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 f3ea6d2..4f875c9 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 @@ -343,9 +343,26 @@ - +
+

Agenda

+
+
+
1.
+

Fetch weather from a single source of truth — 10 out of 10 times.

+
+
+
2.
+

Learn different concepts of Claude Code along the way.

+
+
+
+ + + + +

Jargon you'll hear

I'll unpack each of these as we go — for now, just let them wash over you.

@@ -451,7 +468,7 @@ -
+
Boris Cherny slides showing the spectrum of Claude Code usage styles @@ -466,7 +483,7 @@ -
+

What is Claude Code?

Model (Brain 🧠 — e.g. Opus, GPT) + Harness (Body 💪 — e.g. tools, MCP, memory)

@@ -476,7 +493,7 @@ -
+

🧠 Models — e.g. Opus, GPT

@@ -498,7 +515,7 @@ -
+

🧠 Limitations

The raw model has no real-time access — no internet, no files, no clock.

@@ -509,7 +526,7 @@ -
+

💪 Harness — the body around the brain

@@ -561,7 +578,7 @@ -
+

💪 Harness — the body around the brain

@@ -591,7 +608,7 @@ -
+

🎉 Yayyyyy! Problem solved with harness

The harness reaches out via WebSearch and fetches a real answer from live sources.

@@ -602,7 +619,7 @@ -
+
?

Really?

@@ -612,7 +629,7 @@ -
+

💪 Non-determinism — Doesn’t always use its tools

Similar prompt — but this time the model decided not to use the tool.

@@ -623,7 +640,7 @@ -
+

💪 Non-determinism — Tools can fail

The model first tried one source — it failed (403) — so it fell back to another.

@@ -632,9 +649,27 @@
- + -
+
+

The Two Problems

+

These are the two problems we’re trying to solve.

+
+
+
1.
+

Models sometimes don’t do the vibe coding.

+
+
+
2.
+

Models don’t follow the single source of truth.

+
+
+
+ + + + +

Vibe Coding

Andrej Karpathy — OpenAI founding team · former Director of AI at Tesla · founder of Eureka Labs.

@@ -645,7 +680,7 @@ -
+

Vibe Coding vs Agentic Engineering

@@ -711,129 +746,19 @@ todoapp/
- - - -
-

What is Vibe Coding?

-
-
-

Vibe Coding (ad-hoc)

-

"Write me a weather report for Dubai."

-

No source specified. No format agreed. No memory of last time. The output varies every run.

-

Unpredictable. Hard to share. Hard to repeat.

-
-
-

Agentic Engineering (structured)

-

"/weather-orchestrator"

-

One keystroke. Claude knows the source (Open-Meteo), the format (SVG card), the agent (weather-reporter).

-

Repeatable. Shareable. Same every time.

-
-
-
- Claude Opus hallucinating the letter count in 'strawberry' - Claude Opus hallucinating the current year -
-
-

The Fix Isn't Better Prompting

-

Better prompting doesn't fix these. But giving Claude a tool to count letters and a file that says today's date does. That's what agents, skills, and CLAUDE.md are for — and that's what this session teaches.

-
-
- - - - -
-

Good vs Bad Prompts

-

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

-
-
-

Weak Prompt

-

"Give me the weather."

-

Which city? Celsius or Fahrenheit? From a live API or training data? Claude guesses.

-
-
-

Strong Prompt

-

"Fetch the current temperature for Dubai from Open-Meteo and return it in Celsius."

-

Source named. Location named. Unit specified. No guessing needed.

-
-
-
-
-

Weak Prompt

-

"Make this better."

-

Better how? Shorter? More formal? Better structured? Claude will pick one at random.

-
-
-

Strong Prompt

-

"Rewrite this in a warmer, less formal tone. Keep it under 100 words."

-

Tone named. Length constrained. Unambiguous.

-
-
-
-

But Here's the Bigger Move

-

You can encode good prompts permanently so you never have to write them again. That's what the next five topics are about.

-
-
- - - - -
-

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.

-
-
- 1 -
-
👤 Agents — The Person (job title: weather reporter)
-
A specialist hired for a specific role — same Claude, different hat
-
-
-
- 2 -
-
🎓 Skills — What the Person Can Do
-
do reporting on weather • play a game • read a book
-
-
-
- 3 -
-
🧠 Context — The Person's Brain (storage — the 1M-token space)
-
where knowledge gets loaded in — resets each session
-
-
-
- 4 -
-
📋 CLAUDE.md — The Pocket Rulebook
-
standing instructions read at the start of every shift
-
-
-
- 5 -
-
🎼 Workflow — The Trigger
-
one command kicks off the whole chain — commands are the entry point
-
-
-
-
- -
+
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

@@ -856,7 +781,7 @@ 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.

@@ -897,7 +822,7 @@ todoapp/ -
+

Agents Get Their Own Brain

Tip from Thariq (Anthropic) — Apr 16, 2026

@@ -930,7 +855,7 @@ 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.

@@ -973,7 +898,7 @@ 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:

@@ -1021,14 +946,14 @@ 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

@@ -1055,7 +980,7 @@ todoapp/
-
+

When to Turn Something Into a Skill

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

@@ -1092,7 +1017,7 @@ todoapp/
-
+

Why Separate Agents and Skills?

@@ -1118,7 +1043,7 @@ todoapp/
-
+

How to Create Your Own Skill

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

@@ -1171,7 +1096,7 @@ 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:

@@ -1211,14 +1136,14 @@ 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

@@ -1256,7 +1181,7 @@ 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 @@ -1290,7 +1215,7 @@ 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.

@@ -1334,7 +1259,7 @@ 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.

@@ -1379,14 +1304,14 @@ 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

@@ -1414,7 +1339,7 @@ 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.

@@ -1459,7 +1384,7 @@ 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

@@ -1496,7 +1421,7 @@ open, edit, save # Tweak it like any doc<
-
+

What Goes in CLAUDE.md

# CLAUDE.md @@ -1524,7 +1449,7 @@ 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:

@@ -1557,14 +1482,14 @@ 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

@@ -1608,7 +1533,7 @@ 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.

@@ -1663,14 +1588,14 @@ 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 @@ -1697,7 +1622,7 @@ 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:

@@ -1720,7 +1645,7 @@ 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.

@@ -1771,7 +1696,7 @@ 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.