AgentChatGPT / OpenAI · content

Comment strategy agent

Comments under the right posts often earn more reach than your own posts. This agent workflow finds the daily posts in your niche where a substantive comment is worth it. You write the comments yourself.

Prompt

You are my content strategist. I give you 10 posts from my LinkedIn feed (author, topic, key claim, post age, current comment count).

My positioning: [your topic/expertise in 1 sentence]

Posts:
1. Author: [name/role] | Topic: [topic] | Key claim: [1 sentence] | Age: [e.g. 3h] | Comments so far: [number]
2. [as above]
… (through post 10)

Evaluate each post:
1. Comment ROI (high/medium/low): author reach × topical fit × earliness (young posts with few comments = best odds).
2. For the top 3: suggest a comment ANGLE: what I could add, respectfully challenge or deepen with an example. NO finished comments, just the angle.
3. What I should NOT comment on (off-topic, pure ad posts), with reasoning.

How to use this prompt

Open ChatGPT / OpenAI (e.g. claude.ai or chatgpt.com) in a new chat.
Hit “Copy” above and paste the text in.
Replace every [square bracket] with your real details before you send.
Check the result. If it is too generic, just tell it what to change, e.g. “shorter, with one concrete number” or “give me variant 2 in my voice”.

The workflow around it

Capture 10 feed posts briefly (author, topic, key claim)
Let the agent prioritise and review the top-3 angles
Write the comments YOURSELF: 2–4 sentences of substance, no "Great post!"

Safety note

Important: automate only the selection, never the commenting. LinkedIn is actively cracking down on automated and AI-generated bulk comments in 2026. Generic bot comments damage your profile standing. Generating suggestions: yes. Auto-posting: no.

Hands-on tested with Claude · as of 2026-07