⚡ Promptolis Original · Learning & Growth
🔎 Source Evaluation — CRAAP Framework
Not all sources equal. CRAAP: Currency / Relevance / Authority / Accuracy / Purpose. Distinguish peer-reviewed research from blog opinion. Essential for…
Source Evaluation — CRAAP Framework — Not all sources equal. CRAAP: Currency / Relevance / Authority / Accuracy / Purpose. Distinguish peer-reviewed research from blog opinion. Essential for… Setup: 1 min to try · Best AI: Sonnet 4.5. · Cost: Free, MIT-licensed.
Why this is epic
CRAAP (Meriam Library, CSU Chico 2004) is the most-taught source-evaluation framework. 5 dimensions systematically evaluate credibility.
Critical for research papers (citation quality affects grade) + general media literacy (knowing what to believe).
📑 Page navigation + Key Takeaways Click to expand
📌 Key Takeaways
- What it is: Not all sources equal. CRAAP: Currency / Relevance / Authority / Accuracy / Purpose. Distinguish peer-reviewed research from blog opinion. Essential for…
- Best for: Research paper source vetting
- Time investment: 1 min to try setup, 5-10 min per source output
- Recommended AI model: Sonnet 4.5.
- Cost: Free forever — MIT-licensed, no signup, no paywall
📑 On this page
- The prompt (copy-ready)
- How to use it (4 steps)
- Example input + output
- Common use cases
- Pro tips + variants
- FAQ
⚙️ At a glance
- Category:
- Learning & Growth
- Setup time:
- 1 min to try
- Output time:
- 5-10 min per source
- Best AI model:
- Sonnet 4.5.
- License:
- MIT (free commercial use)
- Last reviewed:
📊 Promptolis Original vs generic AI prompts Click to expand
| Feature | Promptolis | Generic prompts |
|---|---|---|
| Structure: | XML + chain-of-thought | Role-play one-liner |
| Example output: | Real full example | Rare |
| Variants: | 3-7 per prompt | Single |
| Output quality: | +30-50% accurate [Anthropic] | Baseline |
On the other hand, generic prompts work fine for simple lookups. Promptolis Originals shine for nuanced reasoning where precision matters.
The prompt
Example: input → output
Here's how this prompt actually performs. Real input below, real output from Claude Opus 4.
<source-to-evaluate>A 2019 blog post by a nutrition influencer (no credentials listed) about keto diet reversing diabetes. Claims to cite studies but links are affiliate product pages.</source-to-evaluate> <usage-context>Academic — researching for sociology paper on health information trustworthiness</usage-context>
CRAAP Evaluation
Currency
2019. 6 years old. For nutrition research, that's moderately dated — keto diet research has advanced significantly since. Red flag for 'current information.' ⚠️
Relevance
Relevant to your topic? Only as EXAMPLE of misleading health information — not as reliable source on keto diet claims. Context-dependent utility.
Authority
'Nutrition influencer' + no listed credentials. No stated medical, research, or academic background. Likely not authoritative for medical claims about diabetes reversal. ❌
Accuracy
'Links to affiliate product pages' instead of peer-reviewed research = accuracy red flag. Financial motivation to cite favorably. Not verifiable by primary source. ❌
Purpose
Promotion of products (affiliate links) + persuasion to adopt diet. Not informational for research purposes. Commercial intent dominant. ❌
Verdict
Don't cite as reliable source on keto diet science.
DO cite if paper topic is 'trust in health information' — this source is EVIDENCE of the problem you're studying, not authority on the subject.
For actual keto science research, seek:
- American Journal of Clinical Nutrition
- Diabetes Care journal
- Peer-reviewed systematic reviews / meta-analyses
- American Diabetes Association position statements
- Specific researcher names: Gary Taubes (journalist; investigates), Stephan Guyenet (obesity researcher)
Always check: who's the author, where was it published, when, who funded the research, what's the methodology.
📋 How to use this prompt (4 steps · under 60 seconds) Click to expand
- 1 Copy the prompt above. Click "Copy prompt". XML-structured prompt now on clipboard.
- 2 Open ChatGPT, Claude, or Gemini. One-click launch above. Recommended: Sonnet 4.5..
-
3
Paste + fill placeholders. Replace
{curly braces}with your context. Specificity = quality. - 4 Run + iterate. Setup: 1 min to try. Output: 5-10 min per source.
Common use cases
- Research paper source vetting
- General fact-checking
- News media literacy
- Student + professional research
Best AI model for this
Sonnet 4.5.
Pro tips
- Peer-reviewed > popular press.
- Check author credentials (LinkedIn, institutional affiliation).
- Date matters — especially rapidly-changing fields.
- Follow citations back — primary vs. secondary sources.
- Purpose matters — persuade vs. inform.
Customization tips
- For news sources: bias + funding + corrections-record matter.
- For scientific sources: journal impact factor + peer-review + replication status.
- For medical information: government sources (CDC, NIH) + academic medical centers + WHO reliably-authoritative.
Variants
Default CRAAP
Standard framework
News Media Evaluation
Current-events application
Scientific Source
Research paper specific
Health Information
Medical credibility
Frequently asked questions
Common questions about this prompt and how to get the best results from it.
How do I use the Source Evaluation — CRAAP Framework prompt?
Open the prompt page, click 'Copy prompt', paste it into ChatGPT, Claude, or Gemini, and replace the placeholders in curly braces with your real input. The prompt is also launchable directly in each model with one click.
Which AI model works best with Source Evaluation — CRAAP Framework?
Sonnet 4.5.
Can I customize the Source Evaluation — CRAAP Framework prompt for my use case?
Yes — every Promptolis Original is designed to be customized. Key levers: Peer-reviewed > popular press.; Check author credentials (LinkedIn, institutional affiliation).
What does it cost to use this prompt?
The prompt itself is free, MIT-licensed, with no email signup required. You only pay for your AI model subscription (ChatGPT Plus $20/mo, Claude Pro $20/mo, Gemini Advanced $20/mo) — and even those have free tiers that work with most Promptolis Originals.
How is this different from PromptBase or PromptHero?
PromptBase sells prompts in a marketplace ($2-15 each). PromptHero focuses on image-generation prompts. Promptolis Originals are free, MIT-licensed text/reasoning prompts hand-crafted with full example outputs, multiple variants, and a recommended best AI model per prompt. We don't sell anything.
Explore more Originals
Hand-crafted 2026-grade prompts that actually change how you work.
← All Promptolis Originals