Duration
120 minutes
Workshop Snapshot
01Audience
Beginners / no-code builders / working professionals
Tools
Relay or similar, form tool, Google Sheets, Slack or email, AI step/agent builder
Running Example
Lead capture workflow: form submitted, lead saved, notification sent, AI summary added, agent scoped
Learner Output
One mapped workflow, one basic automation, one AI step, one scoped first agent
Core Rule
Working beats perfect. Keep the first version narrow.
Automation handles structure. AI handles flexible thinking. Agents pursue a narrow goal with tools and boundaries.
120-Minute Agenda
02| Time | Segment | Facilitator Job | Learner Output |
|---|---|---|---|
| 0:00-0:10 | Frame + mental model + use case | Define automation, explain the automation to AI workflow to agent progression, and introduce the lead-capture use case. | Understands the workshop arc. |
| 0:10-0:22 | Find your automation target | Have learners list repetitive, low-judgment, annoying work. | One automation target. |
| 0:22-0:38 | Map the lead capture workflow | Map the shared lead-capture workflow using Trigger, Inputs, Steps, Output. | Shared workflow map. |
| 0:38-0:43 | Demo 1: basic automation | Show Relay form trigger, Sheets row, and Slack/email notification. | Sees the target build. |
| 0:43-1:05 | Practice 1: build & test | Learners build and test the basic Relay automation. | Working automation or documented blocker. |
| 1:05-1:35 | Demo 2 + Practice 2: add AI | Demo the AI step, then learners add summarization/classification to their workflow. | AI-enhanced workflow. |
| 1:35-1:45 | Agents: what they are & how to scope | Contrast fixed automations with goal-driven agents, then define goal, tools, instructions, boundaries, output, and review. | Agent scope. |
| 1:45-2:00 | Demo 3 + Practice 3: build the agent + close | Demo the narrow agent, learners build or draft their first version, then close with humans in the loop, share-out, and takeaways. | Narrow first agent, review checkpoint, and next test. |
What To Teach
031. What Is Worth Automating?
Use three signals:
- Repetition: it happens again and again.
- Low judgment: it does not require deep thinking every time.
- Friction: it is annoying, slow, forgotten, or wasteful.
Shortcut: Frequency x Time x Annoyance.
2. Workflow Mapping
TriggerWhat starts the workflow?
InputsWhat data comes in?
StepsWhat happens in order?
OutputWhat do you get at the end?
Key line: If you cannot explain the workflow in plain English, you are not ready to build it.
3. Automation vs. AI Workflow vs. Agent
- Automation: fixed path. Example: form submitted to sheet to notification.
- AI workflow: fixed path with AI interpretation. Example: AI summarizes and classifies the lead.
- Agent: narrow goal with flexible steps. Example: research the lead, evaluate fit, draft a reply.
§ 05
Step-by-Step
Demo Scripts
Keep demos tight. Demo 1 stands alone; Demos 2 and 3 immediately lead into the matching practice block.
Demo 01 · Automation
Open Relay template: lead-capture automationGoal
Show a simple fixed-path automation: form submitted, lead saved, notification sent.
Step-by-Step
- Open the pre-built Relay workflow.
- Point out the form submission trigger.
- Show the Google Sheets action and mapped fields.
- Show the Slack or email notification action.
- Submit one test form and show the Sheet row plus notification.
Facilitator Line
"This is automation: a trigger starts a fixed sequence of steps."
Demo 02 · AI Workflow
Open Relay template: lead-capture AI workflowGoal
Show how the fixed automation becomes smarter when AI summarizes and classifies the lead inquiry.
Prompt to Use
TASK: Summarize this lead inquiry in one sentence. Then classify the lead as high intent, medium intent, or low intent.
CRITERIA:
High intent: specific business problem, clear interest, asks for demo or next step.
Medium intent: interested but vague or exploratory.
Low intent: unrelated, unclear, or no business need.
OUTPUT FORMAT:
Summary:
Intent:
Reason:
Step-by-Step
- Open the workflow with the AI step added after the trigger.
- Pass the form message into the prompt.
- Update the Slack/email notification to include summary, intent, and reason.
- Submit a lead with a long message and show the summarized notification.
Facilitator Line
"The automation still handles the structure. The AI handles the flexible thinking inside the structure."
Demo 03 · AI Agent
Open Relay template: lead-capture AI agentGoal
Turn the workflow into a narrow agent without making it dangerously broad.
Agent Brief
GOAL: Evaluate inbound leads and draft personalized replies.
TOOLS: Lead form data, Google Sheets, web research, email draft.
INSTRUCTIONS: Research the company, identify the primary business problem, decide whether the lead is high quality, and draft a concise response.
BOUNDARIES: Draft only. Do not send automatically. If information is missing, ask a follow-up question.
OUTPUT: Fit assessment, reason, draft reply, recommended next step.
Step-by-Step
- Start from the AI-enhanced workflow.
- Replace the single classification task with the broader lead-evaluation goal.
- Add only the tools the agent needs.
- Write boundaries before testing.
- Run one test lead and inspect the draft before approval.
§ 06
From Listening to Doing
Practice Activities
Only run these three hands-on blocks. The AI and agent practices happen immediately after their demos.
0:43-1:05 · Practice 1
Build Your First Relay Automation
Objective: Create one working automation with one trigger and at least two actions.
- Set the trigger.
- Add a storage action, such as Google Sheets.
- Add a notification action, such as Slack or email.
- Run one successful test.
- Submit what it does plus a screenshot or short description of it working.
1:10-1:35 · Practice 2
Add One AI Step
Objective: Upgrade the automation by adding one simple AI task.
- Choose summarize, classify, draft, or extract.
- Write a specific prompt for the AI step.
- Use the AI result later in the workflow.
- Test and compare the output before and after the AI step.
1:50-2:00 · Practice 3
Build a Narrow First Agent
Objective: Ship the first version of an agent that does one useful thing well.
- Define the agent goal.
- Choose the tools it can use.
- Write instructions and boundaries.
- Define the output.
- Run one test case and submit how it works, with screenshots or a link if possible.
§ 11
Anticipated Questions
FAQ & Q&A
Short answers facilitators can use without turning the workshop into a technical lecture.
Automation Questions
"How do I know if something should be automated?"
Look for repetition, low judgment, and friction. If it happens often, takes time, and annoys you, it is a candidate.
"What should not be automated?"
Anything that requires nuanced judgment, trust, personal relationship, high-stakes decision-making, or sensitive data should start with human review.
"What if my workflow has lots of branches?"
Start with one path. Build the most common path first. Add branches only after the basic version works.
"Do I have to use Relay?"
No. Relay is the workshop example. The principles transfer to Zapier, Make, n8n, Airtable automations, or other workflow tools.
AI Workflow Questions
"Where does AI fit best inside an automation?"
Use AI where information needs to be summarized, classified, extracted, drafted, compared, or transformed.
"Can I trust the AI classification?"
Treat it as a useful first pass. For important outcomes, review it or route uncertain cases to a human.
"Why not make the AI do everything?"
Broad AI tasks are less reliable. Simple, narrow AI steps are easier to test, debug, and trust.
Agent Questions
"What makes an agent different from an automation?"
An automation follows predefined steps. An agent has a goal and can decide which steps to take within boundaries.
"Do agents need tools?"
Useful agents usually do. The AI model reasons; tools let it search, read, write, update, draft, or retrieve information.
"What is a good first agent?"
A narrow one: lead qualification, meeting summary, content research, email drafting, or vendor intake. One goal, few tools, clear output.
"Should the agent send emails automatically?"
Not for v0.1. Have it draft emails and send them to a human for approval. Add autonomy only after repeated successful tests.
§ 13
Pre & Post Flight
Before & After
Click each item as you complete it. The state lasts only in the current browser session.
Before the Session
- Review source transcripts end-to-end
- Prepare the lead-capture form
- Create a clean Google Sheet for demo leads
- Confirm Relay account access
- Confirm Slack or email notification access
- Build the demo automation once before teaching
- Prepare a test lead message for AI summarization
- Prepare screenshots for each critical step
- Print opportunity and workflow worksheets
- Print agent design canvas
- Prepare fallback if tool access fails
After the Session
- Collect automation screenshots or descriptions
- Collect AI step prompts that worked well
- Collect agent capstone submissions
- Send recap with worksheets and prompt templates
- Send reminder to test workflows with real data
- Ask learners where the workflow broke
- Update FAQ with new questions
- Replace weak demo screenshots
- Note which workshop segment ran long
- Pick one learner build to feature next time
Facilitator Reflection
- Which segment produced the clearest learner outputs?
- Where did learners get stuck: idea selection, mapping, tool setup, AI prompting, or agent scoping?
- Did the lead-capture example feel relevant to this cohort?
- Which AI prompt generated the best output?
- Were learners too cautious, too ambitious, or appropriately scoped with agents?
- What should change before the next run?