"Don't replace a human with AI.Double your power instead."
Taught byIrina KellyUX Designer, Salesforce Leads AI-enhanced workflows at product, Creative AI team
The class in brief
Irina Kelly (Salesforce) taught the AI-Enhanced Workflow Canvas: map a project's steps, then work down through desired outcome, barriers, AI use case, tools, and how your own role shifts. Dom and Tony opened with a debate on who owns creative value once AI speeds everything up. After this page you can map any real workflow onto the canvas, tag each AI use Automate, Enhance, or Advise, and stop starting every chat from a blank page.
The night at a glance
Why this matters · 6:21 PM
Clients are compressing time, not quality. Someone has to hold the line.
The night opened with the room's running AI-portrait debate, whether an artist should be paid for AI-assisted revisions, and who owns the vision through them . Dom's reframe: clients used to give three weeks for a creative exercise; now the request reads the same but assumes AI, and the time shrinks to one. A classmate read the market the same way from the job side: postings that once just asked for design skill now add "scale your design work with AI" as a qualifier, a year apart.
"We kind of have to stand up as protectors of curation, and what is good."
Dom, on the creative's job once AI compresses time
2
of three you get: good, fast, cheap. "Whatever tools we use to make the sausage, that's how long it takes to make the sausage."
1
year is roughly how long it took job postings to start asking designers to "scale your work with AI," per the room's own read of the market.
The framework · 6:44 PM
The AI-Enhanced Workflow Canvas
Irina opened her half of the night on the reframe the whole lesson sits on: organizations think "replace one human with AI." What she wants instead is everybody keeping their own AI partner and getting twice as capable . The canvas itself has one student per Miro frame: columns are your project's 4 to 6 high-level steps, and five rows go underneath.
01
Desired outcome"if I do it well, it will be…"
The adjectives you'd use to describe a step done right. This row is where the human expresses taste; that's the value nobody automates away.
02
Barriers"but first I must…"
Not a problem statement. The one hard thing you must actually do to reach the outcome, kept separate from what good looks like.
03
AI use case"it would be great if I had help…"
Where AI could take load off this step. Leaving it blank, "this stays human," is a valid answer.
04
AI tools"for this, I could use…"
Name the actual tool per step and tag it. One step can carry several tools.
05
My role"now I've become…, with more time for…"
How the job itself shifts once the row above is filled in. The night's real question, made concrete per project.
The blank Canvas template · 6:49 PM
The exercise · 7:16 PM
Work out your own workflow
The model answer
Irina's own six UX steps, filled all the way across.
She ran her own workflow (client briefing, brainstorm, research, and so on) through the canvas first, Desired Outcome and Barriers written out row by row, as the pattern to copy .
Homework: finish the last two rows, AI Tools and My Role, by the next class.
A canvas finished early
A classmate working on an auto-show booth project had a canvas filled end to end well before the room's quiet work block ended: a finished canvas, steps mapped from brief to install, each with its own barrier and AI use case named plainly rather than left blank.
Leaving a row blank is an answer
Irina's repeated point through the work block: a step with no AI Use Case entry isn't an unfinished row. It's the canvas telling you the step stays human, and that's worth writing down as deliberately as any tool name.
The craft · 7:55 PM
Three questions to ask of any AI use case before you name a tool.
Post-break, the AI Use Case row got its own vocabulary : can it Automate a repetitive task and just run (meeting notes, weekly research)? Can it Enhance by working with you (brainstorm, "upload a brief, give me 15 campaign territories with mood and headlines")? Or can it Advise, surfacing insight you couldn't reach alone, like reading a client's history to predict their objections before the meeting ?
3
mindsets to tag any AI use case against: Automate, Enhance, Advise. One step can carry more than one.
15
campaign territories, mood plus headlines, was Irina's own example of what "Enhance" looks like in one prompt.
The tools · 8:18 PM onward
Sorted by what they actually do
Irina's own habit, when a classmate asked how she keeps projects straight across so many tools: "I already have a workspace that knows so much about my project. I'm not starting from a blank state." One notebook or gem per client, reused every session, not a fresh chat each time the Communication category .
Research tools carried the same discipline further: NotebookLM answers only from what you upload, cites who said what, and says "I don't have that" instead of guessing, accuracy over creativity for work that has to be right. Perplexity's Model Council runs one question across Google, ChatGPT, and Claude at once and shows where they agree, disagree, and go their own way . On the design side, Figma Make turns a prompt into a click-through prototype and Figma Sites publishes it; on presentations, Gamma and Beautiful.ai draft a deck from a dump of thoughts so time goes to the story, not the pixels.
"I don't start from a blank chat. I have a workspace set up that already knows my project."
Irina, answering how she keeps projects straight across tools
Methods and prompts
Five methods to take with you
METHOD 01 · THE CANVASpart of: keep the judgment human
Map the workflow yourself first
Write your own steps, desired outcomes, and barriers before asking AI anything. The canvas only works if the taste (the outcome row) and the real friction (the barrier row) come from you.
Where it came fromTaught by Irina Kelly during the AI-Enhanced Workflow Canvas exercise in class 7, where each student mapped four to six steps of a real project and filled in the desired outcome and barriers before naming any AI use case.Use it whenReach for this when you are about to bring AI into a project and want to name what success looks like and where the real difficulty sits before letting a tool answer for you.
Here is one real workflow from my work, 4 to 6 steps beginning to end: [list them]. I'll write the desired outcome and the one barrier for each step first, then you check me: did I keep "what good looks like" separate from "what it takes to get there"? For any step I leave without an AI use case, tell me honestly whether "this stays human" is true, or whether I'm just avoiding it.
You will know it worked whenit names a specific step where you likely wrote a barrier instead of an outcome, or calls out a 'stays human' step you may be avoiding.
METHOD 02 · THE MINDSETSpart of: structure your ask
Tag each task Automate, Enhance or Advise
Every AI use case earns one of three labels before you pick a tool. The label tells you what kind of tool you actually need, not just that you need one.
Where it came fromIntroduced by Irina Kelly right after the workflow canvas exercise in class 7, as the vocabulary for the AI Use Case row: label each AI use as Automate, Enhance, or Advise before choosing a tool.Use it whenUse this once you have listed possible AI uses for a workflow and need to figure out what kind of tool each one actually calls for.
Here's my workflow with an AI use case noted for each step: [paste]. Tag each one Automate (runs on its own, set once), Enhance (works with me, brainstorm-style), or Advise (surfaces insight I couldn't get alone). One step can carry more than one tag. If a step doesn't actually need AI, say so plainly.
You will know it worked wheneach step in your workflow carries one of the three tags, and it says plainly if a step doesn't actually need AI at all.
METHOD 03 · THE WORKSPACE HABITpart of: context beats prompts
Prime a workspace instead of starting blank
Irina's own answer to "how do you stay consistent across tools": one notebook or gem per client, fed once, reused every session instead of re-explaining the project each time.
Where it came fromIrina Kelly's answer in class 7 when a student asked how she keeps projects consistent across different AI tools: she keeps one notebook or gem per client, loaded once and reused every session.Use it whenSet this up when you are starting repeated work on the same project and are tired of re-explaining the brief in every new chat.
Before we start: here is my project [upload the brief, brand material, past work, whatever you actually have]. Study it and hold it as context for this entire conversation. Don't make me re-explain the project every time I ask something new.
You will know it worked whenlater questions in the same conversation get answered using the project material you uploaded, without you having to repeat it.
METHOD 04 · RESEARCHpart of: go wide then narrow
Run one question through a model council
Perplexity's Model Council pattern, portable to any set of models you have access to: same question, multiple models, and the value is in where they disagree.
Where it came fromCovered in class 7 during Irina Kelly's research tools segment, describing Perplexity's Model Council feature, which runs one question across multiple models at once and shows where they agree or disagree.Use it whenUse this when a research question matters enough that you want to see where different AI models disagree, not just take one answer.
Research [topic], and before giving me one answer, show me where different models would agree, where they'd disagree, and what unique angle each brings. Then give me your synthesis and flag anything you're least confident about.
You will know it worked whenit names at least one specific point where models would disagree, not just a single averaged answer, and flags its own weakest point.
METHOD 05 · RESEARCHpart of: know where it fails
Ground the answer in your own sources
NotebookLM's core discipline, usable in any tool that supports uploaded context: the model answers only from what you gave it, and says so when it can't.
Where it came fromCovered in class 7 during Irina Kelly's research tools segment, explaining NotebookLM's discipline of answering only from documents you upload and saying so plainly when it cannot.Use it whenUse this when accuracy matters more than creativity and you need an answer that will not fill gaps with the model's outside guesses.
Working prompt
Answer only from the sources I've given you: [upload]. If something isn't in these documents, tell me you don't have it instead of filling the gap from general knowledge. Cite which source each claim comes from.
You will know it worked whenevery claim it makes is tied to one of your uploaded sources, and it tells you plainly when something isn't in them at all.
The close · 9:03 PM
The homework is the last two rows
The closing slide left the room with a fully-filled example canvas, tool logos named per step, as the target for the two rows Irina skipped for time . AI Tools: name the tool per step and tag it. My Role: finish the sentence "now I've become…, and I have more time for…." Due by the next class.
Try this prompt
Quiz me on the five rows of the AI-Enhanced Workflow Canvas and the three mindsets. Then hand me a small real workflow of mine and make me fill the canvas out loud, one row at a time.
You will know it worked whenit quizzes you on the five rows of the workflow canvas and the three mindsets first, then makes you fill the canvas out loud on a real workflow, one row at a time.
Related classes
Where this class connects
The shelf
Tools and references
Tools that night
The AI-Enhanced Workflow Canvas, one per student on Miro
48 captures, in order. Click any one to see it full size.
Pick two of good, fast and cheap
Slide titled "Before Class: Explore & Prepare, Hopes and Fears of AI in My Work" with a three-step Miro board task and an October 7th deadline, under the Creative AI...A slide titled "Before Class: Explore & Prepare, Hopes and Fears of AI in My Work" outlining a three-step pre-class Miro board exercise with an October 7th deadline.
The Workflow Canvas
A Creative AI slide reading "A symbiotic, learning relationship for both the Human and the AI" with overlapping circle and square icons labeled Human and AI.Slide showing six overlapping circle and square icon pairs, each pairing a lightbulb figure with a small image icon, numbered page 11 under the Creative AI logo.A title slide reading "Workflows with AI" on a blue-green gradient background.A slide titled "Some Workflows at an Ad Agency" listing nineteen numbered steps from client brief intake through wrap and learnings.Slide titled "UX Design Workflow" showing a horizontal flowchart of four steps: Briefing, Brainstorm, Research, Design.A slide titled "Some Workflows at an Experiential Agency" listing twenty numbered steps from client brief intake through post-event debrief.A slide titled "UX Design Workflow" showing a horizontal flow of four boxes: Briefing, Brainstorm, Research, and Design.Slide titled "Work Out Your Workflow" (3 mins) with a filled-in table of Barriers and AI Use Cases across the Client Briefing, Brainstorm, Research, Design, Testing,...A blank Miro template titled "AI Enhanced Workflow Canvas" with rows for Desired Outcome, Barriers, AI Use Case, AI Tools, and My Role across five project columns.A slide titled "Desired Outcome for UX Workflow" with a table defining desired outcomes for Client Briefing, Brainstorm, and Research steps.
Work out your workflow
Slide titled "Work Out Your Workflow" (10 mins) showing the same process table with an added Desired Outcome row above the Barriers and AI Use Case rows.A slide titled "Barriers for UX Workflow" showing a table of client briefing, brainstorm, and research steps each paired with a "but first I must" barrier statement.A slide titled "Work Out Your Workflow" with a table mapping desired outcomes, barriers, and AI use cases across six UX workflow steps.Slide titled "Barriers for UX Workflow" showing a table of "But first I must..." barrier statements for the Client Briefing, Brainstorm, and Research steps.
Automate, enhance, or advise
A minimal title slide reading "Let's Think AI" on a light gray background.A slide titled "Turn Obstacles into Opportunities" showing three empty category cards labeled Automate, Enhance, and Advise.Slide titled "Turn Obstacles into Opportunities" with three columns, Automate, Enhance, and Advise, each listing example AI prompts for that use.A slide titled "AI Use Case, 10 mins" showing a filled-in workflow table across client briefing, brainstorm, research, design, testing, and presenting steps for a UX...A slide titled "Turn Obstacles into Opportunities" with the Automate, Enhance, and Advise categories filled in with example AI prompts for each.
Sorting the tools
Title slide reading "Elevate Communication with AI" listing Research, Design, and Planning & Execution on a blue gradient background.A slide titled "How do we communicate with each other?" showing the classic six-panel cartoon of how a swing project was explained, understood, designed, documented,...A slide comparing meeting-transcription AI tools Otter.ai, Fireflies, Teams, and Zoom AI, showing a search bar asking "What did I promise Charlotte?" alongside app...Slide titled "Microsoft Copilot" showing a Teams meeting screen with automatic notes, an email organizer prompt, and a meeting recap card.A slide titled "Notebook LM, Copilot Notebook" showing a Copilot notebook interface next to NotebookLM screens for a rapid adoption research paper.A slide titled "Text to Visual" demonstrating how Microsoft Copilot or Google Gemini can turn pasted data into a bar chart dashboard and executive summary.Slide titled "Notebook LM, Copilot Notebook" showing a Copilot notebook interface alongside three NotebookLM screenshots with source, chat, and audio overview panels.A slide titled "Text to Visual" showing an example of pasted data being converted into a Q1 manager performance dashboard with bar chart and executive summary.A dark blue title slide reading "Elevate Research, Design, Planning & Execution with AI" under the heading Communication.Slide titled "Brainstorm with an LLM" showing example screenshots of Claude, ChatGPT, and Gemini generating a list of premium membership perk ideas.A slide titled "Large Files & Data" describing NotebookLM, showing a Velmora Nuit Doree campaign strategy notebook with sources, chat, and studio panels.A screenshot of the NotebookLM homepage showing featured notebooks including Sherlock Holmes, a Google Research brain-simulation notebook, and an Economist...Slide titled "Large Files & Data" showing a NotebookLM workspace called "Velmora Nuit Doree Campaign Strategy and Launch Blueprint" with sources, chat, and studio panels.A slide titled "Perplexity Labs, Research" describing project-based AI research with a screenshot of the Perplexity Labs interface and its Pro features.A screenshot of a Perplexity-style AI search answer to "what are top 5 most popular ai tools now?" listing ChatGPT, Canva, Gemini, Grok, and DeepSeek in a ranked table.Slide titled "Perplexity Deep Research" showing the Perplexity Pro interface with a search bar and a Deep Research option menu open.A slide titled "Research Deeper, with Sources" comparing deep research tools, showing a ChatGPT Researcher interface with footwear market research prompts.A slide titled "Creating User Personas" showing an AI-generated persona named Oliver with a personality radar chart and demographic details, describing Synthetic...Slide titled "Human-in-the-Loop" showing three sticky notes about workplace software habits above an embedded tweet from Sam Altman about GPT-4o's sycophantic...A title slide reading "Elevate Design with AI" listing Communication, Research, Planning & Execution on a dark blue gradient background.A slide titled "Visual Exploration" describing Ideogram and Midjourney as tools for early concept and mood-board generation, with screenshots of both apps' interfaces.Slide titled "Figma Make" showing a two-panel prototype of a "Join Us Today" account sign-up flow generated from a text prompt.A slide titled "Figma Sites" describing team website publishing directly in Figma, with a Figma Make interface showing a flower shop website design.A slide titled "Nano Banana" describing Google's Gemini image-editing model, showing a robotic banana render and example product-mockup image pairs.Slide titled "Design Feedback" describing AI-assisted heat maps, structured comments, and synthetic user personas, next to a persona profile named Oliver and mobile...A slide titled "Drafting Presentations" comparing Gamma, Pop.AI, Beautiful.ai, and Copilot PowerPoint, showing sample presentation template grids.A slide titled "Drafting Presentations" describing Google Slides' "Enhance Slide" AI feature, with a screenshot of a Gemini panel generating a bar-chart slide.
