to see the evidence EMBER found, how it scored the claim, and what to do if the claim does not hold.

### The report is your document, with the evidence attached.

- 1**Executive summary**How many claims were checked and whether the document is safe to rely on. Which parts to quote freely, and which to check first.
- 2**Verification summary**How many claims landed in each tier, and how many citations were broken or pointed to the wrong evidence. Click a tier to list its claims.
- 3**Remediation brief**The to-do list prioritises the most serious items first. Each entry specifies the claim, the issue, the required action, and the estimated effort.
- 4**Quality scorecard**How much of the document was covered, and whether every link and check passed. If coverage is high, the verdicts can be taken at face value.

![Read The Report](https://landing.aicadium.ai/hubfs/ember_report_mock_9x16_v2.png)

Three Predictions

## What we expect to be standard practice by 2027

### "Has this been checked?" becomes a standard question before a document goes out.

Not "who wrote it" or "does it look right", but whether the claims in it have been tested against sources outside the document. The teams that can answer this will find their documents move faster.

### A trust summary becomes something readers expect to see.

A document comes with a record of which claims were checked, which were held, and which still need work. Without that record, a reader has only the author’s confidence to rely on. The record remains with the document, whether it is sent or received.

### Every revision gets checked, not just the first draft.

The version that goes out is rarely the version that was reviewed. Figures get updated, paragraphs get added, and the second read is lighter than the first. Checking the revision becomes as routine as checking the original.

Why this matters now

## Most documents get a skim and a gut check. **EMBER applies the same level of scrutiny to every claim.**

Without EMBER

A few claims

the ones that looked wrong or that you happened to know about

- Checking rests on whichever reader has time, and their instinct for what looks off
- Citations are trusted because they exist, not because anyone opened them
- Claims outside your expertise get taken on the author's word
- No record of what was checked, so the next reader starts again
- The revised version gets the same skim, or none

→

With EMBER

Every claim

tested against the same standard, whoever the reader is

- Every checkable claim is extracted and quoted verbatim, so nothing depends on what caught the eye
- Each claim tested against sources the author did not choose, ranked by authority
- Every citation opened and checked against the sentence it supports
- A report that records what was checked, what held, and what to fix
- One trigger phrase to run it again on the revised version

Voices from the field

## What the first people to run EMBER told us

Early feedback from our own team, who put EMBER to work on real documents before anyone outside Aicadium did.

“

We ran it on a guide we'd already published, and it caught figures that had quietly gone out of date since we wrote it. The remediation brief told us which ones to correct and which just needed a date on them. The fixes took an afternoon, and the guide went back out with stronger sources than it started with.

M

Marketing practitioner checking outbound content

“

Numbers from reports are sometimes used in briefings and decks, usually without the report attached. EMBER tells me which ones can travel and which ones shouldn't leave the document. For the ones that can, it also gives me the source, so when someone asks where a figure came from, the answer is already there

S

Senior stakeholder reviewing incoming reports

Part of the SPARK series

## SPARK checks the research you generate. EMBER checks the documents you publish and receive.

Both sit on the same trust infrastructure: similar scoring methodology, overlapping trust tiers, and the same insistence that every claim carries its evidence. SPARK came first. People who saw it asked whether the same standard could be applied to documents that already existed, their own and other people's. EMBER is the answer to that question.

 

|  | **SPARK** | **EMBER** |
| --- | --- | --- |
| Who uses it | Researcher | Reviewer, of your own document or someone else's |
| Why it is used | To generate verified AI research for a topic | To verify claims in any existing documents |
| How claim-level trustworthiness is tiered | Three trust tiers: Verified, Caution, Contested | Four trust tiers: Verified, Caution, Contested, Unverified |
| When to run it | Use it to create the initial report, and refresh it any time the world changes | Single point-in-time verification of a report |
| What it outputs | Source report and fact file | Annotated original with remediation brief |

 

 

The series

## Read more about EMBER

### [![Five questions to ask before a statistic leaves the report it came from](https://landing.aicadium.ai/hubfs/AdobeStock_728791504.jpeg) Explainer Five questions to ask before a statistic leaves the report it came from Generation now outpaces review, but accountability stays with whoever publishes. Five questions decide whether a figure can be reused, with or without the tool. How EMBER checks claims →](https://aicadium.ai/verify-statistics-before-reuse/)

### [![Four kinds of document that deserve a check, and what to look for in each](https://landing.aicadium.ai/hs-fs/hubfs/AdobeStock_2025248998.jpeg?width=400&height=200&name=AdobeStock_2025248998.jpeg) Use Case Examples Four kinds of document that deserve a check, and what to look for in each Polished, footnoted, fluent, or once-accurate: why every document looks trustworthy, and how to tell which check it actually needs. Check before you trust →](https://aicadium.ai/when-to-fact-check-a-document/)

### [![We built a tool that checks every claim in a document. Here's how it works.](https://landing.aicadium.ai/hs-fs/hubfs/AdobeStock_2086356839.jpeg?width=400&height=200&name=AdobeStock_2086356839.jpeg) Insights We built a tool that checks every claim in a document. Here's how it works. Why we built a tool to check every claim in a document, what the five checks look for, and how the first results held up. Read the full story →](https://aicadium.ai/we-built-a-tool-that-checks-every-claim-in-a-document/)

### Ideas like this shape how we work at Aicadium

Get updates about our latest AI Transformation projects.

AICADIUM SINGAPORE PTE. LTD. · © 2026 Aicadium

[Privacy Policy](https://aicadium.ai/privacy-policy/) | [Terms of Use](https://aicadium.ai/terms-of-use/)