diff --git a/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html b/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html index 24677cb..3815a24 100644 --- a/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html +++ b/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html @@ -484,9 +484,45 @@ - +
+

🧠 Models — e.g. Opus, GPT

+

The model is the brain. It ships with everything it was trained on — and nothing else. Every model has a knowledge cut-off date.

+
+
+

✅ Can answer

+

“What is the capital of Japan?”

+

A fact that existed before the cut-off — already lives inside the brain.

+
+
+

❌ Can’t answer

+

“Who won yesterday’s match?”

+

Anything after the cut-off date — the brain simply doesn’t know it.

+
+
+
+

Example: Opus 4.7

+

Anthropic’s latest model has a knowledge cut-off of January 2026. It knows facts up to that date — anything after it is invisible to the raw model.

+
+
+ + + + +
+

🧠 Limitations

+

The raw model has no real-time access — no internet, no files, no clock. Ask it something happening right now, and it will tell you it can’t help.

+
+ Anthropic Workbench screenshot showing the model refusing a real-time weather query +
+

Above: the model declining a weather query — “I don’t have real-time access.”

+
+ + + + +

Vibe Coding vs Agentic Engineering

@@ -555,7 +591,7 @@ todoapp/ -
+

What is Vibe Coding?

@@ -584,7 +620,7 @@ todoapp/ -
+

Good vs Bad Prompts

Even before you set up any structure, how you prompt matters. Specific beats vague. Context beats assumption.

@@ -620,7 +656,7 @@ todoapp/ -
+

Meet the Person

We're going to learn five concepts using one running example: a weather reporter agent that fetches Dubai's temperature and renders a weather card. Same person — five different angles.

@@ -667,14 +703,14 @@ todoapp/ -
+
Topic 1

👤 Agents — The Weather Reporter

An agent is Claude playing a specific role. Meet the weather reporter — a specialist hired to fetch and report weather data for Dubai. Same Claude, different hat.

-
+

The Restaurant Kitchen

Think of it like this

@@ -697,7 +733,7 @@ todoapp/
-
+

Prompting vs. Agent — Side by Side

The difference in one picture: prompting is asking a stranger on the street; using an agent is asking your dedicated specialist.

@@ -738,7 +774,7 @@ todoapp/ -
+

Agents Get Their Own Brain

Tip from Thariq (Anthropic) — Apr 16, 2026

@@ -771,7 +807,7 @@ todoapp/
-
+

How to Create Your Own Agent

You don't write an agent from scratch — Claude helps you build one. Type /agents inside Claude Code and a guided menu opens.

@@ -814,7 +850,7 @@ todoapp/
-
+

Agent Config Fields

The config block at the top of an agent file controls its identity and capabilities. Here's what the real weather-agent.md uses:

@@ -862,14 +898,14 @@ todoapp/ -
+
Topic 2

🎓 Skills — What the Weather Reporter Knows

Skills are the specific things the reporter has been trained to do. Our reporter has two: fetch the data, and render it as a card.

-
+

The Training Manual

Think of it like this

@@ -896,7 +932,7 @@ todoapp/
-
+

When to Turn Something Into a Skill

Tip from Boris Cherny (creator of Claude Code) — Feb 1, 2026

@@ -933,7 +969,7 @@ todoapp/
-
+

Why Separate Agents and Skills?

@@ -959,7 +995,7 @@ todoapp/
-
+

How to Create Your Own Skill

Skills are plain markdown files. If you can write a recipe, you can write a skill.

@@ -1012,7 +1048,7 @@ Fetch the current temperature for Dubai, UAE.
-
+

Skill Config Fields

The small config block at the top of a SKILL.md (the "frontmatter") controls how the skill behaves:

@@ -1052,14 +1088,14 @@ Fetch the current temperature for Dubai, UAE. -
+
Topic 3

🧠 Context — The Reporter's Brain

Now that you've met the reporter and know their skills, let's understand what they can actually hold in mind at once. Every agent — including the weather reporter — gets its own fresh brain.

-
+

Claude's Brain

Think of it like this

@@ -1097,7 +1133,7 @@ Fetch the current temperature for Dubai, UAE.
-
+

What Loads at Session Start

The moment you open Claude Code, certain things land in Claude's brain before you've typed a word. The rest waits in the wings — only loaded when you actually need it. This is called progressive disclosure.

Diagram showing what loads into Claude's context window at session start @@ -1131,7 +1167,7 @@ Fetch the current temperature for Dubai, UAE.
-
+

Keep the Brain Clear

The more stuff crammed into Claude's brain, the harder it is to focus on what matters. This is called context rot — performance drops as the brain gets crowded.

@@ -1175,7 +1211,7 @@ Fetch the current temperature for Dubai, UAE.
-
+

How to Manage Your Context

You can't create the context — it's just there, the moment you open a chat. But you can see how full it is, trim it down, or wipe it clean. Three commands give you full control.

@@ -1220,14 +1256,14 @@ Fetch the current temperature for Dubai, UAE. -
+
Topic 4

📋 CLAUDE.md — The Reporter's Pocket Rulebook

The weather reporter consults this at the start of every shift — even though their brain resets overnight. It's the standing instructions pinned in that brain before you've said a word.

-
+

The Employee Handbook

Think of it like this

@@ -1255,7 +1291,7 @@ This is the Q2 marketing campaign brief — targeting small business owners.
-
+

How to Create Your CLAUDE.md

You don't need to write CLAUDE.md by hand. Claude can look at your project and draft one for you.

@@ -1300,7 +1336,7 @@ open, edit, save # Tweak it like any doc<
-
+

Grow CLAUDE.md With Every Mistake

Tip from Boris Cherny (creator of Claude Code) — Feb 1, 2026

@@ -1337,7 +1373,7 @@ open, edit, save # Tweak it like any doc<
-
+

What Goes in CLAUDE.md

# CLAUDE.md @@ -1365,7 +1401,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
-
+

How CLAUDE.md Loads

Claude Code uses two mechanisms to find CLAUDE.md files:

@@ -1398,14 +1434,14 @@ This is a TodoApp with a FastAPI backend and React frontend. -
+
Topic 5

⚡ Commands — The Trigger

One word kicks off the whole chain. /weather-orchestrator → agent → skill → SVG card. Commands are the entry point into any workflow.

-
+

Commands — The Entry Point

Think of it like this

@@ -1449,7 +1485,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
-
+

How to Create Your Own Command

Commands are markdown files too. If you can write a recipe, you can write a command.

@@ -1504,14 +1540,14 @@ This is a TodoApp with a FastAPI backend and React frontend. -
+
Putting It All Together

🎼 Workflow — All Five Pieces Together

Watch the weather reporter example run from one keystroke to SVG card output. Five concepts, one orchestrated flow.

-
+

Command → Agent → Skill

This is the core architecture pattern of Claude Code workflows — demonstrated in this very repo by the weather example:

The Orchestration Flow @@ -1538,7 +1574,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
-
+

Two Ways Skills Are Used

The weather workflow demonstrates both skill patterns in a single flow:

@@ -1561,7 +1597,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
-
+

How to Wire Your Own Workflow

A workflow isn't a separate file type. It emerges when one command calls agents and skills in sequence.

@@ -1612,7 +1648,7 @@ This is a TodoApp with a FastAPI backend and React frontend. -
+

Journey So Far

Five concepts, one running example

From meeting the weather reporter to wiring the full Command → Agent → Skill chain. The same five pieces compose every workflow you'll ever build.