🤖 AI & IT Training
Automating PPT with Claude Design
Same script, a different design every time — no more. Write your company’s design rules as a document, teach them once, and build a PPT production system that remembers them, in 2 hours
⏱ Training hours2 hours
🏢 FormatOn-site delivery · Customized design
👤 InstructorJohn Kim
✅ Key OutcomePresentation production time drops sharply — design work that took half a day per deck shifts to feeding in the script and reviewing
“I tried making a PPT with AI, but I still had to rework it.” Almost everyone who has used an AI presentation tool says much the same. Give it the same prompt and today’s result differs from yesterday’s; colors and fonts change every time, so to get something usable for the company you end up reopening PowerPoint. The problem is not the AI’s performance but the lack of rules. This course is not about prompt-writing tricks. It is a 2-hour hands-on workshop where you define your company’s design rules in a document (Design MD) and register it in Claude Design, building a system that produces the same brand tone whatever content you feed it. All you need is one well-made existing PPT slide: the AI extracts the key colors, fonts, and layout rules and draws up a blueprint. If you have no materials, we work out the rules together in an interview. You then feed real work drafts into the system to generate a deck, edit it in the browser as you would in PowerPoint, and finish with the most important step: saving the feedback you accumulated while editing as defaults, so it is applied next time without being asked. By the end, you leave with one design rules file for your company and one real presentation you can use next week.
💻 Start learning this topic with an online course →Who is this course for?
This course is designed for practitioners and leaders at companies and institutions building AI and IT skills. It is especially useful for organizations that want to diagnose why AI presentations come out different every time — the cause is 'missing rules,' not 'the prompt' — and to understand the production cycle that runs from rules → system → generation → editing → learning.
What will you learn?
- Learn to diagnose inconsistent AI presentations as a lack of rules, not a prompt problem, and understand the production loop: rules → system → generation → editing → learning
- Write your company’s design rules document (Design MD) using three methods — extracting from existing materials, borrowing from references, and interviewing — and self-check its quality with a checklist
- Register your rules in Claude Design, review samples of the color palette, text hierarchy, and element styles, and correct anything you dislike right away with prompts
- Feed in a real work script to generate a draft presentation, then adjust text, sizes, and shapes in the browser editor and compare several versions to finalize the best one
- Save the feedback from editing as the system’s defaults, regenerate with the same prompt, and see the before-and-after difference yourself
Curriculum
Module 1: Why results differ every time — it’s the 'system,' not the prompt (about 15 min)
- Compare two decks built from the same script side by side — see with your own eyes the difference between a result made without rules and one built on a design system
- Limits of existing AI presentation tools — colors, fonts, and layouts change every time, and fine adjustments aren’t possible, so people end up reworking the result themselves
- The big picture on one page: the cycle of defining rules (Design MD) → registering in the system → generating content → editing → learning from feedback and saving
- Deliverables — by the end, you leave with 'one brand rules file + one deck for real work'
Module 2: Design MD — turning your company’s design rules into a document (about 25 min · hands-on)
- What goes into a design rules document — key colors and the role of each, fonts and a three-level text hierarchy, margin and alignment rules, logo placement, and what not to do
- Track A (the fastest route): attach an existing PPT you consider well made and ask, "Extract the key colors, fonts, and style from this file and turn them into a design rules document," to generate the blueprint automatically
- Track B: how to take a public brand style reference as a starting point and replace its values with your company’s
- Track C: When you have no materials at all — build the rules from scratch through conversation with “Interview me for the elements you need”
- A 5-item self-check list for a good rules document, and common problems when specifying Korean fonts and how to handle them
Module 3: Register the design system and review samples (about 20 min · hands-on)
- Where quality first diverges — choosing a top-tier model, setting reasoning effort, and when to raise or lower it
- Register the rules document you wrote in the design system, then review the color palette, button, and text hierarchy samples the AI generates from it
- A review loop where you fix anything you dislike instantly with a prompt and check again — catch problems here so you don’t have to redo everything later
- The pitfall of over-specifying rules, which makes results rigid — how to decide what to lock down and what to leave open
Module 4: Build and edit a deck from your own script (about 25 min · hands-on)
- Feed in your lecture scripts, report drafts, and proposals as is to generate a first draft of the presentation
- Interactive format: answer the AI’s follow-up questions (how long the presentation is, whether you will add images yourself, and so on) to sharpen the deck’s purpose
- Edit text, resize, and add shapes in the browser editor — a workflow that finishes the deck without opening PowerPoint
- For elements you’re unsure about, toggle several versions on and off and compare them to pick the best option
- How to export the finished deck for real presentations and distribution, and what to watch out for
Module 5: Make feedback the default — a system that remembers what you teach it once (about 25 min · hands-on)
- Make your accumulated edits permanent in the system rules by telling it, “Save all feedback so far as the default” (e.g., logo always top right, title on one line)
- Save your changes, regenerate from the same prompt, and compare the results side by side — the core experience of this training and what sets it apart from other AI tools
- How to resolve conflicts as rules accumulate, and how to share rule files with your team so everyone follows the same document standards
- A demo of extending the same system to social media carousels, report templates, and landing pages, followed by Q&A
Tools used in this course
Expected results / After the course
- Much shorter production time for presentations — design work that used to take half a day per deck shifts to feeding in the script and reviewing the output
- Brand consistency that holds when owners change — color, font, and layout rules live in a document, so the whole team builds materials to the same standard
- Extend the design system you built to social card posts, report templates, and landing pages — put the energy you spent on design into the substance of your message
About the instructor
John KimInstructor John Kim, author of “B2B Marketing Design” and CEO of Nanum ConsultingView profile →
Related courses
Recommended online courses
Start with an Online Course
Before you book on-site training, preview the essentials of this topic in an online course.
AI · Online Courses
Claude Cowork · Hands-On Basics
An introductory hands-on course for building work tools that run on plain conversational instructions.
KRW 59,000 (≈ US$44)89,000View Course →
AI · Online Courses
Practical AI for Corporate Instructors
Use AI in your daily work, from lesson prep to content creation.
KRW 59,000 (≈ US$44)89,000View Course →
We tailor this course to your company
From diagnosis to execution — Nanum Consulting
FAQ
Yes. It is built for practitioners without a design background. You do not pick colors or arrange layouts yourself; you work with the AI in conversation to document the rule “this is how our company’s materials are made.” With just one well-made existing deck, the AI extracts the color, font, and layout rules for you, so what you need is not design expertise but a sense of what looks like your company.
Yes. The training covers all three paths. ① If you have a well-made existing PPT, we extract the rules from it. ② If there is a style you want to follow, we use it as a starting point and swap in your own values. ③ If you have nothing, the AI interviews you one item at a time and builds the rules from scratch. For organizations without a brand guide, this training itself becomes the occasion to create the first one.
You’ll get the most out of the hands-on practice if you bring a laptop with your account logged in, plus two files prepared in advance: (1) one existing presentation your company considers well made (for extracting rules), and (2) the script or draft of a document you actually need to produce soon (for generating a deck). For participants who find preparation difficult, the instructor prepares a sample rules file and a sample script, so the hands-on session proceeds even if you can’t bring your own.
The decisive difference is “learning and saving.” Most tools generate from scratch every time, so you keep repeating the same corrections. This approach saves the feedback from your edits into a rules file and applies it automatically from the next deck onward. The more you use it, the better it fits your organization, so this training goes beyond teaching a one-off tool — it builds a system that grows into a lasting asset.
Yes. Once built, a design system isn’t used only for presentations. Applying the same rules, you can produce card news, report templates, landing pages, and more in a consistent style, and we demonstrate these extensions in the final module. The more often a department produces materials, such as marketing, training, or planning, the greater the benefit.
Automating PPT with Claude Design
Same script, a different design every time — no more. Write your company’s design rules as a document, teach them once, and build a PPT production system that remembers them, in 2 hours
Training objectives
- Learn to diagnose inconsistent AI presentations as a lack of rules, not a prompt problem, and understand the production loop: rules → system → generation → editing → learning
- Write your company’s design rules document (Design MD) using three methods — extracting from existing materials, borrowing from references, and interviewing — and self-check its quality with a checklist
- Register your rules in Claude Design, review samples of the color palette, text hierarchy, and element styles, and correct anything you dislike right away with prompts
- Feed in a real work script to generate a draft presentation, then adjust text, sizes, and shapes in the browser editor and compare several versions to finalize the best one
- Save the feedback from editing as the system’s defaults, regenerate with the same prompt, and see the before-and-after difference yourself
Expected results
- Much shorter production time for presentations — design work that used to take half a day per deck shifts to feeding in the script and reviewing the output
- Brand consistency that holds when owners change — color, font, and layout rules live in a document, so the whole team builds materials to the same standard
- Extend the design system you built to social card posts, report templates, and landing pages — put the energy you spent on design into the substance of your message
Curriculum
Module 1Module 1: Why results differ every time — it’s the 'system,' not the prompt (about 15 min)
- Compare two decks built from the same script side by side — see with your own eyes the difference between a result made without rules and one built on a design system
- Limits of existing AI presentation tools — colors, fonts, and layouts change every time, and fine adjustments aren’t possible, so people end up reworking the result themselves
- The big picture on one page: the cycle of defining rules (Design MD) → registering in the system → generating content → editing → learning from feedback and saving
- Deliverables — by the end, you leave with 'one brand rules file + one deck for real work'
Module 2Module 2: Design MD — turning your company’s design rules into a document (about 25 min · hands-on)
- What goes into a design rules document — key colors and the role of each, fonts and a three-level text hierarchy, margin and alignment rules, logo placement, and what not to do
- Track A (the fastest route): attach an existing PPT you consider well made and ask, "Extract the key colors, fonts, and style from this file and turn them into a design rules document," to generate the blueprint automatically
- Track B: how to take a public brand style reference as a starting point and replace its values with your company’s
- Track C: When you have no materials at all — build the rules from scratch through conversation with “Interview me for the elements you need”
- A 5-item self-check list for a good rules document, and common problems when specifying Korean fonts and how to handle them
Module 3Module 3: Register the design system and review samples (about 20 min · hands-on)
- Where quality first diverges — choosing a top-tier model, setting reasoning effort, and when to raise or lower it
- Register the rules document you wrote in the design system, then review the color palette, button, and text hierarchy samples the AI generates from it
- A review loop where you fix anything you dislike instantly with a prompt and check again — catch problems here so you don’t have to redo everything later
- The pitfall of over-specifying rules, which makes results rigid — how to decide what to lock down and what to leave open
Module 4Module 4: Build and edit a deck from your own script (about 25 min · hands-on)
- Feed in your lecture scripts, report drafts, and proposals as is to generate a first draft of the presentation
- Interactive format: answer the AI’s follow-up questions (how long the presentation is, whether you will add images yourself, and so on) to sharpen the deck’s purpose
- Edit text, resize, and add shapes in the browser editor — a workflow that finishes the deck without opening PowerPoint
- For elements you’re unsure about, toggle several versions on and off and compare them to pick the best option
- How to export the finished deck for real presentations and distribution, and what to watch out for
Module 5Module 5: Make feedback the default — a system that remembers what you teach it once (about 25 min · hands-on)
- Make your accumulated edits permanent in the system rules by telling it, “Save all feedback so far as the default” (e.g., logo always top right, title on one line)
- Save your changes, regenerate from the same prompt, and compare the results side by side — the core experience of this training and what sets it apart from other AI tools
- How to resolve conflicts as rules accumulate, and how to share rule files with your team so everyone follows the same document standards
- A demo of extending the same system to social media carousels, report templates, and landing pages, followed by Q&A
About the instructor
John Kim, Lead Instructor
10 years in industry · 15 years teaching (3,000+ lectures)
Education
· MBA (advanced major: Marketing), Korea University Graduate School of Business (graduated)
· Sungkyunkwan University Consultant Program (completed)
· Sogang University Graduate School of Business, Short-Term MBA (completed)
· Seoul National University Lifelong Education Instructor Development Program (completed)
· Chung-Ang University, B.A. in English Language and Literature (graduated)
Experience
· Current: CEO, Nanum Consulting
· Formerly at Hyosung Corp., Daeduck Electronics and Shinhan Diamond: overseas assignments and strategic planning (10+ years)
· Current partner instructor, Expert Consulting
· Current: Partner instructor, PSI Consulting
· (Current) Partner instructor, Korea SMEs and Startups Agency and SME Training Institute
Credentials and publications
· Certified consultant
· Certified teacher
· Completed official IDEO Design Thinking training
· B2B Marketing Design (1 Apr 2025)
· The Chinese Diamond Tool Market: Present and Future (co-authored, Korea Tool Association)
· Battles That Changed History and Innovative Weapons (in progress)