How do I analyze Facebook posts with ChatGPT, Claude, or Gemini?

PostSnag exports plug directly into ChatGPT, Claude, or Gemini: export a profile, a group, or your whole Posts library to Markdown or CSV, then paste or upload the file and ask a specific question about the posts. Export Data plus media instead and, because the real video files come with it, an AI tool that accepts uploads can watch the videos and read the captions in the same pass.

This is one of the main reasons people use PostSnag. Capturing and exporting gets you the raw data and the real media; an AI tool is what turns that into something you can act on the same day.

How to do it, step by step

1. Capture the profile or group with the extension first, if you haven't already. Open it on Facebook, scroll, and click Export To Dashboard. See How do I send my captured posts to the dashboard? (Export To Dashboard).
2. Open the profile, group, or the global Posts page, and filter down to what you want to study, or multi-select specific posts.
3. Choose a format: Markdown for most pasted-text questions, CSV for structured row-by-row work, or Data plus media if you want the AI tool to see the real video and image files alongside the data.
4. Open ChatGPT, Claude, or Gemini in a browser tab or app.
5. Paste the Markdown or CSV contents into the chat, or upload the file, and for Data plus media, the video or image files, if the tool supports attachments.
6. Ask a specific question. The more precise the prompt, the more useful the answer; "what do you think of these posts" gets a vague answer, a targeted question doesn't.

[SCREENSHOT: A Markdown export pasted into an AI chat interface alongside a specific prompt]

Example prompts to try

Once your export is in the chat, adapt one of these to what you're actually deciding:

Find the pattern behind what's working

• "What do the highest-engagement posts in this export have in common that the lowest-engagement posts don't? Look at hook style, caption length, and where the call to action lands."

Compare post types

• "Group these posts by type and rank each group by average reactions, comments, and shares. Which post type is actually carrying this profile?"

Turn history into a plan

• "Based on what worked in this export, draft a two-week content calendar with 10 post ideas, each modeled after a specific post from the data."

Build a swipe file

• "Pull the first line of every caption from the 10 highest-engagement posts. I want a list of hooks I can adapt for my own content."

Get the AI to watch, not just read

• "Watch this video and tell me the hook in the first three seconds, the pacing, and where attention is most likely to drop off."

Spot timing patterns (CSV works well for this one)

• "Look at the Posted column in this CSV. Is there a day of the week or time pattern where reactions are consistently higher?"

Adjust the wording to your niche and your actual goal. A prompt that names what you're deciding, a content calendar, a hook list, a format decision, beats a generic "analyze this."

Markdown, CSV, or Data plus media for AI work

• Markdown tends to read more naturally when you're asking about tone, structure, or "what's the pattern here" questions, since each post is already a labeled, self-contained section.
• CSV is better when you want the AI tool doing structured, row-by-row comparisons or basic math across a large number of posts, like ranking by engagement or checking for a day-of-week trend.
• Data plus media is the one to reach for when the video itself matters: pacing, on-screen text, what happens in the first three seconds, or anything a caption alone can't tell you. Upload it to an AI tool that accepts video, and it can watch the file, not just read a description of it.

See Which export format should I choose? (Markdown, CSV, media, or both) for the full comparison.

A few things that get better answers

• Export a real sample, not a handful. A few posts won't give an AI tool much to compare. A few dozen does much better.
• Say if you're working from a capped export. If a profile is on the Free plan's 30-post cap, mention that in your prompt so the AI tool doesn't assume it's seeing that profile's complete history.
• Give the AI tool your goal, not just the data. "I run a similar page and want to grow engagement" gets a more useful answer than pasting the file with no context at all.

What this doesn't do

PostSnag doesn't include a built-in AI analysis feature of its own; it captures and exports the data and the real media, and you bring your own AI tool to interpret it. A pasted Markdown or CSV file still has no embedded images or video, only links; export Data plus media and upload the files if you want the AI tool to actually see the content. No format includes a per-reaction-type breakdown either: exports report a total reaction count only, so a prompt asking the AI to analyze a specific reaction type won't have anything to work with. See What is included in a PostSnag export? for the full list of what's in each format.

PostSnag is not affiliated with, endorsed by, or sponsored by Meta Platforms, Inc.

Common questions

Do I need a paid ChatGPT, Claude, or Gemini account for this?
No. A free-tier AI tool account can read a pasted or uploaded export, though very large exports or video files may hit that tool's own file size or message length limits.

Should I use Markdown, CSV, or Data plus media for AI analysis?
Markdown and CSV both work for pasted-text questions; Markdown tends to read more naturally for pattern and tone questions, CSV is better for structured comparisons. Use Data plus media when you want the AI tool to watch the actual video files.

Can the AI actually watch the videos I captured?
Yes, if you export Data plus media and upload the video files to an AI tool that accepts video or file uploads, like ChatGPT or Claude. A pasted Markdown or CSV file only links to the post; it doesn't carry the video itself.

Can the AI tell me the reaction breakdown for a post?
Not from an export. Every exported format includes the total reaction count only, so an AI tool working from any of them can't break that number down into like, love, or haha. Check the dashboard itself for that.

Related articles

• Which export format should I choose? (Markdown, CSV, media, or both)
• What is included in a PostSnag export?
• How do I export a profile, and what are the formats?
• How do I find the post types and posting days that work?
• How do I build a Facebook swipe file?
• How do I analyze a competitor's Facebook profile?