Automate a Workflow · Lesson 2Pro~14 min readMulti-step + AI stepsBuilds on Lesson 1

Multi-step automations — with AI in the middle.

A one-step automation moves data; a multi-step one does the work. This lesson chains several apps together and drops AI into the flow — to summarize, classify, draft, and route — so the automation makes the small judgments a human used to make. Then you branch on the result and map data cleanly across apps.

The mental model

Real automations chain several steps — and the magic step is AI in the middle.

A one-step automation moves data. A multi-step one does work: it gathers, then an AI step reads and decides (summarize this, categorize that, draft a reply), then it routes the result to the right place. That AI-in-the-middle step is what separates dumb plumbing from an assistant that handles the task.

The Reframe

The AI step is where judgment goes. Anywhere your old process needed a human to read something and decide, that’s a place an AI step can slot in — summarizing, classifying, or drafting.

Step 01 Chain the steps

Extend WHEN-DO into a sequence: when X → do A → then B → then C. Each step’s output feeds the next.

Multi-step promptBuild a workflow: when [trigger], first [step A], then [step B], then [step C]. Pass the result of each step into the next. Show me the data at each stage so I can confirm it’s right.

Step 02 Add AI in the middle

Insert a step that reads content and produces a decision or output:

Summarize — turn a long email or document into the key points.
Classify — “is this a complaint, a question, or a sale?”
Draft — generate a reply or a record from the input.
Extract — pull the date, amount, or name out of messy text.

AI-step promptIn this step, read the incoming [content] and [summarize it in 2 lines / categorize it as A, B, or C / draft a reply]. Output only [the format the next step needs].

Step 03 Branch on the result

Use the AI step’s output to route: if it’s a complaint, send to the support channel; otherwise, log it and move on. Conditional paths are where automations start to feel intelligent.

Step 04 Map data cleanly across apps

Most breakage happens at the seams between apps — a date in the wrong format, a field that doesn’t exist. Be explicit about which field maps to which, and what to do with anything missing.

Multi-step automations fail silently — a step errors and you never notice the leads stopped arriving. Always add a “tell me if anything fails” step that notifies you, and check it for the first week.

Your challenge: build a smart workflow

Build a multi-step automation that makes a decision:

Chain a trigger into at least three steps.
Add one AI step that summarizes, classifies, or drafts.
Branch the flow based on that AI step’s output.
Add a failure notification and run it on real data.

That’s an automation doing real, judgment-bearing work. Next, make it production-grade — reliable, monitored, and safe to roll out to a team. That’s Lesson 3.

Next: production automations →Back to Automate a Workflow

What you can do now

Chain a trigger into a multi-step sequence
Insert an AI step to summarize, classify, draft, or extract
Branch a workflow based on an AI decision
Map data cleanly across apps and handle missing fields
Catch silent failures with a notification step

Pro+

Up next in Automate a Workflow

Lesson 3 · Production automations — reliability & team rollout

Triggers that scale, error handling and retries, monitoring and alerts, and rolling an automation out to a whole team without it breaking. Go to Lesson 3 →