Beginner Playbook

AI Workflow Automation Playbook

Map your business as a single linear workflow, break every role into its constituent actions, and automate each one with a purpose-trained AI agent.

Time2–4 weeks for first workflow
ToolsWhiteboard + AI tool (ChatGPT/Claude)
CostFree to start
Strategy Automation B2B

How This Works

Most teams organize around roles: "We need an editor," "We need a marketer." But roles are abstractions. What you actually need are specific, repeatable actions performed consistently. A better approach: map every action your business performs, group them into workflows, and replace humans with AI agents trained to execute each action.

This playbook teaches you to:

The result: your business runs faster, cheaper, and more consistently—without hiring.

The Play: From Roles to AI-Powered Workflows

Roles Workflows GranularActions AI Agents Iterate
Why this works: Machines don't understand vague language—but neither do humans. The difference is you can watch a human and adapt. With AI agents, you improve the prompt the same way you would train a team member, making it clearer and more specific each time.
1

Map Your Business End-to-End

Draw your entire business as one linear workflow from start to finish.

Before you can automate anything, you need to see everything. Get a whiteboard and draw your business in one continuous flow. Start at the top: what does your customer see first? End when the customer has received the final output.

For Acme Inc (a 12-person accounting firm), the workflow might look like:

Example: Acme Inc Tax Preparation Workflow

Client signs up → Intake form sent → Documents collected → Data entered → Tax return calculated → Return reviewed → Return signed → Client portal access granted → Return delivered

This is your business map. If you can't draw it, you don't fully understand your business. The act of drawing forces clarity.

Components of Your Workflow

Break your business map into 5–8 big steps. Each step should be:

Step Type

Intake — Getting information into the system. Forms, uploads, data entry.

Step Type

Processing — Transforming the inputs. Calculations, transcription, sorting.

Step Type

Delivery — Getting the output to the customer. Email, portal access, signing.

Your Deliverable: The Business Workflow Map

A single document (digital or photo of whiteboard) showing your business as a linear flow. This becomes your north star for all future automation decisions.

Bridge to Phase 2: You now have the big picture. Next, you'll zoom in on each step and break it down into the irreducible actions that make it work.

2

Go Granular — Decompose Every Step

Break each high-level step into the 6–7 actions that make it work.

Under each big step from Phase 1, there are 6–7 actual actions. These are the real work. An accountant doesn't just "enter data"—they open the portal, pull the tax form, read the client's information, type it in correctly, verify it against the source, save it, and flag errors. Each of these can become an AI agent.

How to Break Down a Step

Pick one big step. Ask yourself: if I had to train someone to do this, what would I tell them to do, in order, step by step? Write it down. Then ask: can this be broken down further? Keep breaking until you can't reduce it anymore.

Example: Breaking down "Documents Collected" for Acme Inc

"Documents collected" sounds simple, but it's actually 7 actions:

  1. Check client's intake form to see which documents they need to submit
  2. Look at the client portal to see what's already been uploaded
  3. Send a reminder email for any missing documents
  4. Track which documents arrived and from when
  5. Verify each document is the right type (W2, 1099, etc.)
  6. Flag documents that look incomplete or damaged
  7. Notify the team when all documents are in

Each of these 7 actions could be an AI agent. "Send reminder email" is clear enough to train an AI. "Collect documents" is too vague.

Real Example: Hormozi Hotlines Video Production

Alex Hormozi's team uses this approach for video editing. "Produce a finished video" sounds like one job. In reality, it's 8 distinct AI agents:

1

Transcribe

AI transcribes the full hotline recording into text.

2

Segment

AI identifies different speakers (Alex vs. callers) and marks clip boundaries.

3

Find Tension

AI finds the highest-tension moment in each clip (the "hook").

4

Reorder

AI puts the high-tension moment at the start of the clip.

5

Clean Audio

AI removes all filler words (ums, ahs, repetitions).

6

Extract Insight

AI identifies the key data point or lesson in each clip.

7

Collapse Content

AI removes everything except the key insight and the hook.

8

Export

AI exports the final file in the right format for posting.

The power of granularity: Eight AI agents can each do one thing extremely well. One "video editor" agent would have to be incredibly complex and would fail more often. Specificity beats flexibility.

Criteria for an Irreducible Action

You've found an irreducible action when:

Your Deliverable: Granular Action Map

For each of your 5–8 big steps, a list of 6–7 irreducible actions. This should be in a document (spreadsheet or text) that your team can review. Format: Big Step > Action 1, Action 2, Action 3, etc.

Acme Inc Example Output

Step: Data Entered

  • Open the correct tax form in the system
  • Pull the client document uploaded to the portal
  • Transcribe the handwritten/printed numbers into the form fields
  • Cross-check each entry against the source document
  • Save the form and log the completion
  • Flag any ambiguous entries for accountant review
  • Move the form to the "ready for review" queue

Bridge to Phase 3: You now have a list of specific, trainable actions. Next, you'll pick the first action and build an AI agent to execute it.

3

Build Your First AI Agents

Train an AI agent on one action and watch it execute consistently.

Pick one irreducible action from your Granular Action Map. This will be your first agent. Choose something:

For Acme Inc, good first agents might be: "Flag missing documents from the intake form" or "Transcribe handwritten data into the system."

How to Train an AI Agent

Create a prompt. Your prompt is your agent's training manual. Here's the structure:

Prompt Section

Role: What are you? "You are a document verification specialist."

Prompt Section

Task: What do you do? "Your job is to check if all required documents are present."

Prompt Section

Instructions: How do you do it? Step-by-step specifics.

Prompt Section

Success Criteria: What does done look like? "Return a JSON with fields: missing_docs, ready_to_proceed."

Prompt Section

Examples: Show 2–3 worked examples of input and output.

Prompt Section

Edge Cases: What if X happens? "If a document is scanned sideways, mark it as 'needs_rotation'."

Build Your First Prompt: Example

Sample Prompt: Flag Missing Documents

Role: You are a document verification agent for a tax preparation firm.

Task: Verify that a client has submitted all required documents based on their intake form.

Instructions:

  1. Check the client's intake form (you will be given the list of required documents)
  2. Look at what's been uploaded to the client portal (you will be given a list of files)
  3. Compare: is each required doc present?
  4. If a required document is missing, add it to the "missing" list
  5. If all required documents are present, set status to "complete"

Output format: JSON with fields: missing_documents (array of doc names), status (complete/incomplete), next_step (string)

Examples:

  • Input: Required = [W2, 1099-NEC, mortgage statement]. Uploaded = [W2.pdf, 1099-NEC.pdf]. Output: {"missing_documents": ["mortgage statement"], "status": "incomplete", "next_step": "Send reminder email for mortgage statement"}

Iterate the Prompt

Run your agent on 5–10 real examples from your business. Track what goes wrong. Update the prompt. Run again. This is how you train an AI agent—the same way you'd train a human employee. Each iteration makes the prompt clearer and the agent smarter.

Common mistake: Writing vague prompts like "be thorough" or "double-check your work." AI doesn't understand these. Instead, write: "Check each field against the source document. If a value differs by more than $10, flag it for review."

Tools You'll Need

You can build agents with:

Start simple: test your prompt in ChatGPT, then automate once it works.

Your Deliverable: Trained First Agent

A prompt that an AI can execute consistently on your chosen action. Evidence that it works: results from 5–10 test runs, side-by-side with what your team member would do, showing the agent is 85%+ accurate.

Bridge to Phase 4: You've proven the concept: one specific action can be automated reliably. Now you'll expand this approach across your entire business.

4

Expand and Iterate

Automate every remaining action and build a flywheel of continuous improvement.

You have one working agent. Now you build the rest. The pattern is the same: pick an action, write a prompt, test, iterate, automate. This is how Hormozi's team went from manual video editing to 8-step AI pipeline. This is how you scale.

Expansion Strategy

Don't try to automate everything at once. Instead, follow this sequence:

1

Week 1: First Workflow

Go deep on one complete workflow (one of your 5–8 big steps). Build agents for all its actions. This is your proof of concept.

2

Week 2–3: Second Workflow

Pick the workflow with the second-highest impact. You'll move faster because you now understand the pattern. Copy prompts where possible, modify where needed.

3

Week 4+: The Rest

Once two workflows are automated, the third is easy. Each subsequent workflow takes less time.

How to Track Progress

Create a simple spreadsheet:

Automation Tracker

Columns: Big Step | Action | Owner (person currently doing it) | Status (Not Started / In Progress / Testing / Live) | Time Saved / Week | Notes

Update this weekly. Watch your automation coverage grow. This is your business's automation roadmap.

Iterate Your Prompts Continuously

As your agents run, track failures. A failure is an opportunity to improve the prompt. When an agent gives a wrong answer:

This is your learning loop. It never stops. The best prompts are ones that have been tested and refined 20+ times.

Scale Across the Organization

Once you have 2–3 workflows fully automated:

The leverage of an AI specialist: One person fluent in AI automation and your business can often automate 20+ actions across the entire company. They become a force multiplier for every department.

Focus Areas for Immediate Impact

Start with back-office functions. These are where AI excels and where time savings are measurable:

High-Impact Area

Invoicing & Receivables: Generate invoices, send reminders, process payments, reconcile accounts

High-Impact Area

Lead Nurture: Qualify leads, segment contacts, send personalized emails, schedule follow-ups

High-Impact Area

Customer Support: Route tickets, draft responses, pull knowledge base articles, escalate issues

The Future: AI Replaces Your CRM Interface

Within a year, you won't type into your CRM. Instead, you'll talk to an AI agent: "Get me all deals in this quarter that are below contract." The agent pulls it from your system instantly. Your CRM becomes a silent backend; the interface is conversational AI. This is already happening. Build automation today so you're ahead of this shift.

Your Deliverable: Automation Roadmap

A clear plan for the next 12 weeks: