diff --git a/README.md b/README.md
index 7bb1c4a..9a81bfc 100644
--- a/README.md
+++ b/README.md
@@ -12,6 +12,8 @@
 
 [中文版](README.zh-CN.md)
 
+![Agentic Design Patterns — 29 patterns, sketched](assets/hero.png)
+
 > **Transform your AI applications from simple prompts to sophisticated intelligent systems.**
 
 ## 🧭 Principles
diff --git a/assets/hero.png b/assets/hero.png
new file mode 100644
index 0000000..185a15c
Binary files /dev/null and b/assets/hero.png differ
diff --git a/assets/hero/make_hero.sh b/assets/hero/make_hero.sh
new file mode 100755
index 0000000..a5cd566
--- /dev/null
+++ b/assets/hero/make_hero.sh
@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+# Regenerate assets/hero.png — 2x2 montage of 4 representative pattern diagrams
+# in the Da Vinci sepia/parchment palette.
+#
+# Requires: bun (for `bunx`), ImageMagick (`magick`).
+# Mermaid CLI is fetched on-demand by bunx; no global install needed.
+
+set -euo pipefail
+
+cd "$(dirname "$0")"
+OUT="../hero.png"
+BG="#f5ecd9"
+BORDER="#c5b393"
+
+for f in multi-agent rag react tot; do
+  bunx --bun @mermaid-js/mermaid-cli -i "$f.mmd" -o "$f.png" -s 2 -b "$BG"
+done
+
+magick montage multi-agent.png rag.png react.png tot.png \
+  -tile 2x2 -geometry +20+20 \
+  -background "$BG" -bordercolor "$BORDER" -border 8 \
+  "$OUT"
+
+echo "Wrote $OUT"
diff --git a/assets/hero/multi-agent.mmd b/assets/hero/multi-agent.mmd
new file mode 100644
index 0000000..f5fdc6b
--- /dev/null
+++ b/assets/hero/multi-agent.mmd
@@ -0,0 +1,25 @@
+---
+title: Multi-Agent Collaboration
+---
+%%{init: {'look':'handDrawn','theme':'base','themeVariables':{'background':'#f5ecd9','primaryColor':'#ede0bd','primaryBorderColor':'#6b4423','primaryTextColor':'#3e2723','lineColor':'#6b4423','clusterBkg':'#efe5cd','clusterBorder':'#c5b393','edgeLabelBackground':'#f5ecd9','tertiaryColor':'#efe5cd','tertiaryBorderColor':'#c5b393','tertiaryTextColor':'#3e2723','fontFamily':'Caveat, Patrick Hand, cursive'}}}%%
+flowchart LR
+    Goal([research goal])
+    Out([final report])
+
+    subgraph orchestration ["orchestration"]
+        Pl[planner_agent]
+        Plan[/plan steps/]
+        Ex{executor_agent}
+        Pl --> Plan --> Ex
+    end
+
+    subgraph specialists ["specialist agents"]
+        R["research_agent<br/>arXiv · Tavily · Wiki"]
+        W[writer_agent]
+        Ed[editor_agent]
+    end
+
+    Goal --> Pl
+    Ex --> R & W & Ed
+    R & W & Ed -- "result" --> Ex
+    Ex --> Out
diff --git a/assets/hero/rag.mmd b/assets/hero/rag.mmd
new file mode 100644
index 0000000..276a2a1
--- /dev/null
+++ b/assets/hero/rag.mmd
@@ -0,0 +1,23 @@
+---
+title: RAG
+---
+%%{init: {'look':'handDrawn','theme':'base','themeVariables':{'background':'#f5ecd9','primaryColor':'#ede0bd','primaryBorderColor':'#6b4423','primaryTextColor':'#3e2723','lineColor':'#6b4423','clusterBkg':'#efe5cd','clusterBorder':'#c5b393','edgeLabelBackground':'#f5ecd9','tertiaryColor':'#efe5cd','tertiaryBorderColor':'#c5b393','tertiaryTextColor':'#3e2723','fontFamily':'Caveat, Patrick Hand, cursive'}}}%%
+flowchart LR
+    Q([password reset question])
+    Ans([grounded answer + sources])
+
+    subgraph retrieval ["retrieval"]
+        Idx[(support docs<br/>vector store)]
+        Ret[hybrid retriever<br/>BM25 + dense]
+        Ctx[/top-k chunks + citations/]
+        Idx -.-> Ret --> Ctx
+    end
+
+    subgraph generation ["generation"]
+        LLM{{ChatOpenAI}}
+    end
+
+    Q --> Ret
+    Ctx --> LLM
+    Q -. "+ question" .-> LLM
+    LLM --> Ans
diff --git a/assets/hero/react.mmd b/assets/hero/react.mmd
new file mode 100644
index 0000000..4b8a57d
--- /dev/null
+++ b/assets/hero/react.mmd
@@ -0,0 +1,17 @@
+---
+title: ReAct
+---
+%%{init: {'look':'handDrawn','theme':'base','themeVariables':{'background':'#f5ecd9','primaryColor':'#ede0bd','primaryBorderColor':'#6b4423','primaryTextColor':'#3e2723','lineColor':'#6b4423','clusterBkg':'#efe5cd','clusterBorder':'#c5b393','edgeLabelBackground':'#f5ecd9','tertiaryColor':'#efe5cd','tertiaryBorderColor':'#c5b393','tertiaryTextColor':'#3e2723','fontFamily':'Caveat, Patrick Hand, cursive'}}}%%
+flowchart LR
+    Q([query])
+    F([final answer])
+
+    subgraph loop ["ReAct cycle"]
+        T[Thought<br/>reasoning trace]
+        A[Action<br/>tool call]
+        O[/Observation/]
+        T --> A --> O --> T
+    end
+
+    Q --> T
+    T -. "enough info" .-> F
diff --git a/assets/hero/tot.mmd b/assets/hero/tot.mmd
new file mode 100644
index 0000000..dd2a09f
--- /dev/null
+++ b/assets/hero/tot.mmd
@@ -0,0 +1,14 @@
+---
+title: Tree of Thoughts
+---
+%%{init: {'look':'handDrawn','theme':'base','themeVariables':{'background':'#f5ecd9','primaryColor':'#ede0bd','primaryBorderColor':'#6b4423','primaryTextColor':'#3e2723','lineColor':'#6b4423','clusterBkg':'#efe5cd','clusterBorder':'#c5b393','edgeLabelBackground':'#f5ecd9','tertiaryColor':'#efe5cd','tertiaryBorderColor':'#c5b393','tertiaryTextColor':'#3e2723','fontFamily':'Caveat, Patrick Hand, cursive'}}}%%
+flowchart TB
+    Q([problem])
+    Sol([solution])
+
+    Q --> Ta[thought a] & Tb[thought b] & Tc[thought c]
+    Ta & Tb & Tc --> E1{evaluate}
+    E1 -- "best" --> Ta1[a · 1] & Ta2[a · 2]
+    Ta1 & Ta2 --> E2{evaluate}
+    E2 --> Sol
+    E1 -. "backtrack" .-> Tb