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 f453f2a..880a928 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
@@ -525,39 +525,45 @@
🧑💼
Agents — the specialists
-
A dedicated Claude worker — own context, tools, focus.
+
A dedicated Claude worker — own context, tools, focus.
+
✅ fresh brain per run
🎯
Skills — the know-how
-
What the specialist (or Claude) can actually do.
+
What the specialist (or Claude) can actually do.
+
✅ progressive disclosure
📘
Workflows — the instruction manual
-
Repeatable step-by-step recipes — like an AC install guide.
+
Repeatable step-by-step recipes — like an AC install guide.
+
✅ reproducible recipes
📝
CLAUDE.md — your memory
-
Knowledge you provide to the model.
+
Knowledge you provide to the model.
+
⚠️ 200-line problem
📝
System Prompt — Claude’s memory
Knowledge Anthropic bakes in.
-
e.g. identity · tone · safety
+
e.g. identity · tone · safety
+
✅ always on
💭
Context — the working memory
-
What Claude holds in his head now.
+
What Claude holds in his head now — fresh every new chat session.
+
⚠️ dumb-zone problem
@@ -593,9 +599,30 @@
-
+
+
🎉 Yayyyyy! Problem solved with harness
+
The harness reaches out via WebSearch and fetches a real answer from live sources.
+
+

+
+
+
+
+
+
+
+
+
?
+
But does the harness always work this cleanly?
+
+
+
+
+
+
+
💪 Non-determinism — Doesn’t always use its tools
Same question, different prompt — sometimes the harness asks first instead of acting.
@@ -604,20 +631,9 @@
-
+
-
-
💪 Non-determinism — Different sources, different answers
-
Same question across runs can route through different tools and sources.
-
-

-
-
-
-
-
-
-
+
💪 Non-determinism — Tools can fail
External tools can time out, return errors, or fetch stale data.
@@ -626,9 +642,9 @@
-
+
-
+
💪 Same question. Different path each time.
A harness gives the brain hands — but not a fixed routine.
@@ -638,7 +654,7 @@
-
+
Vibe Coding vs Agentic Engineering
@@ -707,7 +723,7 @@ todoapp/
-
+
What is Vibe Coding?
@@ -736,7 +752,7 @@ todoapp/
-
+
Good vs Bad Prompts
Even before you set up any structure, how you prompt matters. Specific beats vague. Context beats assumption.
@@ -772,7 +788,7 @@ 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.
@@ -819,14 +835,14 @@ 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
@@ -849,7 +865,7 @@ 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.
@@ -890,7 +906,7 @@ todoapp/
-
+
Agents Get Their Own Brain
Tip from Thariq (Anthropic) — Apr 16, 2026
@@ -923,7 +939,7 @@ 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.
@@ -966,7 +982,7 @@ 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:
@@ -1014,14 +1030,14 @@ 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
@@ -1048,7 +1064,7 @@ todoapp/
-
+
When to Turn Something Into a Skill
Tip from Boris Cherny (creator of Claude Code) — Feb 1, 2026
@@ -1085,7 +1101,7 @@ todoapp/
-
+
Why Separate Agents and Skills?
@@ -1111,7 +1127,7 @@ todoapp/
-
+
How to Create Your Own Skill
Skills are plain markdown files. If you can write a recipe, you can write a skill.
@@ -1164,7 +1180,7 @@ 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:
@@ -1204,14 +1220,14 @@ 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
@@ -1249,7 +1265,7 @@ 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.

@@ -1283,7 +1299,7 @@ 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.
@@ -1327,7 +1343,7 @@ 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.
@@ -1372,14 +1388,14 @@ 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
@@ -1407,7 +1423,7 @@ 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.
@@ -1452,7 +1468,7 @@ open, edit, save <
-
+
Grow CLAUDE.md With Every Mistake
Tip from Boris Cherny (creator of Claude Code) — Feb 1, 2026
@@ -1489,7 +1505,7 @@ open, edit, save <
-
+
What Goes in CLAUDE.md
@@ -1517,7 +1533,7 @@ 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:
@@ -1550,14 +1566,14 @@ 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
@@ -1601,7 +1617,7 @@ 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.
@@ -1656,14 +1672,14 @@ 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:
@@ -1690,7 +1706,7 @@ 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:
@@ -1713,7 +1729,7 @@ 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.
@@ -1764,7 +1780,7 @@ 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.