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 0e842ca..5bb9791 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 @@ -323,9 +323,22 @@ - +
+ I'll unpack each of these as we go — for now, just let them wash over you.
@@ -463,7 +476,7 @@
- Model (Brain 🧠 — e.g. Opus, GPT) + Harness (Body 💪 — e.g. tools, MCP, memory)
@@ -473,7 +486,7 @@ -The raw model has no real-time access — no internet, no files, no clock.
The harness reaches out via WebSearch and fetches a real answer from live sources.
Really?
@@ -609,7 +622,7 @@ -Similar prompt — but this time the model decided not to use the tool.
The model first tried one source — it failed (403) — so it fell back to another.
These are the two problems we’re trying to solve.
Andrej Karpathy — OpenAI founding team · former Director of AI at Tesla · founder of Eureka Labs.
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 difference in one picture: prompting is asking a stranger on the street; using an agent is asking your dedicated specialist.