LinkedIn MAXXING with ChatGPT Dots: a 12-prompt system for posts worth reading

LinkedIn MAXXING with ChatGPT Dots means giving a dot the work behind a good post (knowing your customers, finding an angle, collecting evidence and knowing what you can credibly claim) and keeping the decisions and the publishing for yourself. When you just hand an AI a topic and ask for a LinkedIn post, all of that work is skipped. The 12 prompts below turn it into a system you can repeat, from market research to a content calendar to tracking which posts led to real business conversations.

By the end you will have:

• A voice guide built from the way you actually write and speak.
• A research routine that collects good ideas before you need them.
• A drafting and review process with clear quality standards.
• A monthly report that tells you what to write next.

A dot suits this kind of system. It is an always-on agent inside ChatGPT with its own cloud computer and browser; it carries on working between conversations and comes back to you when something needs your judgment.

Keep this page for your next content planning session.

What should you give a ChatGPT dot before the first prompt?

A job title and a request to “sound human” won’t get you far. The dot needs to know who you sell to, what you believe and which claims you can back up.

Start with this:

Treat what follows as the working context for my LinkedIn content. Store the main points in your notes, keep the complete version as a reference I can reuse, and tell me exactly what you stored and where. Business: [company name, website, product or service, how we make money, and the usual sales cycle]. Audience: [customer roles, company sizes, industries and locations]. The problems they have are [problems], the objections they raise are [objections], and the events that send them looking for help are [triggers]. Positioning: we help [audience] reach [outcome] by [approach]. What sets us apart most is [differences]. We are the wrong choice for [disqualifiers]. Viewpoint: I hold [three opinions about my industry]. I disagree with [common advice] because [reason]. Evidence: these are the case studies, results, examples and personal experiences you may use: [sources]. Never make up customers, revenue numbers, stories or quotes. Voice: here are [10–20 posts] and [transcripts or writing samples] that sound like me. Stay away from [phrases, tones and formatting habits]. Goals: my main LinkedIn goal is [qualified conversations / deal support / hiring / awareness]. My offer is [offer], and the step I want interested readers to take next is [action]. Working rules: use connected sources only where you have access and permission. If you can’t reach a source, ask me for an export or pasted text. LinkedIn publishing, comments, connection requests and messages stay with me. Put drafts in [review destination], keep evidence and inference apart, and flag anything that needs my input.

Update that context whenever your offer, audience or opinions change.

Where does a ChatGPT dot keep this context?

A dot draws on three layers: the conversation you are having, the relevant parts of your ChatGPT memory, and its own notes on your preferences, decisions and ongoing work. Those notes travel with it across ChatGPT, Slack, Teams and calls, so you can brief it at your desk and correct it later from your phone.

The notes aren’t a transcript, and they are kept apart from ChatGPT’s saved memory. Changing a memory setting won’t necessarily change what the dot has already noted. When your context changes, tell the dot directly and ask it to confirm the update. Once a week, ask it what it is keeping in its notes about your LinkedIn work, because those notes come with it into every new conversation and channel.

Two settings make the “working rules” in the prompt firmer. Instructions describe how you want the dot to work, such as “show me every draft before it goes anywhere”. A longer version: “For LinkedIn work, use my business context and voice guide from your notes. Send drafts and questions to me in ChatGPT, keep routine progress to a weekly summary, and tell me when a source you need is not connected.”

Custom Rules (Settings > Personalization > Custom rules) attach one of four behaviours to an action: take action without asking, take action when you say so, ask before taking action, or hand off to you. Write one rule covering anything that would appear on LinkedIn under your name, and set it to Hand off to you. Instructions and rules don’t turn off the built-in safeguards: Auto-review still checks any action that could affect your accounts or share information before the dot goes ahead.

One more detail saves confusion. When a dot passes a job to a background agent or a new cloud thread, that job runs in its own conversation and doesn’t automatically see everything you told the dot. Ask the dot to send the business context and voice guide with every job it hands off.

Part 1: research and content production (prompts 1–8)

1. How do you build a voice guide with a ChatGPT dot?

A useful voice guide explains the choices behind your writing: how you open an argument, how you use examples and how you move from one idea to the next. Labels like “conversational and authoritative” don’t help much.

Study the posts and transcripts I have shared and turn them into a working LinkedIn voice guide. Cover: how I start posts, explain ideas and finish an argument; the words I tend to use, my sentence and paragraph lengths, and how I use lists; how I show disagreement, doubt, humour and confidence; phrases that come naturally to me, quoted word for word with where they came from; and habits that show up in my weaker pieces and shouldn’t become rules. Add a list of phrases and patterns to avoid, such as needless repetition, invented drama, certainty without support, and too many one-line paragraphs. End with three before-and-after edits that turn generic copy into my voice without changing what it says. Make the guide concrete enough that another writer could follow it.

Setting it up in ChatGPT Dots: share the posts and transcripts in the dot’s conversation, or keep them in a Google Drive folder the dot reads through the Google Drive plugin. OpenAI’s own content-creator example is close to this job: the dot learns your voice and audience, drafts for your approval and carries your edits into the next batch.

That only works if the guide lives somewhere the dot can find it again, so ask it to keep the guide on a Page in Space and to record in its notes where that Page is. Review the first version and fix what’s missing before you give it more to do, which is how OpenAI recommends starting any new responsibility. Connect only the plugins this job needs; adding Slack or Teams as a messaging channel doesn’t give the dot access to your apps or files.

Why it matters: A voice guide makes your feedback reusable. You stop correcting the same phrasing every week and improve the instructions behind every draft instead.

2. How do you find the customer questions worth answering?

Sales calls and customer conversations surface questions a keyword tool never shows. The best ones usually involve a decision someone is finding hard to make.

Go through the sales calls, support threads, customer interviews and closed-lost notes I have shared from [period]. Sort the questions that keep coming up into five groups: problems customers are trying to understand; worries that hold up a decision; alternatives they are weighing; expectations that end in disappointment; and questions they ask just before they commit. For each theme, give an anonymised quote, where it came from, how many separate conversations it appears in, the customer’s role and where they are in the decision. Suggest two LinkedIn angles for each theme, one that helps the reader work out the problem and one that helps them judge a solution. Rank the top 10 by how often they recur, how relevant they are to sales and how strong our evidence is. Keep what customers said apart from your reading of it.

Setting it up in ChatGPT Dots: this is where a dot pays off, because new questions keep arriving after the first run. If call notes land in Gmail or a Slack channel, connect those plugins and tell the dot which label or channel to watch; connecting Slack by itself doesn’t start any monitoring.

In proactive research the dot can read what it has permission to read and keep private notes, but it never sends or changes anything in that mode. Ask it to add new quotes to the backlog and message you only when a theme enters the top 10. In the desktop app, Activity lists every research job it started, so you can open one and see which sources it read.

Why it matters: You get a backlog tied to conversations your business is already having, in words you recognise and with evidence you can check.

3. How do you spot topics moving from X into your market?

A discussion picking up on X can make a good LinkedIn post, as long as you explain why it matters to your customers and add something of your own instead of rewriting it.

With your own browser, web search and the X links I send, look at the last [seven days] of discussion about [topics] and from these accounts: [accounts]. Pick up to 10 developments or arguments that matter to [customer]. For each one, give me: the original source, author, date and link; a neutral summary of what happened or what people are arguing; the strongest competing readings; what it means for our audience day to day; and an angle we could back with our own experience or evidence. Mark any reaction counts as a snapshot, don’t treat popularity as proof, and check factual claims against the original source where you can. Recommend three ideas worth developing and say what I would need to add before each one becomes a credible LinkedIn post.

Setting it up in ChatGPT Dots: the dot researches in its own cloud browser, which runs its own sessions apart from the browser on your computer. OpenAI doesn’t document a direct X connection, and some websites block cloud browsers. If X pages won’t load, ask the dot to use your connected computer, or paste the links yourself.

Ask it to name the source domain for every item, so you can see where each story came from, and to drop anything older than your window. Run the prompt once to check the format, then make it recurring with a complete schedule: “Every Monday at 8 AM [time zone] for the next eight weeks. Message me only if a story fits [customer]. Confirm the schedule.” Say which changes deserve a message and which can wait for the weekly summary, or you will hear about everything.

Why it matters: Research gives you a place to start; your judgment gives readers a reason to follow you. A good adaptation ties the discussion to a decision your readers actually face.

4. How do you analyse posts that beat their authors’ usual results?

Measuring every post against a famous account’s biggest hit skews your research. Compare a post with its author’s normal results first, then look at what might explain the gap.

Work through this LinkedIn swipe file and whatever performance data comes with it: [file]. Where there is enough comparable data, set each post’s reactions and comments against the author’s median for a similar format and period. Show the maths and flag small samples, missing numbers and very recent posts. For the clearest outliers, describe: the topic and the intended reader; the opening, argument, evidence and close; the format and rough length; whether the comments suggest real customer interest; and possible confounders such as a launch, a news event or unusually wide distribution. Turn this into five structural patterns I can reuse, then suggest an original idea for each based on my own experience. Don’t copy distinctive wording, and don’t present a pattern you observed as a rule of the algorithm.

Setting it up in ChatGPT Dots: the dot analyses data on its own computer, so give it the swipe file as a spreadsheet and ask for the medians back as a file you can open. A large file suits background agents: the dot can split the authors between them and keep talking to you while they run.

Before it starts, tell it which columns count as reactions and comments, so every background agent measures the same thing. To compare one of your own posts with the medians it finds, use our LinkedIn Engagement Rate Calculator. Ask the dot to save the median table to the voice guide Page, so prompt 12 can compare next month against the same figures.

Why it matters: You end up with hypotheses worth testing, and you avoid assuming that copying a successful layout will copy its results.

5. How do you turn recorded calls and interviews into original posts?

A transcript can hide a strong post inside a story, a throwaway explanation, or a disagreement that deserved more airtime than it got.

Read this interview, podcast, webinar or meeting transcript: [source]. Find eight moments that could carry an original LinkedIn post, favouring decisions, mistakes, surprising observations, practical explanations and opinions rooted in experience. For each moment, give: the exact quote with its timestamp or location; the main idea and who it would help; any context needed so the speaker isn’t misrepresented; facts we already have that support it; and one follow-up question that would make the idea stronger. Pick the three best moments and draft a post from each, following my voice guide. Keep the speaker’s level of certainty, take out confidential details, and leave placeholders wherever a result or example still needs confirming.

Setting it up in ChatGPT Dots: OpenAI lists “prepare content from each interview” as a dot use case, so make it a standing job instead of a one-off. Whenever a new transcript lands in the Google Drive folder you name, the dot runs this prompt and sends you the eight moments, with a short list of the moments it rejected and why, so you can overrule it.

You can check quotes and adjust a draft’s tone from your phone, then publish yourself. Ask the dot to record each speaker’s original certainty in its notes so the next batch doesn’t drift. If the recording exists only on your laptop, connect your computer through the dot’s profile; it has to be online with the ChatGPT app open while the dot uses it.

Why it matters: You get posts from knowledge your team already has, without asking anyone to come up with a fresh opinion every time the calendar has a gap.

6. How do you plan a four-week LinkedIn content calendar?

A calendar should weigh what customers need to understand against what you have the evidence to say. Filling every slot with another version of your offer makes your feed repetitive.

Plan four weeks of LinkedIn posts at [three posts a week] from the ideas I approved in our research. Mix in: practical explanations that help customers fix a problem; opinions backed by experience or evidence; customer examples we have permission to use; answers to objections and late-stage questions; and an occasional offer post with a relevant next step. For every post, set out the reader, the one goal, the central argument, the source material, a suggested format and what we want the reader to do. Check for repeated topics, overlapping arguments, claims without support, and too many sales posts. Write full briefs for week one and shorter outlines for weeks two to four. Leave one slot a week open for a timely swap, since the calendar doesn’t have to stay fixed.

Setting it up in ChatGPT Dots: make the calendar a responsibility the dot owns over time, and ask for one line per post naming the source file behind it. Have it keep the calendar on a shared Page, slot in the timely swap when prompt 3 finds something better, and flag any slot that has lost its evidence. Changes then appear on the Page instead of in a new file each week.

Choose your posting days with the best time to post on LinkedIn tool. The dot keeps the plan current and you publish. Tell it which calendar changes need you, such as a slot with no approved source, and which routine reshuffles can wait.

Why it matters: A good calendar cuts weekly planning time and still leaves room for better ideas, new evidence and changes in the market.

7. How do you get drafts that say something?

The research should settle the argument before the dot starts polishing sentences. Without that, you get clean prose that takes several paragraphs to say the obvious.

Write three LinkedIn drafts from these approved briefs: [briefs]. Follow my business context and voice guide. In each draft: make one clear argument for one reader; open with a specific observation, tension, result or question that the brief supports; explain the reasoning with a concrete example; use bullets where they make parallel items easier to scan; vary sentence and paragraph length, with the odd one-line paragraph for emphasis; and finish with a useful implication or a natural next step. Aim for [180–300 words] unless the idea needs a different length. Avoid restating the same ending, invented personal stories, inflated promises and formula contrasts. Give me two alternative openings and say briefly how each shifts the emphasis. List any missing evidence separately from the copy I could publish.

Setting it up in ChatGPT Dots: tell the dot where drafts go, such as a private Slack channel for drafts and ChatGPT for questions, so routine output doesn’t bury decisions. Away from your desk, you can approve a draft or send it back from the mobile app; it is the same dot on every device, and your Hand off to you rule keeps the last step with you.

When an opening feels flat, generate a few more in our LinkedIn hook generator. If a draft needs a stronger structure, run it through the LinkedIn post booster before you return it to the dot with your notes. Ask the dot to label each draft with the brief it came from, so every claim can be traced before you publish.

Why it matters: Clear limits give you drafts that are easier to judge, so your review is about the argument and not about cutting filler.

8. How do you set up a separate editorial review?

Give the reviewer a defined job: find the weak spots in a draft and say how to fix them. A reassuring “This is strong” isn’t an editorial process.

Check these LinkedIn drafts against the brief, the source material, my business context and my voice guide. Score each one out of 100: customer relevance up to 25; specificity and evidence up to 25; strength and clarity of the argument up to 20; match with my voice up to 20; readability and formatting up to 10. Show what each score is based on. Verify every factual claim, flag generic passages, and mark repetition, abrupt one-line fragments and paragraphs that would read better as lists. Return a revision ready to publish, a short note on the changes that matter, and any open questions. Treat invented evidence, leaked confidential information or a misquoted source as a blocker whatever the score. Keep everything in the review document for a human to approve.

Setting it up in ChatGPT Dots: ask the dot to send the review to a separate cloud thread so it doesn’t grade its own writing in the same conversation. The thread shows up as its own conversation on desktop, web and mobile, so you can read the scores there. In the desktop app you can follow it under Activity in the dot’s profile, where each job lists its files, results and any request for your input.

Before you approve, look at the revision as it will appear in the feed with our LinkedIn post preview, and tidy line breaks with the LinkedIn Text Formatter. The dot can send follow-up instructions to jobs it created, so once you answer the open questions, ask it to pass them to the review thread for a final pass.

Why it matters: A scoring rubric makes your standards explicit. The score organises the feedback, while the source checks and your own judgment decide whether the post is ready.

What should you do in the first hour after you publish?

Every MAXXING technique points at the same moment: the first hour after a post goes live, when you want as many reactions as you can get.

Start with people you can reach directly. Colleagues, friends, family, clients: anyone you can message yourself. Their reactions are the ones worth asking for.

If you don’t have that circle yet, a community can help, provided the people in it are real and the activity is moderated. The groups we checked for other articles are listed in the next section.

LinkedInLikes is our own community. Members like, comment on, repost and save each other’s posts by hand from their own LinkedIn accounts, and write comments in their own words. You paste the post link, choose the action, and set how many actions you want and how many points each one is worth. New accounts get 100 starter points, and you get more by helping other members, up to 600 points a day. If someone confirms an action they didn’t do, you can report it within 72 hours and the points are taken back, and we remove accounts we detect as automated.

Keep the dot out of this step: add your post to LinkedInLikes yourself, the same way you publish, comment, connect and message on LinkedIn yourself. Ask members to comment on your post.

Which LinkedIn groups can you join for early reactions?

We checked these free communities on Oct 21, 2026, and the member counts are what each platform showed on that date. Each group has its own admins and rules, so read the pinned message before you post.

If you’d prefer to skip group chats, add your post to LinkedInLikes and members will find it in the shared list.

Part 2: pipeline and performance (prompts 9–12)

9. How do you write content around deals that got stuck?

Some of your most useful posts can answer a worry several prospects raised in private. The aim is to explain the issue well enough that future customers arrive better informed.

Look through the CRM records and call notes I have shared for qualified deals that got stuck during [period]. Find the objections that recur and separate: objections stated outright in conversations; possible explanations nobody has confirmed; and operational delays that content is unlikely to fix. For each repeated objection, note the customer’s role, the deal stage, the evidence we have and the question a useful LinkedIn post should answer. Suggest five content briefs. Each should present the concern fairly, show where our approach fits, admit where it doesn’t and name the proof needed. Draft the two strongest posts without naming prospects or revealing deal details. In a separate list, suggest approved resources we already have that a salesperson could share in a relevant conversation.

Setting it up in ChatGPT Dots: connect your CRM as a plugin if one is available on your account, and set it to read-only so the dot can study deals without changing them. Plugin permission levels sit under Settings > Plugins, where Always ask is the strictest. If the plugin can write, add a Custom Rule for CRM changes set to Ask before taking action.

Deal notes are exactly the private material a dot handles with care: before it shares anything from a private conversation with other people, it checks that you have allowed it. If the dot runs in a team Slack channel, state plainly that prospect names stay out of that channel. Any drafting job it delegates should receive only the anonymised objections, because a new job sees just the context the dot passes to it.

Why it matters: It links marketing to the questions salespeople answer again and again, and it keeps you from writing persuasive posts about problems your customers don’t care about.

10. How do you prepare replies to LinkedIn conversations?

When someone responds to a post, the right next step depends on what they said and whether a business conversation would be welcome. A like on its own doesn’t show business interest.

Go through these LinkedIn conversations I have shared: [comments, inbound messages or interactions I logged by hand]. Sort them into: questions that deserve a useful public answer; conversations where sharing a resource would help; clear interest in our offer; and general discussion with no business next step. For each relevant conversation, sum up the person’s stated need, the business context we have and what we still don’t know. Draft a reply that deals with what they actually wrote before bringing up anything else. Where it fits, suggest one follow-up question or an existing resource. Don’t read business interest into a like, don’t pretend to know someone, and don’t push a meeting request into a conversation that can’t carry one. Keep every reply as a draft for me to review and send.

Setting it up in ChatGPT Dots: forward comments to the dot from wherever you are, a Slack DM on your phone included, and get the briefs back in the same place, one row per person. The dot treats a direct request in the conversation as approval, so phrase this one as “draft only”; your Hand off to you rule covers anything that would go out on LinkedIn.

For a quick public reply in a different tone, compare its draft with one from our LinkedIn comment generator. You can also talk a tricky reply through with the dot on a call; ending the call doesn’t stop work you gave it during the call, so the draft arrives afterwards. Ask it to keep a short note of who you have already answered so the next batch skips them.

Why it matters: Preparation makes your replies more thoughtful without turning every exchange into a sales sequence. Sometimes the right result is simply a useful answer.

11. How do you report LinkedIn results with honest attribution?

Impressions tell you how widely a post travelled. They can’t tell you whether the right people got interested or whether a post helped close a deal.

Combine the LinkedIn analytics, tracked website visits, inbound inquiry records and relevant CRM data I have shared for [period]. Report on: reach, reactions and comments by post, topic and format; qualified inbound conversations; resource sign-ups and demo requests where we track them; opportunities with a documented LinkedIn contact; and the time spent producing and reviewing content. Keep directly tracked conversions, self-reported discovery and possible influence apart. Don’t attribute a whole deal to LinkedIn because one contact reacted to a post. Mark posts that reached relevant customers, posts that reached a wide but less relevant audience, and posts with too little data to judge. End with three findings, three limitations and one experiment to try. Where you can, compare posts at the same age so new posts aren’t judged against older ones.

Setting it up in ChatGPT Dots: save this as a monthly schedule with a time zone and an end date, and say where the report should go. Ask the dot to hand the document itself to ChatGPT Work and to tell you which export it was missing. If a source needs a website login, the dot sends you a private sign-in request instead of asking for credentials in the chat.

A finished run doesn’t prove the report is right, so open it and check the sources before you share it. For posts where the analytics export has gaps, log a consistent estimate from our LinkedIn impressions calculator. Ask the dot to start the report with the date range, the exports it used and any posts it left out, so next month’s comparison is like for like.

Why it matters: Better reporting gives you a reason to repeat or change an approach, and it shows uncertainty openly instead of turning patchy tracking into a confident revenue claim.

12. How do you turn your edits into a better system?

Every draft you edit carries information about your standards. Write down the lessons that repeat and you will spend less time fixing familiar problems.

Compare the original drafts, my edits, the published versions and whatever performance data we have from [period]. Find: voice corrections I keep making; claims that needed more evidence; ideas that got clearer after a change of framing; formatting changes that made posts easier to read; and topics that led to useful customer conversations. Propose updates to the voice guide, the research briefs and the editorial checklist. For each proposed rule, give an example, explain what it is for and note when an exception might make sense. Keep style preferences apart from performance hypotheses. Don’t turn one post that did well or badly into a permanent rule. Return a short change log for me to approve and suggest one controlled experiment for next month.

Setting it up in ChatGPT Dots: the dot is already gathering this material, because it updates its notes as you decide things and can search your past ChatGPT conversations for earlier decisions. Once you approve the change log, ask it to update the voice guide Page, rewrite its own notes, drop notes that no longer apply, and read back what it changed or removed.

Then check under Scheduled that the recurring prompts use the new guide. Stopping a job doesn’t undo what it has already done, so approve rule changes before the dot applies them to scheduled work.

Why it matters: This is how the workflow gets easier to run over time. Your corrections become guidance the dot can use, and performance ideas stay testable instead of hardening into superstition.

How do you roll out all 12 prompts?

Add the workflow in stages so you can check the output before you add another recurring job.

For every recurring job, define its inputs, destination, frequency and owner. Test one run before relying on the schedule, and have the dot report missing access or unfinished work.

A dot decides on its own when to wake up and follow up, but work that repeats at fixed times needs a saved schedule. Give it four things: what to check or update, when to run (with a time zone and an end date), which changes deserve a message, and where to deliver results. Ask it to confirm what it saved.

In the dot’s profile, Scheduled shows recurring work and Activity shows delegated jobs and their results. Pause stops the current main job; recurring work is cancelled separately under Scheduled. If you already use ChatGPT Work automations, the dot can read and edit those as well.

A saved schedule for prompt 2 could say: “Every weekday at 7 AM [time zone] until [end date], check the [call notes channel] for new conversations, add new quotes to the customer questions Page, and message me in Slack only if a theme moves into the top 10. Confirm the schedule.” When a connected service supports events, you can ask the dot to respond to new messages there instead of checking on a timer; ask it to confirm which events it can follow.

You don’t need 12 scheduled jobs on day one. Start with the job that eats the most time and produces output you can judge reliably.

What a ChatGPT dot can and can’t do for your LinkedIn

A dot can organise research, find useful evidence, prepare drafts and learn from your edits. The quality still depends on the experience and judgment you bring. The dot keeps the work moving between conversations; deciding what is worth saying stays with you.

That means holding a real opinion, being willing to explain it, and noticing when a polished draft says something you would never defend in person.

When the workflow starts producing posts, you can add them to LinkedInLikes for early likes and comments from members. Otherwise, open your dot, load your context and run prompt 1; better inputs make every later step more useful. For a wider setup, read how to build an AI content system for LinkedIn or the 2027 LinkedIn marketing playbook.