CheckedMake content

A practical method for your work

Source Quality Tested Tip

Ask AI to rank sources by primary evidence, recency, incentive, specificity, and claim support before trusting a summary.

Download and start →View original source ↗
Original sourceGoogle Search Central helpful content guidance + OpenAI prompt engineering guideChecked 2026-07-08
Use this whenResearch · SEO writing · Fact-sensitive decisions
You will getA reusable way to start the work

Core idea

Most research prompts ask the model to summarize too early. This tip inserts a source-audit step first: separate primary sources from commentary, label stale or incentive-heavy pages, and attach each claim to the strongest available evidence.

Why it works

A fluent answer can hide weak evidence. Ranking source quality changes the task from “write a summary” to “manage evidence,” which is closer to how reliable, people-first content should be built.

Weak

Summarize these links and tell me what is true.

Better

Before summarizing, audit each source. Label: primary/secondary, date, author/incentive, direct evidence, claim supported, confidence, and what would disconfirm it. Then write only claims supported by the strongest sources.

Customize it

Allowed sourcesSource typePublication dateAuthor or incentiveDirect evidenceSupported claimConfidenceDisconfirming evidence

Working template

Goal: [what I am trying to accomplish] Context: [background, audience, constraints] Use this pattern: Source Quality Tested Tip Variables: Allowed sources, Source type, Publication date, Author or incentive, Direct evidence, Supported claim, Confidence, Disconfirming evidence Return: [exact output format] Before finalizing: state limits and one improvement

Operating recipe

  1. Start with the weak version so you know what problem you are fixing.
  2. Add the missing variables instead of making the instruction longer randomly.
  3. Ask the model to follow the output contract exactly once.
  4. Review the first answer against the checklist below.
  5. Save the improved version as your reusable pattern.
Free audit template

Download the source quality audit

Paste this before summarizing links so the model ranks sources before writing claims.

Download .md
Primary vs secondary source
Date, author, and incentive
Direct evidence and supported claim
Confidence and disconfirming evidence

Quality checklist

  • Did I give the model the real goal, not just the task?
  • Did I define the output shape before asking for the answer?
  • Did I include examples, constraints, or a quality bar?
  • Did I ask for limits, uncertainty, or failure cases?
  • Can I reuse this as a pattern next time?

Model notes

Claude

Strong for long context, critique, and structured writing. Give it clear sections and examples.

ChatGPT

Strong for fast iteration and everyday templates. Be explicit about output format and assumptions.

Gemini

Useful for broad synthesis and Google-adjacent research. Keep source requirements explicit.

Limits

AI can rank only the sources it can see. If browsing is unavailable, paste excerpts and URLs. For medical, legal, financial, or safety claims, use primary/official sources and human review.

Read next

Context Pack PatternGive AI the work environment before asking for serious output.Role + Rubric PatternGet better critique by defining the judge and the scoring criteria.Ask Before Answer PatternUse clarification only when missing context changes the answer.
Free downloads

Turn this into a reusable workflow.

Get the Prompt Debugging Checklist and Solo Builder AI Setup Pack as language-specific .md files.

Open free downloadsBack to library →