Steps to build your own biz dev agent workflow
This resource is based on The AI outreach stack that handles prospecting, follow-up, and scheduling, featuring Amanda Pressner Kreuser of Masthead, published on the AI Lab by ActiveCampaign.

Get the checklist
By the end of this checklist, you’ll have five custom GPTs that handle prospecting, outreach, scheduling, follow-ups, and tracking for your business development workflow. This is based on the system that Amanda Pressner Kreuser built at Masthead, a content marketing agency. She estimates the setup saves her 4–5 hours each week.
Before you start
- Set up a ChatGPT Plus account: custom GPTs require a paid plan
- Identify your ideal customer profile (ICP): define your target titles, industries, and company size thresholds
- Gather your email templates: collect 5–15 of your most-used outreach and follow-up emails
- Set up LinkedIn Sales Navigator: needed for the prospecting phase
- Create accounts on PhantomBuster and Hublead: for data extraction and CRM sync
The workflow
Phase 1: Create your meta-prompt process
After this phase, you’ll have: a repeatable method for generating custom GPT instructions without writing prompts from scratch
- Open ChatGPT and describe what you need: (copy and edit the Starter prompt below)
- Answer ChatGPT’s clarifying questions: provide details about your tone, templates, requirements, and typical outputs
- Copy the generated prompt into the custom GPT “Create” interface: this becomes the foundation for your specialized tool
Starter prompt
I want to set up a custom GPT to do [TASK], and I want you to help me create a prompt for this custom GPT so I never have to write these same instructions again.
“I used to be so perfectionistic about my first drafts. Now I’ve been able to become more relaxed, just saying what’s in my brain, saying it imperfectly, and getting AI to provide a draft that organizes my thoughts.”
Phase 2: Build prospecting and outreach agents
After this phase, you’ll have: a Referral Scout GPT that filters LinkedIn contacts against your ICP, and an email library GPT that drafts personalized outreach
- Run a LinkedIn Sales Navigator search: pull up profiles from a contact who offered introductions
- Extract contact data with PhantomBuster: export names, job titles, and company information from your Sales Navigator results
- Create a “Referral Scout” custom GPT: upload your ICP criteria so the GPT can scan exported lists and recommend who to connect with
- Sync LinkedIn contacts to your CRM with Hublead: this tool guesses email addresses for your curated prospect list
- Compile your email template library: gather 10–15 templates covering re-engagement, referrals, follow-ups, and new outreach
- Create an “Email & Follow-Up Library” custom GPT: upload your template library so the GPT generates drafts that match your brand voice
- Test with a real outreach scenario: give the GPT details on audience and goals, review the draft, and edit in a separate doc
Phase 3: Build scheduling and follow-up agents
After this phase, you’ll have: a scheduling assistant that suggests meeting windows and a follow-up GPT that drafts personalized emails from call recordings
- Export your calendar as a JSON file: use Google Apps Script, n8n, or a manual export
- Create a “Scheduling Assistant” custom GPT: upload the JSON and use the Scheduling prompt below
- Create a “Follow-Up” custom GPT: upload your email templates and configure it with your voice, signature, and sales stage definitions
- Test the follow-up GPT with a real call recording: feed a transcript and specify the sales stage to get a personalized draft
Scheduling prompt
You are my scheduling assistant. I’ve uploaded a JSON file containing my calendar events for this week. Identify 3–5 open time slots that are:
- 30 or 60 minutes long
- Between [START_TIME] and [END_TIME] [TIMEZONE], Monday to Friday
- Not adjacent to another meeting unless there’s at least a 15-minute buffer
- Excluding events labeled as [BLOCKED_EVENT_TYPES]
Present the results in a table with: Date, Time Range, Duration, and Why it’s a good time.
Phase 4: Build your tracking system
After this phase, you’ll have: an automated spreadsheet that logs outreach activities without manual data entry
- Ask ChatGPT to generate a Google Apps Script using the prompt below: describe what you want to track (email opens, responses, follow-up sequences, engagement levels)
- Create the Google Sheet for tracking: set up columns for the metrics ChatGPT recommended
- Install the script in Google Apps Script: follow ChatGPT’s instructions for where to paste and authorize the code
- Verify the script runs correctly: send a test email and confirm it appears in your tracking sheet
Google Apps Script prompt
I need a Google Apps Script that connects to my Gmail inbox and logs outreach activities to a Google Sheet. Track: [LIST_OF_METRICS]. Organize by [CONTACT_NAME/DATE/STAGE]. Tell me exactly where to input this script.
Quick reference
- Total time: 4–6 hours for initial setup across all five agents
- Tools needed: ChatGPT Plus, LinkedIn Sales Navigator, PhantomBuster, Hublead, Google Apps Script, Google Sheets
- Key output: Five custom GPTs that handle prospecting, outreach drafting, scheduling, follow-ups, and activity tracking
Ready for the full story?
Read The AI outreach stack that handles prospecting, follow-up, and scheduling, featuring Amanda Pressner Kreuser of Masthead, published on the AI Lab by ActiveCampaign.
Related
More data from the AI Lab.