The task
You suspect a competitor in your niche is doing something structurally smarter than you — better hooks, tighter format, smarter cadence. You want a teardown that tells you what to copy at the pattern level, not “post more videos.”
When this is the right job for AI
- You can hand AI 15-25 of their recent posts (titles, hooks, captions, engagement numbers).
- You want pattern-level insight, not “they get more likes.”
- You will adapt patterns to your own voice. AI is for analysis; not for cloning.
What to feed the AI
- Competitor handle + platform
- 15-25 posts: title or first line + format (carousel / short / long) + engagement (likes, comments, shares)
- The 3 questions you want answered: “what’s their hook formula?”, “what cadence?”, “what topic clusters?”
- Your audience: who you are writing for
Copy-ready prompt
You are doing a content teardown for me.
Competitor: @creatorname (Xiaohongshu)
My audience: Chinese-speaking junior PMs (1-3 yrs experience), curious about AI workflows.
Recent posts (last 20, format: hook | format | engagement):
1. "I rewrote 3 years of PRD templates with AI" | carousel | 4.2k likes
2. "5 things GPT can do in a PM's day job" | text | 1.1k likes
3. "Cursor wrote my first user-interview guide" | short video | 8.7k likes
... [paste 20, in the original language used by the competitor]
Find:
1. The hook formula (their top 3 posts have hooks that share what structural property?).
2. The format-engagement pattern (does short video outperform carousel for them?).
3. The 3 topic clusters they keep returning to.
4. The thing they don’t do that I could.
5. Two specific posts I should NOT copy directly because they are off-brand for my audience.
Output as a 5-bullet teardown. No "they are great at content"-style filler.Sample output structure
- Hook formula: all three top posts open with a number + specific tool (e.g., “I rewrote 3 years of [artifact] with AI”). Numbers + named tools out-perform generic “AI in a PM’s day job” hooks 4:1 here.
- Format pattern: short video wins on reach (avg 8k vs carousel 4k), but carousels collect comments 3x. They optimize for reach; you could optimize for community signal.
- Topic clusters: PRD workflows, user-research prompts, Cursor for non-engineers. Two of three overlap your audience.
- Gap: they don’t cover “AI for junior PM career moves” — résumé, interview, debriefs. That’s the wedge.
- Skip: the “5 things GPT can do in a PM’s day job” listicle — generic, aimed at PM-curious non-PMs, not your audience.
How to refine
- Output too high-level → add “every claim must reference at least one specific post.”
- Wrong audience → add “do not analyze for general PM audience; analyze for MY audience as defined.”
- AI sycophantic → add “be willing to say
they are wrong on Xif the data supports it.” - Missing the gap → add “the deliverable is one wedge — a topic THEY are not covering and MY audience needs.”
Common mistakes
- Pulling 5 posts instead of 20 — too small a sample to see patterns.
- Looking only at top-performing posts. Their flops tell you what to skip.
- Asking AI for engagement numbers — give it the numbers; AI cannot scrape.
- Copying the hook formula verbatim. Adapt the structure; bring your own specifics.
Practical depth notes
For AI Competitor Content Teardown: Spot the Patterns You Can Actually Use, the difference between a usable AI result and a generic one is the input packet. Give the model the audience, the current draft or raw material, the desired format, the decision you need to make, and two examples of what good and bad output look like. Ask it to preserve facts first, then improve structure or wording second.
After the first response, do a separate review pass. Look for missing constraints, invented details, weak calls to action, and language that sounds plausible but does not match the real situation. The best final output should be easy to use immediately: clear owner, clear next step, and no hidden assumption that someone else has to untangle. A stronger version of this workflow also defines the handoff. Decide who will use the output, what they should do next, and what information would make them reject it. If the deliverable is copy, test whether it has a single clear action. If it is analysis, test whether it separates observation from recommendation. If it is planning, test whether dates, owners, and tradeoffs are explicit enough for someone else to execute. One final check: compare the finished result against the original goal in a single sentence. If that sentence is hard to write, the output is probably polished but unfocused. Tighten the goal, remove decorative language, and rerun only the weak section instead of regenerating the entire piece.
FAQ
- What if my competitor only posts video? Give AI the hooks (first 3 seconds spoken) plus thumbnail text. AI can analyze without watching.
- How often should I redo this? Quarterly per top competitor. Patterns shift slower than you think.
- What about analyzing my own content the same way? Yes — same prompt, swap “competitor” for “my last 20 posts.” Useful retrospective.
Related
- AI short-video ideation
- AI content calendar for creators
- AI personal brand voice design
- AI Xiaohongshu series content
- Comment-to-Content Prompts: Turn Replies Into Posts
Tags: #AI writing #Creator #Content creation #Competitor #Social media