diff --git a/wasm/app/demos/bend-gpu.lsp b/wasm/app/demos/bend-gpu.lsp
index 3784268..0d1a681 100644
--- a/wasm/app/demos/bend-gpu.lsp
+++ b/wasm/app/demos/bend-gpu.lsp
@@ -9,11 +9,14 @@
 ;   (health)                    → (ok (load-avg ...)) — worker telemetry
 ;   (cuda-shake-fanout INPUTS OUT-BYTES)
 ;                               → (ok (HEX0 HEX1 ...)) — N SHAKE256 outputs
-; Binary modes (BSHK / BCGB / BSCP / BSRT / BSB3) and the
-; 1M-input "feel the GPU win" run stay native-only until Phase 2
-; lands server-side factory recipes — those compile per-call
-; binaries on the worker filesystem and stream them through
-; the existing handlers.
+;   (cuda-sim-ops-bin PATH N-BATCHES)
+;                               → (ok (cuda-sim-result … (timing-ms …)))
+;                                 — kickmix circuit on the worker's bin
+;
+; Binary modes (BSHK / BCGB / BSCP / BSRT / BSB3) stream raw bytes via
+; the wire-TCP path and stay native-only until Phase 2 lands server-side
+; factory recipes (gated on auth — today an open recipe endpoint would
+; let anyone occupy our GPU).
 
 (display ";; 1. probe round-trip ...") (newline)
 (define r1 (bend!-call "(ping)"))
@@ -36,4 +39,14 @@
 (display "   result : ") (display r3) (newline)
 (newline)
 
+(display ";; 4. feel the GPU win — kickmix circuit simulation") (newline)
+(display ";;    14,848 ops / 58 qubits / 9024 shots / 141 batches") (newline)
+(display ";;    tiny HTTP payload (~70 bytes), heavy GPU work") (newline)
+(display ";;    CPU baseline ~1450 ms, GPU kernel ~360 ms (~4x)") (newline)
+(define heavy "(cuda-sim-ops-bin \"/tmp/ecdsa-queue/out.bin\" 141)")
+(display "   payload: ") (display heavy) (newline)
+(define r4 (bend!-call heavy))
+(display "   result : ") (display r4) (newline)
+(newline)
+
 (print "done")
diff --git a/www/playground/demos/bend-gpu.lsp b/www/playground/demos/bend-gpu.lsp
index 3784268..0d1a681 100644
--- a/www/playground/demos/bend-gpu.lsp
+++ b/www/playground/demos/bend-gpu.lsp
@@ -9,11 +9,14 @@
 ;   (health)                    → (ok (load-avg ...)) — worker telemetry
 ;   (cuda-shake-fanout INPUTS OUT-BYTES)
 ;                               → (ok (HEX0 HEX1 ...)) — N SHAKE256 outputs
-; Binary modes (BSHK / BCGB / BSCP / BSRT / BSB3) and the
-; 1M-input "feel the GPU win" run stay native-only until Phase 2
-; lands server-side factory recipes — those compile per-call
-; binaries on the worker filesystem and stream them through
-; the existing handlers.
+;   (cuda-sim-ops-bin PATH N-BATCHES)
+;                               → (ok (cuda-sim-result … (timing-ms …)))
+;                                 — kickmix circuit on the worker's bin
+;
+; Binary modes (BSHK / BCGB / BSCP / BSRT / BSB3) stream raw bytes via
+; the wire-TCP path and stay native-only until Phase 2 lands server-side
+; factory recipes (gated on auth — today an open recipe endpoint would
+; let anyone occupy our GPU).
 
 (display ";; 1. probe round-trip ...") (newline)
 (define r1 (bend!-call "(ping)"))
@@ -36,4 +39,14 @@
 (display "   result : ") (display r3) (newline)
 (newline)
 
+(display ";; 4. feel the GPU win — kickmix circuit simulation") (newline)
+(display ";;    14,848 ops / 58 qubits / 9024 shots / 141 batches") (newline)
+(display ";;    tiny HTTP payload (~70 bytes), heavy GPU work") (newline)
+(display ";;    CPU baseline ~1450 ms, GPU kernel ~360 ms (~4x)") (newline)
+(define heavy "(cuda-sim-ops-bin \"/tmp/ecdsa-queue/out.bin\" 141)")
+(display "   payload: ") (display heavy) (newline)
+(define r4 (bend!-call heavy))
+(display "   result : ") (display r4) (newline)
+(newline)
+
 (print "done")