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 e51bf59..f91fdf3 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 @@ -615,9 +615,173 @@ - +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Control loop + + decides the next call + + Reins + + + + + + + + Tool allowlist + + constrains what it can do + + Bit + + + + + + + + Context management + + narrows what it sees + + Blinders + + + + + + + + Evaluator + + decides when done + + Driver + + + + + + + + State persistence + + carries work forward + + Traces + + + + +

A horse harness. A model harness.

+

Same verb.

+ +
+
+ + + + +

💪 Harness — the body around the brain

@@ -669,7 +833,7 @@ -
+

💪 Harness — the body around the brain

@@ -699,7 +863,7 @@ -
+

🎉 Yayyyyy! Problem solved with harness

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

@@ -710,7 +874,7 @@ -
+
?

Really?

@@ -720,7 +884,7 @@ -
+

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

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

@@ -731,7 +895,7 @@ -
+

💪 Non-determinism — Tools can fail

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

@@ -742,7 +906,7 @@ -
+

The Two Problems

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

@@ -760,7 +924,7 @@ -
+

Vibe Coding

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

@@ -771,7 +935,7 @@ -
+

Vibe Coding vs Agentic Engineering

@@ -842,14 +1006,14 @@ 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

@@ -872,7 +1036,7 @@ 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.

@@ -913,7 +1077,7 @@ todoapp/ -
+

Agents Get Their Own Brain

Tip from Thariq (Anthropic) — Apr 16, 2026

@@ -946,7 +1110,7 @@ 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.

@@ -989,7 +1153,7 @@ 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:

@@ -1037,14 +1201,14 @@ 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

@@ -1071,7 +1235,7 @@ todoapp/
-
+

When to Turn Something Into a Skill

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

@@ -1108,7 +1272,7 @@ todoapp/
-
+

Why Separate Agents and Skills?

@@ -1134,7 +1298,7 @@ todoapp/
-
+

How to Create Your Own Skill

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

@@ -1187,7 +1351,7 @@ 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:

@@ -1227,14 +1391,14 @@ 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

@@ -1272,7 +1436,7 @@ 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 @@ -1306,7 +1470,7 @@ 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.

@@ -1350,7 +1514,7 @@ 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.

@@ -1395,14 +1559,14 @@ 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

@@ -1430,7 +1594,7 @@ 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.

@@ -1475,7 +1639,7 @@ 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

@@ -1512,7 +1676,7 @@ open, edit, save # Tweak it like any doc<
-
+

What Goes in CLAUDE.md

# CLAUDE.md @@ -1540,7 +1704,7 @@ 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:

@@ -1573,14 +1737,14 @@ 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

@@ -1624,7 +1788,7 @@ 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.

@@ -1679,14 +1843,14 @@ 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 @@ -1713,7 +1877,7 @@ 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:

@@ -1736,7 +1900,7 @@ 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.

@@ -1787,7 +1951,7 @@ 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.