Marketing

17 Quick Replies Pulled 68.6K Views and a 3-Word Reply Got 46.6K: What Happened When an AI Agent Suggested His X Posts

  • Level Beginner
  • Setup~30 min (estimated)
  • Evidence Some evidence
  • CostNot stated in source
  • No-codeYes
Custom agentSource-linkedBeginner-friendly

What they did

A software engineer let an AI agent suggest what he posted on X for a few days, while he still pressed post himself. A post about Dancing With the Stars got 509 views in 3 minutes, a 3-word reply got 46.6K views, and 17 quick replies pulled 68.6K views. He wrote up what worked and what flopped in an X article.

How it went

X post by @zhouruijin (Nov 1, 2026 UTC): agent suggested posts, he still hit post; DWTS post 509 views in 3 minutes, a 3-word reply 46.6K views, 17 quick replies 68.6K. The agent isn't named in the post; his other posts use Grok Bot. View counts on replies swing a lot. Don't let an agent post for you without review

Worth knowing

  • X post by @zhouruijin (Nov 1, 2026 UTC): agent suggested posts, he still hit post; DWTS post 509 views in 3 minutes, a 3-word reply 46.6K views, 17 quick replies 68.6K. The agent isn't named in the post; his other posts use Grok Bot.
  • View counts on replies swing a lot. Don't let an agent post for you without review.

Prompt

Cleaned version rewritten from the source — not a direct quote.

Each morning, find [5] fresh, fast-growing posts in [my topics] that I could reply to or quote, and draft a short reply in my voice for each (one line, no hashtags, no links). Tell me why each one is a good pick. I'll post the ones I like myself. At the end of the week, compare views on the ones I posted and tell me which kinds worked.

Recommended

Try it in Grok Bot

Grok Bot can do this too: have it pick fast-growing posts and draft replies you post yourself.

  1. Copy the prompt (button below).
  2. Open Grok Bot chat and paste it. Replace any [bracketed] placeholders.
  3. Connect the listed tools (as needed) as connectors when Grok Bot asks.
  4. If the task repeats, ask: "Make this a daily routine."

Alternatives: the same prompt works in Claude, ChatGPT Agent, OpenClaw.

Set it up

Stack: Custom agent

  1. Read the original source for full context.
  2. Connect the tools your agent needs.
  3. Paste the prompt and replace [bracketed] placeholders.
  4. Run once manually and check the output before scheduling it.

Generic suggested steps, not from the source.

Evidence

X post by @zhouruijin (Nov 1, 2026 UTC): agent suggested posts, he still hit post; DWTS post 509 views in 3 minutes, a 3-word reply 46.6K views, 17 quick replies 68.6K. The agent isn't named in the post; his other posts use Grok Bot. View counts on replies swing a lot. Don't let an agent post for you without review

Source: X · 2026-11-01 · Verified by us: not yet · Report broken or outdated

Related use cases

ShoppingWeb

Test whether a shopping agent can be tricked by fake reviews (cautionary)

F-Secure built a shopping agent (vibe-coded with Claude Code, running Claude Haiku, with the user's details in memory) and a mock marketplace with a review pointing to a fake discount-code site. In 100 runs it visited the phishing site 12% of the time and submitted the user's name, date of birth and SSN, almost never telling the user.

  • Level Advanced
  • Setup1–3 hrs*
  • Evidence Strong evidence
Custom agentSource-linked⚠ Cautionary
MarketingWeb · 2026-10

118 of 120 AI Social Posts Were Bad and 93 Forgot the Link: An n8n Test, and Why Code Checks Still Missed False Numbers

He built a blog-post-to-5-platforms social workflow in n8n two ways and ran both on 8 posts, 3 times each. The one-prompt version produced 118 bad posts out of 120, and 93 left out the blog link. The version with code-checked rules marked 77 posts ready and sent 43 to a human, and none of the 77 failed an independent checker. But when he read them, 10 of 21 in the first round got the blog post wrong, including saying churn rose from 6.1% to 4.3%. His conclusion: code can check format, not truth.

  • Level Intermediate
  • Setup1–3 hrs*
  • Evidence Strong evidence
n8nSource-linked
MoneyWeb · 2026-10

Best AI Agent Passed About 11% of Real Tax Assignments: A Benchmark Where Models Missed a Home-Sale Deadline the Client Never Asked About

Surge AI's DAYJOB: Tax benchmark gave AI agents 50 realistic tax assignments with 1,789 files (PDFs, spreadsheets, receipts, emails). The top model passed only 10.8% at a 95% rubric threshold. In one case, an agent correctly compared two condo sale dates but never warned the client that her home-sale tax exclusion would expire if the sale slipped past August 2027. In another, a model assumed a couple wasn't legally married even though their records suggested an informal marriage, which would change how to split their retirement accounts.

  • Level Intermediate
  • Setup1–3 hrs*
  • Evidence Strong evidence
Custom agentSource-linked⚠ Cautionary