diff --git a/app/api/chat/route.ts b/app/api/chat/route.ts
index 22813ab..a96948f 100644
--- a/app/api/chat/route.ts
+++ b/app/api/chat/route.ts
@@ -35,8 +35,9 @@ Pre-screen context: Technical depth for platform engineer role. Cert rotation, q
 
 export async function POST(request: NextRequest) {
   const token = process.env.LLM_API_TOKEN
+  const isDev = process.env.NODE_ENV === 'development'
 
-  if (!token) {
+  if (!token && !isDev) {
     return new Response(
       JSON.stringify({ error: 'LLM_API_TOKEN not configured' }),
       { status: 500, headers: { 'Content-Type': 'application/json' } }
@@ -46,6 +47,44 @@ export async function POST(request: NextRequest) {
   try {
     const { message } = await request.json()
 
+    // Dev fallback: mock streaming response
+    if (isDev && !token) {
+      const encoder = new TextEncoder()
+      const mockReasoning = `Analyzing "${message}"...`
+      const mockContent = `Rock has 6+ years experience in Infrastructure, Backend, and LLM Systems. His expertise spans Kubernetes, Terraform, vLLM optimization (60% latency cut), AWS Distributed-Map across 57+ regions, and production homelab with 99.2% uptime.`
+
+      const stream = new ReadableStream({
+        async start(controller) {
+          let reasoning = ''
+          let content = ''
+          
+          // Stream reasoning
+          for (const char of mockReasoning) {
+            reasoning += char
+            controller.enqueue(encoder.encode(`data: ${JSON.stringify({ type: 'reasoning', text: reasoning })}\n\n`))
+            await new Promise(r => setTimeout(r, 5))
+          }
+          
+          // Stream content
+          for (const char of mockContent) {
+            content += char
+            controller.enqueue(encoder.encode(`data: ${JSON.stringify({ type: 'content', text: content })}\n\n`))
+            await new Promise(r => setTimeout(r, 10))
+          }
+          
+          controller.enqueue(encoder.encode(`data: ${JSON.stringify({ type: 'done' })}\n\n`))
+          controller.close()
+        },
+      })
+      return new Response(stream, {
+        headers: {
+          'Content-Type': 'text/event-stream',
+          'Cache-Control': 'no-cache',
+          'Connection': 'keep-alive',
+        },
+      })
+    }
+
     const response = await fetch(LLM_API_URL, {
       method: 'POST',
       headers: {