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 cb143f9..e7ba514 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
@@ -516,9 +516,73 @@
-
+
+
💪 Harness — e.g. tools, MCP, memory
+
+
+
🌍 Reach beyond training
+
WebSearch, WebFetch, MCP servers
+
+
+
✋ Act on your files
+
Read, Edit, Write, Bash
+
+
+
+
The body around the brain
+
Gives the model hands to do, and eyes to see beyond its training.
+
+
+
+
+
+
+
+
💪 Limitation — Doesn’t always use its tools
+
Same question, different prompt — sometimes the harness asks first instead of acting.
+
+

+
+
+
+
+
+
+
+
💪 Limitation — Different sources, different answers
+
Same question across runs can route through different tools and sources.
+
+

+
+
+
+
+
+
+
+
💪 Limitation — Tools can fail
+
External tools can time out, return errors, or fetch stale data.
+
+

+
+
+
+
+
+
+
+
+
💪 Same question. Different path each time.
+
A harness gives the brain hands — but not a fixed routine.
+
+
+
+
+
+
+
Vibe Coding vs Agentic Engineering
@@ -587,7 +651,7 @@ todoapp/
-
+
What is Vibe Coding?
@@ -616,7 +680,7 @@ todoapp/
-
+
Good vs Bad Prompts
Even before you set up any structure, how you prompt matters. Specific beats vague. Context beats assumption.
@@ -652,7 +716,7 @@ 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.
@@ -699,14 +763,14 @@ 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
@@ -729,7 +793,7 @@ 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.
@@ -770,7 +834,7 @@ todoapp/
-
+
Agents Get Their Own Brain
Tip from Thariq (Anthropic) — Apr 16, 2026
@@ -803,7 +867,7 @@ 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.
@@ -846,7 +910,7 @@ 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:
@@ -894,14 +958,14 @@ 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
@@ -928,7 +992,7 @@ todoapp/
-
+
When to Turn Something Into a Skill
Tip from Boris Cherny (creator of Claude Code) — Feb 1, 2026
@@ -965,7 +1029,7 @@ todoapp/
-
+
Why Separate Agents and Skills?
@@ -991,7 +1055,7 @@ todoapp/
-
+
How to Create Your Own Skill
Skills are plain markdown files. If you can write a recipe, you can write a skill.
@@ -1044,7 +1108,7 @@ 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:
@@ -1084,14 +1148,14 @@ 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
@@ -1129,7 +1193,7 @@ 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.

@@ -1163,7 +1227,7 @@ 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.
@@ -1207,7 +1271,7 @@ 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.
@@ -1252,14 +1316,14 @@ 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
@@ -1287,7 +1351,7 @@ 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.
@@ -1332,7 +1396,7 @@ open, edit, save <
-
+
Grow CLAUDE.md With Every Mistake
Tip from Boris Cherny (creator of Claude Code) — Feb 1, 2026
@@ -1369,7 +1433,7 @@ open, edit, save <
-
+
What Goes in CLAUDE.md
@@ -1397,7 +1461,7 @@ 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:
@@ -1430,14 +1494,14 @@ 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
@@ -1481,7 +1545,7 @@ 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.
@@ -1536,14 +1600,14 @@ 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:
@@ -1570,7 +1634,7 @@ 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:
@@ -1593,7 +1657,7 @@ 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.
@@ -1644,7 +1708,7 @@ 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.
diff --git a/presentation/assets/harness/harness-limitation-1.jpg b/presentation/assets/harness/harness-limitation-1.jpg
new file mode 100644
index 0000000..4fe8c22
Binary files /dev/null and b/presentation/assets/harness/harness-limitation-1.jpg differ
diff --git a/presentation/assets/harness/harness-limitation-2.jpg b/presentation/assets/harness/harness-limitation-2.jpg
new file mode 100644
index 0000000..c52e8bb
Binary files /dev/null and b/presentation/assets/harness/harness-limitation-2.jpg differ
diff --git a/presentation/assets/harness/harness-limitation-3.jpg b/presentation/assets/harness/harness-limitation-3.jpg
new file mode 100644
index 0000000..9576eb5
Binary files /dev/null and b/presentation/assets/harness/harness-limitation-3.jpg differ