1, 2, 3
Claude
The three levels of Claude and what to ask of each one.
HOW WE WORK
We start with you, not the technology. The whole point is to make AI serve the way you already think and work: hands-on, practical, and genuinely fun. You walk out with AI working for you, not one more tool to manage.
Santiago Restrepo
AI SHERPA · YOUR GUIDE FOR THE DAY
The room today
From your own registration answers. Almost everyone here already uses AI every day, so we are not starting from zero. We are going further.
Live from registrations as of this morning.
The shape of the day
Module 01 of 06
ANTHROPIC'S REAL PRODUCT
To let people actually use these models, Anthropic built three environments to work with them.
The Framework
There are four ways to work with Claude.
Most people don't know the difference.
4 · API
You wire Claude straight into your own software.
An API is how two pieces of software talk to each other, with no person typing in between. Instead of you chatting with Claude, your own tools call Claude directly: to read, write, sort, or generate, at scale and on their own. It is how Claude gets built into a product or a workflow that just runs. We will not go deep today, just know it exists.
Built for: developers and automations
1 · Web
You rent a cubicle in their building.
You rent a workspace inside Anthropic's offices. Your password is the key to your account, and your files live on their servers, not yours. Space is limited, but you can reach it from anywhere, even your phone.
Instruction layer: Master Prompt
2 · Desktop
You bring the mind into your own house.
Instead of going to their offices, you bring Claude home. It works directly in the folders on your computer: no uploads, no size limits. Folder instructions give it a memory that loads every session. Powerful, with guardrails still on.
Instruction layer: Folder instructions
3 · Terminal
You hand over the keys to the whole house.
Full access to your machine. It can build, run, and ship, not just talk. The most powerful and the most technical of the three. Memory, skills, and automations all live here.
Instruction layer: CLAUDE.md, skills, hooks
Across Chat, Cowork & Code
| Capability | Chat | Cowork | Code |
|---|---|---|---|
| Standing instructionsa note Claude reads every time | ● | ● | ● |
| Projects & project filesa saved workspace of context and files | ● | ● | ◐ |
| Memory across sessionsit remembers between conversations | ● | ◐ | ● |
| Skillsteaches Claude a task, your way | ● | ● | ● |
| Pluginsa bundle of skills, connectors and commands | ● | ● | ● |
| Connectors (MCP)a live link to your other apps | ● | ● | ● |
| Subagents & agent teamsClaude spins up helper Claudes | ○ | ◐ | ● |
| Hooksauto-rules that fire at set moments | ○ | ○ | ● |
| Scheduled tasks (local)recurring jobs on your machine | ○ | ● | ● |
| Cloud Routinesrecurring jobs that run in the cloud | ○ | ○ | ● |
| Remote / background agentsstart it, walk away, it finishes | ○ | ○ | ● |
| Artifactsa live panel for docs and dashboards | ● | ◐ | ◐ |
| Direct local file accessworks right in your computer's files | ○ | ● | ● |
| Code execution sandboxactually runs code to test things | ○ | ● | ● |
| Computer useclicks, types and navigates a screen | ○ | ◐ | ● |
THE ONE FILE TO REMEMBER
Think of CLAUDE.md as a sticky note left inside a folder. Every time Claude opens that folder, it reads the note first: who you are, how you work, what matters. Each surface has its own version of that note.
Now let's go build with it.
Module 02 of 06
Demo 1 · Claude Chat
Claude.ai, in your browser or on your phone. The most accessible way in, and where most people meet Claude.
Past quick answers. We give Claude a Master Prompt, then build a specialist that does real work.
Like renting a cubicle in Anthropic's building.
Demo 1 · The Master Prompt
Most people treat Claude like Google: short questions, generic answers. The unlock is context. Answer eleven questions out loud, and Claude writes your Master Prompt.
The 11 questions
Built once, by voice
Module 03 of 06
Demo 1 · Build a specialist
Now that Claude knows you, give it one job. The same idea, getting more specific each step.
General context about who you are and how you work.
A specialist built for one task, dropped into a Project.
Finished deliverables, ready to use.
Demo 1 · The System Prompt
You don't have to be the expert. Claude researches the field first, then writes the brief that makes it one.
A System Prompt is the brief for one job: the frameworks it follows, the method it uses, and what a good result looks like.
Built with Deep Research
Demo 1 · Two kinds of instruction
Master Prompt
Lives in your profile. Applies to every chat you start.
System Prompt
It is the project's instructions. Applies inside that Project only.
Your turn
Build your own assistant from scratch. You have about 20 minutes, and you can ask questions any time as you go.
Module 04 of 06
Module 04
A skill is just a folder you can zip up and share (its packaged file ends in .skill). Plain files tell Claude how to do one job well, and it only opens them when it needs them.
The shape
An example
Same four parts as any skill, filled with real contents. Then you invoke it anywhere: any chat, Cowork, or Code, by slash command or just by asking.
Project vs Skill
Static. A project lives in one place. You bring your work to it.
Portable. A skill goes anywhere. Invoke it by slash command or just by asking.
Built an assistant you rely on? Because the anatomy is almost identical, you can lift it into a skill, use it everywhere, and share it with your team.
Module 04
Make a skill when a task is repeatable. Build it once and it works for you every time, and you can share it with the whole team so everyone runs your best process.
Two ways to build one
Example: a "weekly report" skill you design up front.
Example: you nailed one great deck, now make it repeatable.
Your turn
Turn the assistant you just built into a skill, or create a brand-new one. About 10 minutes, and ask questions any time.
Easiest path: do the task with Claude, get the output right, then say "turn this into a skill."
Module 05 of 06
Demo 2 · Claude Cowork
Claude.ai is capped on file size and cannot reach your computer. You upload one file at a time.
Claude works directly inside a folder on your machine: every file at once, no uploads, no size limits.
Demo 2 · What we start with






Demo 2 · The prompt
The dashboard is only as good as the brief. Here is what we gave Claude, and why each piece matters.
"Hey Claude, I need your help with something."
A folder, Harbor & Pine, for a client: an Amazon FBA seller buried in disconnected Excel files.
He has no single place to see the state of his business or make decisions. It is cumbersome and easy to lose track.
Research the best dashboard designs and practices, read all of the data, and propose a highly visual, interactive dashboard he can act on.
A self-contained HTML file, easy to share and understand, following strong UX/UI and front-end practices.
Use HTML, CSS, React, or whatever fits. Think about what would truly be impactful for his business, and why.
Five parts, one complete brief: context, problem, ask, standard, and room to think.
Demo 3 · Claude Code
Cowork builds inside your folder. Putting things live, wiring up tools, and running big multi-part jobs is still on you.
Claude gets your whole machine and the internet: sub-agents for bigger builds, and live websites it can deploy and maintain, once set up, with very few manual steps.
You still don't write code. You describe the outcome.
Demo 3 · The prompt
Same idea, bigger reach. This brief asks Claude to research, design, check its own work, and put the site live.
"Okay Claude, on my desktop there's a folder called Harbor & Pine Goods."
A folder on my desktop with the data from an Amazon FBA seller.
A commercial website that gives them a web presence: tell their story, show their products beautifully, and link back to their Amazon listings.
Find which products they sell, spin up a sub-agent to search the web for high-quality photos, then use your front-end design skill and study great comparable sites.
Before showing me: critique your own design, spin up a graphic-design agent to review it against the design skill and propose fixes, then navigate the site with Playwright to confirm it holds up.
Host it live on Vercel using my Cloudflare account. You build and deploy; guide me through the one manual step, pointing the CNAME.
Same anatomy, bigger reach: now it researches, self-critiques, and ships.
Beyond the basics
Plugins, skill chaining, and routines: how you go from one assistant to a whole system that runs itself.
Advanced features
If a skill is one capability, a plugin is the box you pack many of them into, plus the hooks, connectors and commands they need, as one installable, shareable unit.
Plugin-only perks
Skill or plugin? Make a skill for one job. Make a plugin when you want to ship a whole toolkit to others and keep everyone on the same version, updates included.
Advanced features
A skill's instructions can tell Claude to run another skill, so one job hands off to the next. You build small pieces and chain them into big ones.
We do this in our own system: the call-triage skill hands off to the summary skill automatically. Claude does the calling by following the instructions, there is no hidden skill-to-skill wiring.
Advanced features · Claude Code
A routine is a task you save once and let run by itself in the cloud, on a schedule, even with your laptop closed. Like a cron job, but it's a whole AI teammate: it reads your sources, decides what matters, and does the next step. (A Claude Code feature.)
Most run on a schedule. They can also fire from an API call or a GitHub event for connected workflows. A "done" status means it ran, not that it nailed it: spot-check.
Module 06 of 06
Other models worth knowing
Claude stays home base for analysis, synthesis, and building. These are specialists you reach for on purpose.
A research move
Run the same deep research on Claude and Gemini, then let Claude fuse the two.
Another tool worth knowing
Upload your own sources and it answers only from them, citing the exact passage, so it won't invent anything beyond your material. Great for studying a dense pile of documents or pressure-testing a dataset. Free with a Google account.
Careful with proprietary data. On the free tier your feedback can be human-reviewed. Use a Workspace or enterprise account for anything confidential.
Working with data
Models sound most confident exactly when they're wrong. A few habits keep you safe:
A tip to take with you
Typed: "competitor analysis Q3 slides." Spoken: "Look at our top three competitors, pull what changed in their positioning this quarter, then draft three slides I can present." Same effort, far more for Claude to work with.
A tip to take with you
The newer models reward collaboration over commands. Don't bark a task, work with it like a sharp coworker:
Adapted from Nate B Jones's AI workflow.
Recap
Rent a cubicle
Claude.ai in your browser or on your phone. Best for everyday thinking: writing, analysis, research, and building a specialist inside a Project.
You give it a Master Prompt
Bring it to your folder
Works directly inside a folder on your computer. Best for turning a pile of files into something useful, like a live dashboard.
You give it Folder instructions
Keys to the machine
Your whole machine and the internet. Best for big builds Claude can research, refine through its own loops, and ship live.
You give it a CLAUDE.md
More reach at every step. The unlock never changes: give Claude context, and tell it what you want.
Thank you.
Now let's put it to work.
aisherpa.me · cal.com/santiago-restrepo