AI in Practice

1. Design in writing first

   Write a short document on what to build, why, and when it is done, then hand it to AI. The more specific the description, the more accurate the result.

2. Hand it to an agent, then review

   Coding agents such as Claude Code and Codex read files, edit them and run commands. You read the changes and decide whether to accept them.

3. Tests set the standard

   Put the tests in place first and ask AI to keep fixing until they pass. Tests are the safety net that catches AI's mistakes.

4. Split small, check often

   Hand over one feature at a time, check it on screen, and commit when it works. The bigger the request, the easier it gets tangled.

5. Keep rules in files

   Write project rules, commands and don'ts in AGENTS.md, CLAUDE.md or skills, and AI works the same way without you explaining every time.

6. Use several AIs together

   Let one AI build and another review, or split the work and run it at the same time. A different AI's eyes find problems the first one missed.

1. Web

   A sketch or a description is enough to get a page, and AI also helps set up the server, database and deployment.

2. Apps

   Build iOS and Android apps from one codebase, and get drafts of store listings and a privacy policy too.

3. Games

   Build a prototype in a day to see if it is fun, generate art, sound and dialogue, and simulate the balance.

4. Everywhere

   Paste an error message and AI explains the cause and what to fix; it also writes docs, translations and tests with you.

• What Vibe Coding Is
• Claude Code
• Codex
• All game topics

• 8 in 10 people who say AI has improved their own productivity (McKinsey, The State of AI 2026)
• 27% → 40% large companies scaling AI agents in at least one function (McKinsey, The State of AI 2026)
• 4% tech leaders with plans to redesign roles for people and agents working together (Gartner survey, October 2026)

1. Always-on agents

   Instead of one-off chats, agents that take a goal and keep working across messengers, email and documents are arriving in work tools.

2. AI coworkers with permissions

   AI works as a digital coworker with its own account and permissions. People decide what it can see and what it can change.

3. Handing over long tasks

   Beyond minute-long tasks, more people hand over research, organizing and writing that takes hours or more than a day, and just receive the result.

4. Connected to company tools

   Connectors and MCP link email, calendars, drives and internal systems to AI so it can find and use scattered information itself.

5. Governance and security come first

   As agents multiply, companies have started to monitor and log them like employees on the inside. Small permissions and kept logs are the basics.

1. Email and messages

   Summarize incoming mail and get reply drafts. Tell AI the tone, length and must-have points, and you will fix less.

2. Meetings

   Record meetings to get minutes, decisions and to-do lists, with owners and deadlines sorted out.

3. Documents and reports

   Give an outline and key points, get a draft, then correct it with facts and numbers you know. Slides work the same way.

4. Research

   Use deep research to compare and organize many sources, then open the source links and check them yourself.

5. Data and spreadsheets

   Upload a table and ask in plain words for calculations, charts and summaries. Get the formulas or code too so you can reuse them.

6. Automating routine work

   Hand weekly chores (collecting reports, reminders, tidying up) to an agent on a schedule and just check the results.

1. Everyone uses AI

   These days everyone uses AI, and everyone thinks they use it best. Using AI alone no longer sets you apart.

2. Building software costs almost nothing

   No one writes 100% of their code with their own mind and hands anymore. Web, app and game development has become more advanced, much faster and much easier. The place for developers who relied only on writing code is disappearing.

3. Start a business alone, fast

   In Seoul, I asked AI and applied for business registration online in 20 minutes; it was done the next day. You could probably do it in 10 minutes. From building the idea to registration and marketing, you can do it alone with AI, without anyone's help.

4. Reaching customers is harder

   Starting a business has become so easy that the number of founders is said to have grown 100 times. Someone is probably already running the business you just thought of. Finding people who will buy is far harder than building.

Seen the other way round, what everyone has (AI, development, registration) makes no difference. The difference comes from these four things.

1. An eye for choosing, not just the power to build

   Since you can build anything, the first skill is choosing a problem people truly want solved, even if they have to pay.

2. Customers before building

   Customers are hard to reach. Find buyers before you build, and grow a direct line to them (community, subscribers, regulars) as your asset.

3. A reason to choose you

   The same idea already exists. Use what AI cannot copy, such as your experience, expertise, trust and story, to give people a reason to buy from you.

4. Launch small, fix fast

   Building costs almost nothing, so launch small instead of perfect, watch how the market reacts, and adjust quickly until you find what makes money.