Slot usage
1 slot
Estimated execution time
~10 seconds per query
What you'll need
- A list of LinkedIn profiles you want to personalize messages for
- A clear prompt or template describing the type of LinkedIn message you want (tone, length, objective)
-
Available PhantomBuster AI credits
→ See the full breakdown of all input fields in the detailed section below.
What you’ll get
-
AI-generated, personalized LinkedIn connection or outreach messages for each lead
→ See the full breakdown of all output fields in the detailed section below.
Before you start
- AI Phantoms don’t extract or post anything on your behalf, they use the data you already have to generate AI-written messages, insights, or other text results (depending on the Phantom you’re using).
-
Awareness of AI credit usage:
- GPT-3.5 Turbo → lowest cost.
- GPT-4o Mini → enhanced capabilities at moderate cost.
- GPT-4o / GPT-4 (Legacy) → highest capabilities, highest cost.
- For testing your prompts, we recommend limiting to 10 leads first.
Step 1: Select your leads
You can choose the leads to enrich by:
-
My Lists:
Choose a saved LinkedIn Leads list you’ve already created in PhantomBuster.
If your goal is to segment or filter leads within the LinkedIn Leads page, it’s best to use this input type.- Go to your LinkedIn Leads page and create a new list using a relevant filter.
- Use that LinkedIn Leads list as the input for this Phantom.
→ This ensures the AI data is properly synced to your Leads Database, so you’ll see the generated AI messages directly on your LinkedIn Leads page.
-
A URL:
- Provide a Google Sheet with LinkedIn profile URLs (make sure it’s shared with “Anyone with the link”).
- Upload a CSV file with LinkedIn profile URLs (make sure it’s publicly accessible, and note that CSV upload is only available on paid plans).
-
My Phantoms:
Use results from another Phantom as input.
This Phantom only updates your LinkedIn Leads page when the input is a LinkedIn Leads list.
If you use a CSV file, Google Sheet, or another Phantom as input, the AI-generated data won’t be written back to your Leads page.
Step 2: Choose your GPT model and add your prompt
-
Select a GPT Model you want to use:
- GPT 3.5 Turbo – basic, lowest cost.
- GPT 4o – advanced, higher cost.
- GPT 4o Mini – enhanced, moderate cost (recommended default).
- (Legacy) GPT-4 – medium capabilities, highest cost.
-
Select a prompt template or write your own:
- Use one of the pre-written prompt templates:
- Connect based on similar work experience (LinkedIn Connection Message)
- Connect with anyone (LinkedIn Connection Message)
- Recruitment (LinkedIn Connection Message)
- Pitch your product (LinkedIn Connection Message)
-
Edit a template directly:
- Once selected, the full prompt text appears in the editor.
- You can adapt the instructions to your specific needs (e.g., change the tone, add formatting rules, etc.).
- Or create a custom prompt tailored to your needs.
- The more specific your instructions, the better the output (define task, tone, format).
- Use one of the pre-written prompt templates:
-
Specify columns to feed to GPT:
- Decide which data GPT should use:
- All LinkedIn Leads Data (recommended for best results).
- Or Custom selection → Specify only certain fields (e.g., firstName, job, company).
- Only the columns you select will be passed to GPT, make sure they contain the info needed for your prompt.
- Decide which data GPT should use:
AI Phantoms require all selected fields to be present in your input data to function correctly.
For example, if your prompt references First name and Last name but some leads don’t include those fields, the Phantom will return this warning:
“All input data has been filtered out. Ensure it contains the properties specified in the property list.”
→ If some data is missing, first run a LinkedIn Profile Scraper to enrich your leads before using this AI Phantom.
Advanced settings (dropdown in setup)
-
Name your results file (optional)
-
You can customize the file name.
If you rename the file between launches, the Phantom will create a new results file and start processing inputs from scratch.
-
-
Fields to keep (optional)
- Export only the fields you care about by listing them (comma-separated).
Example: profileUrl, job, location. - This generates a second CSV file with just those fields.
- Learn more in our guide: Customize how your Phantom results files are saved.
- Export only the fields you care about by listing them (comma-separated).
Step 3: Decide how many leads to process
You can control processing:
- Test mode: Run prompt on the first 10 leads (AI output overwrites each time) - Recommended for testing
- Partial run: Run prompt on a select number of leads.
- Full run: Run prompt on all leads (Phantom resumes where it left off, no duplicates).
Testing first saves AI credits before scaling.
Step 4: Select launch frequency
Choose how often the Phantom should run:
- Launch manually: Start the Phantom yourself whenever you need.
- Launch once at a specific time: schedule a one-time run at a set date and time.
- Launch repeatedly: schedule regular runs (e.g. once per day, several times during working hours).
- Launch after another Phantom: chain automations together so this Phantom starts right after another finishes.
- Advanced scheduling: customize the exact minutes, hours, days, or months when the Phantom should run.
→ For a complete walkthrough of scheduling options, see our guide to scheduling Phantoms automatically.
Step 5 (Optional): Advanced settings
Advanced settings are available if you want to fine-tune how your Phantom runs, but by default they’re already optimized for most use cases.
We recommend leaving them as they are unless a guide specifically instructs you to change something.
→ For a detailed overview of all advanced options (like execution limits, retries, email notifications, proxies, webhooks, and file management), see our Advanced settings guide.
Launch and results
When you’re ready:
- Click Launch to start your Phantom.
- Once it finishes, open the Results tab in the Phantom console.
- Download your results as a CSV or JSON file.
The Phantom adds a new column in your results file called ai_message. Each row in this column contains a personalized message created for that lead, based on their LinkedIn data.
→ To learn how to export your data to Google Sheets, integrate with other tools, or reuse it in more automations, check our Access and Export your Phantom Results guide.
Export and input limits on the Free plan
If you’re on the Free plan or Free trial, some features are limited:
- CSV exports include only the first 10 rows of results.
- CSV download links (for dynamic viewing in Google Sheets or integrations) are not available.
- JSON exports are not available.
- CSV upload as an input method is not supported.
To unlock all features, you’ll need to upgrade to a paid plan.
Use your AI messages in outreach Phantoms
Once your Phantom run is complete, you’ll find a new ai_message column in your results file: it contains the personalized messages generated for each lead.
You can reuse these messages directly in your LinkedIn outreach automations, such as:
Here’s how:
-
Select an outreach Phantom:
- Open the Phantom you'd like to use for your LinkedIn outreach.
-
Choose the AI LinkedIn Message Writer as your input Phantom:
-
In the Input step, select the AI LinkedIn Message Writer Phantom from your list of previously run Phantoms.
→ This ensures the outreach Phantom pulls in all messages from the ai_message column in your results file.
-
-
Insert the AI-generated message into your outreach:
- In the Message content step, look just below the message input box: you’ll see a list of available placeholders.
- Click on {ai_message} to automatically insert the tag into your message box.
→ The tag will appear directly inside the message field, telling the Phantom to send the personalized message created for each lead.
- Complete the setup and launch:
-
Finish configuring your Phantom and launch it.
→ Each lead will receive a unique, AI-generated message as part of your outreach.
-
What you give (Input) and What you get (Output)
This section gives you a detailed breakdown of everything you need to provide to run this Phantom, and everything you’ll receive once it completes.
What you give (Input)
| Type | Description |
|---|---|
| LinkedIn profiles | LinkedIn profile URLs |
What you get (Output)
| Type | Description |
|---|---|
| message | The AI-generated message |
Tips and troubleshooting
Common pitfalls
- Using a private spreadsheet (make sure it’s set to “Anyone with the link”).
- Credits: Always test with 10 leads first.
- Data columns: Ensure selected columns contain useful context.
- Overwriting: Using “first 10 leads” mode overwrites results each time.
If you run into errors or account issues
- Check how to troubleshoot your phantom using Logs.
- Browse the Fix Issues & Troubleshoot Errors section for solutions to common problems.
- Review our Automation Rate Limits by Platform guide.
- Check our Best Practices for Social Media Automation guide.
Suggested automations
After generating AI LinkedIn messages, you can:
- Send messages → with LinkedIn Outreach or LinkedIn Message Sender.
- Warm up leads → with LinkedIn Auto Liker or LinkedIn Auto Commenter.
- Enrich further → combine with LinkedIn Profile Scraper.