Real Agent Cases

Home › Category

AI for marketing: 21 real cases with prompts

21 source-checked cases in Marketing. Each shows what happened and the prompt.

  • Write a drama-style ad script modeled on a winning ad with ManusRecreated promptEvidence: Described by posterBeginner-friendly

    Manus wrote a drama-format script for one of the brand's top historical winning ad concepts, modeled on a winning drama ad from a beauty brand; the poster says it hit 5 ROAS right away.

    Poster says:5 ROAS off the bat

    Manus · Marketing · Source date:

  • Find car brands without a web app and email them a pitch with ManusRecreated promptEvidence: Screenshots or logs

    Manus searched for car brands without a web app, wrote an email and sent it to them; some replied and the poster built one an app.

    Manus · Marketing · Source date:

  • Manage Google Ads with Claude Code connected to analytics and the websiteRecreated promptEvidence: Described by poster

    With Google Ads, Google Analytics and the Webflow site connected to a Claude Code project, the poster adds negative keywords quickly, tracks ad performance, and found that mobile wasn't converting because the page showed nothing relevant above the fold.

    Claude Code · Marketing · Source date:

  • Qualify scraped leads against your ideal customer before cold email with Claude CodeRecreated promptEvidence: Described by poster

    Claude Code reads each scraped company's website and checks it against the poster's ideal customer profile, dropping about 30% of leads before outreach; the poster says reply rates roughly doubled and they booked 100+ meetings in 3 months.

    Poster says:100+ meetings booked in 3 months

    Claude Code · Marketing · Source date:

  • Make a PDF brochure from my website with ManusImproved promptEvidence: Described by posterFailure

    Asked to create a professional PDF brochure from the poster's website, Manus browsed and analyzed the site but delivered what was essentially copy-paste into a plain Google Doc; after feedback it only added a coloured first-page background and a different font, and the poster cancelled.

    Manus · Marketing · Source date:

  • Write a competitor content-marketing report with ChatGPT agentRecreated promptEvidence: Article or interview

    In Lisa Peyton's test, ChatGPT Agent Mode took 18 minutes to produce a 12-page narrative competitive-intelligence report on a list of competitors, with activity summaries, trend analysis, 31 cited sources and recommendations for content strategy.

    Poster says:12-page report in 18 minutes; 31 sources

    ChatGPT agent · Marketing · Source date:

  • Download a gated marketing report and summarize it with ChatGPT agentImproved promptEvidence: Article or interviewPartial

    SE Ranking's reviewer asked ChatGPT agent to get HubSpot's 2025 State of Marketing report; it found the page, filled in the gated form, downloaded the report and wrote a summary without help, but Google blocked it from signing in to email the summary because it was using an unsupported browser.

    ChatGPT agent · Marketing · Source date:

  • Write a cited industry report on AI in B2B visual marketing with Gemini Deep ResearchRecreated promptEvidence: Article or interview

    Lisa Peyton gave Gemini, ChatGPT and Perplexity Deep Research the same prompt for a report on generative AI in B2B visual marketing; Gemini's roughly 9,500-word report was rated highly accurate with 95 distinct citations, though she found it more theoretical than practical, with fewer pricing details and implementation examples than ChatGPT's.

    Poster says:About 9,500 words; 95 citations

    Gemini Deep Research · Marketing · Source date:

  • Research competitors for a board update with ChatGPT Deep ResearchRecreated promptEvidence: Article or interview

    Section's chief of staff gave ChatGPT Deep Research and Gemini Deep Research the same competitive-analysis prompt for its AI coaching product, written from a board member's point of view; she rated ChatGPT's output 4.5/5, saying it surfaced less obvious competitors such as Skillsoft and DataCamp and gave exactly what she asked for, while Gemini's report scored 2.5/5 for being too high level.

    Poster says:Output rated 4.5/5 (Gemini 2.5/5)

    ChatGPT Deep Research · Marketing · Source date:

  • Submit a product to ~300 directories and launch sites with Claude in ChromeRecreated promptEvidence: Described by poster

    In one day, Claude in Chrome filled directory and launch-platform forms 5 tabs at a time; 134 of about 300 submissions went through, with the human handling logins and captchas.

    Poster says:134 submissions went through

    Claude in Chrome · Marketing · Source date:

More Marketing cases