As of 13 August 2026, AI can evaluate whether a source is credible.
This still needs a person who signs their name to it.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill needednone
Who has to check ityou
What the alternative costsYou can carry out the same checks with a web browser, the source's original website and your school, college or university library guidance.
If this goes wrong: you rely on a weak or misleading source and need to replace the citation or revise the argument.
What to actually do
Hand it to a person
The route this page recommends
A person who owns the outcome does this end to end, worth it when the failure is dear.
Do it yourself
Second choiceA chat interface, no skill needed, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open the source in a browser and copy its URL, full title, author, publisher, publication date and the specific claim you want to use.
- Read the source itself and save the passages, data, references and author information that support or qualify the claim.
- Paste the prompt into ChatGPT, Claude or Gemini and replace the bracketed sections with the source details, claim and subject.
- Ask the chatbot to assess the source without filling in details it cannot verify, then open each cited link it mentions.
- Compare the source's references, author details, publication date and funding information with the original publisher, author profile or research record.
- Search the main claim in Google Scholar, your library catalogue or reputable UK institutional websites and record whether independent sources agree.
- Use the AI verdict only as a checklist, then cite the source if its evidence and provenance meet your course requirements.
Prompt
Evaluate whether this source is credible for my assignment. Source link or full text: [PASTE LINK OR TEXT] Claim I want to use it for: [PASTE THE CLAIM] Subject and level of study: [PASTE SUBJECT AND LEVEL] Assess it using these checks: 1. Who wrote it, and what relevant expertise or affiliation can be verified? 2. Who published or funded it, and what editorial or institutional controls are visible? 3. When was it published or updated, and does the date matter for this topic? 4. What evidence does it provide, and do the links or references support the claims? 5. Is it reporting research, interpreting evidence, expressing opinion or trying to sell something? 6. Are there signs of bias, conflicts of interest, exaggerated language or missing context? 7. Can the main claim be corroborated by two independent, reputable sources? Do not treat polished writing, search ranking or an institutional-looking website as proof of credibility. Do not invent author details, publication history or evidence. If you cannot access or verify something, say so clearly. Separate facts you checked from inferences. End with a verdict of credible, usable with caution or not suitable, explain the reasons, list the exact checks I must complete myself, and suggest search terms for independent corroboration. Use UK spelling.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
Use a tool built for this
The distant third
What it gets wrong
- AI cannot turn an unknown or inaccessible author into a verified expert.
- AI cannot reliably distinguish genuine independence from a carefully presented commercial or political interest.
- AI cannot decide whether evidence is strong enough for your subject without knowing the field's standards and debate.
- AI can repeat a source's claims or cite a different page that does not actually support them, so every important link needs opening.
- AI cannot replace your tutor's or institution's rules about which sources count as suitable for the assignment.
Even on a YES, the friction has a name: verification cost, judgement under ambiguity and real time truth.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 1 |
| Liability | 2 |
| Effort delta | 2 |
| Total | 9 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT tell if a website is credible?
- It can check visible signs such as authorship, publisher, date, references, funding and corroboration. It cannot prove that an unknown author is genuine or that every claim is accurate, so open the original links and make the final decision yourself.
- How do I use AI to check if a source is reliable?
- Give it the source link or text, the claim you want to use and your subject level. Ask it to separate verified facts from inferences, identify missing information and suggest independent sources, then check those points outside the chatbot.
- Can AI check whether a source is suitable for my essay?
- Yes, it can compare the source with common academic checks and flag weak evidence, unclear authorship or conflicts of interest. Your course or tutor may apply stricter rules, so confirm that the source type is allowed before citing it.
- Should I trust an AI credibility score?
- No, treat a score as a prompt for checks rather than proof. AI may miss an undisclosed interest, misunderstand specialist evidence or rely on information that has changed, so verify the provenance and main claim yourself.
Nearby answers
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.