Skip to content
TriedPrompts

More in Launches, SEO & content.

Compare ChatGPT, Claude and Gemini on one marketing LinkedIn brief

PartialEvidence: Described by posterPosted Last checked

Chris Biddle's identical LinkedIn brief: ChatGPT was polished but generic; Claude was sharper but missed the word limit.

How to use this

  1. Tap Copy prompt.
  2. Open ChatGPT.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Original prompt

The prompt as the person shared it in the source.

What the prompt labels mean

These are the person's own words, as shared in the source.

You are a digital marketing expert writing for small business owners. Write a LinkedIn post announcing an AI-powered SEO audit service. Tone is confident and direct. Under 150 words. End with a question that invites comments. Reference one real pain point business owners have with SEO.

Try this in:

ChatGPT Used in sourceGemini Used in sourceGrok Claude Used in source

Sends the Original prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Pick the right model for a marketing draft by running one strong brief across ChatGPT, Claude and Gemini.

Questions to ask me first:
- What offer are we announcing, and who is the audience?
- Hard constraints (word limit, CTA, banned claims)?
- Which pain point must be specific, not generic?

Inputs (fill in or confirm):
- Six-part brief: Task/Context/Exemplars/Persona/Format/Tone: [FILLED]
- Word limit: [NUMBER]
- Pain point: [SPECIFIC]

Rules:
- Keep the brief identical across tools.
- Score polish, specificity, constraint-following and originality.
- Call out when a model breaks the word limit or goes generic.
- Recommend which model to use for social vs thought leadership.

Checkpoint: Confirm the brief and rubric before generating the three drafts.

If you get stuck: If a draft invents customer results, strip claims and regenerate with a no-fabrication rule.

Verify before you finish: Count words and check the CTA question exists before scoring.

Output: Three drafts, a score table and a one-line routing rule for future posts.

Done when: I know which model to open first for this content type.

AI tools

ChatGPTClaudeGemini

Outcome

Chris Columbkille Biddle, who runs a digital marketing agency, stopped switching models randomly and tested ChatGPT, Claude and Gemini on the same six-part marketing prompt formula (Task, Context, Exemplars, Persona, Format, Tone). On a LinkedIn post announcing an AI-powered SEO audit service, ChatGPT was polished and ready to post but predictable and generic on the pain point; Claude thought longer, ran long past the word limit and produced a more distinct point of view; Gemini's strengths and gaps are discussed in the same comparison as part of picking tools by job rather than blaming the prompt for mediocre output.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Known limitations

PartialThe source says it only partly worked, or had a significant problem a person had to deal with.

What went wrong: ChatGPT was usable but generic; Claude was sharper but ignored the under-150-word limit; picking one model for every task still failed.

Source

Posted
by Chris Columbkille Biddle (LinkedIn)
Last checked
Method:
How we verify

https://www.linkedin.com/posts/christopherbiddle_i-tried-chatgpt-claude-and-gemini-with-activity-7492520539601690624-4bWp

Context: Date estimated from the LinkedIn activity ID. Partial because no single model won cleanly on constraints plus originality. Gemini is included in the test; detailed Gemini notes are thinner in the fetched preview.

More in Launches, SEO & content

Similar cases