diff --git a/src/lib/home/About.svelte b/src/lib/home/About.svelte
index 379dabb..7ad8f2e 100644
--- a/src/lib/home/About.svelte
+++ b/src/lib/home/About.svelte
@@ -136,8 +136,8 @@
 					</article>
 				</div>
 				<figcaption class="mt-4 text-sm text-neutral-500">
-					dpv1 is proven hardware, dpv2 is the current scaling platform, and dpv3 is a concept
-					design under development.
+					dpv1 is the first platform and where the approach was proven, dpv2 is the current platform
+					running today, and dpv3 is a planned design.
 				</figcaption>
 			</figure>
 		</div>
diff --git a/src/lib/home/Proof.svelte b/src/lib/home/Proof.svelte
index 8d6ce37..bd19672 100644
--- a/src/lib/home/Proof.svelte
+++ b/src/lib/home/Proof.svelte
@@ -4,51 +4,55 @@
 			<p class="uppercase tracking-widest text-sm text-neutral-500 mb-4">From proof to platform</p>
 			<h2 class="text-3xl md:text-5xl font-bold text-white mb-6">Measured on physical hardware.</h2>
 			<p class="text-lg leading-relaxed text-neutral-400">
-				dau began with a 5 GB NYSE TAQ market-data dataset and a concrete time-series analytical
-				task: calculate OHLCV bars. After staging data on dpv1, repeated queries ran in 0.92 seconds
-				versus 1.5 seconds on the CPU—39% lower per-query latency, with every result matched against
-				the software golden. That measured workflow now informs the next platform configurations.
+				dau began on dpv1 with a 5 GB NYSE TAQ dataset and a concrete task: calculate OHLCV bars.
+				Staged resident, repeated queries ran in 0.92 seconds against 1.5 seconds on the CPU—39%
+				lower per-query latency, every result matched to the software golden. dpv2 now carries that
+				work further: a fused temporal-finance workflow—as-of join, derived features, time bars and
+				rolling moments in a single pass, with no intermediate ever written back to memory—runs in
+				11.5 ms against 31.4 ms for the same workload on an 18-core laptop, bit-exact. The
+				accelerator costs a fraction of the machine it outruns.
 			</p>
 		</div>
 		<div class="grid gap-4">
 			<div class="rounded-lg border border-neutral-800 p-6">
 				<div class="flex items-start justify-between gap-6 mb-5">
 					<div>
-						<p class="text-sm uppercase tracking-widest text-neutral-500 mb-2">dpv1 · Proven</p>
+						<p class="text-sm uppercase tracking-widest text-neutral-500 mb-2">
+							dpv1 · Where it started
+						</p>
 						<h3 class="text-2xl font-bold text-white">Personal accelerator</h3>
 					</div>
-					<p class="text-sm text-neutral-400 whitespace-nowrap">Initial platform</p>
+					<p class="text-sm text-neutral-400 whitespace-nowrap">First platform</p>
 				</div>
 				<p class="text-lg text-white mb-2">134K LUTs · 1 GB DDR3</p>
 				<p class="text-sm text-neutral-400">
-					Proved resident analytical queries can outperform CPU execution on accessible hardware.
+					Established the core result: resident analytical queries can outperform CPU execution on
+					hardware you can put beside a laptop.
 				</p>
 			</div>
 			<div class="rounded-lg border border-neutral-700 bg-neutral-800 p-6">
 				<div class="flex items-start justify-between gap-6 mb-5">
 					<div>
 						<p class="text-sm uppercase tracking-widest text-neutral-400 mb-2">
-							dpv2 · Scaling now
+							dpv2 · Current platform
 						</p>
 						<h3 class="text-2xl font-bold text-white">Desktop and server accelerator</h3>
 					</div>
-					<p class="text-sm text-neutral-300 whitespace-nowrap">Next platform</p>
+					<p class="text-sm text-neutral-300 whitespace-nowrap">Running today</p>
 				</div>
-				<p class="text-lg text-white mb-2">204K LUTs · 8 GB DDR3 · PCIe x8</p>
+				<p class="text-lg text-white mb-2">204K LUTs · 2 GB DDR3 · PCIe x8</p>
 				<p class="text-sm text-neutral-400">
-					Designed to expand resident capacity and host bandwidth for larger datasets and more
-					parallel configurations.
+					Carries the same designs as dpv1 at wider memory reads and eight parallel lanes—where the
+					fused temporal workflow now beats the CPU baseline.
 				</p>
 			</div>
 			<div class="rounded-lg border border-dashed border-neutral-700 p-6 opacity-50">
 				<div class="flex items-start justify-between gap-6 mb-5">
 					<div>
-						<p class="text-sm uppercase tracking-widest text-neutral-500 mb-2">
-							dpv3 · Design program
-						</p>
+						<p class="text-sm uppercase tracking-widest text-neutral-500 mb-2">dpv3 · Planned</p>
 						<h3 class="text-2xl font-bold text-neutral-300">Enterprise fabric card</h3>
 					</div>
-					<p class="text-sm text-neutral-500 whitespace-nowrap">Concept platform</p>
+					<p class="text-sm text-neutral-500 whitespace-nowrap">In design</p>
 				</div>
 				<p class="text-lg text-neutral-300 mb-2">
 					663K LUTs · 32–128 GB DDR4 · PCIe Gen3 x8 · Fabric links
diff --git a/tests/test.ts b/tests/test.ts
index 8b323b0..668f093 100644
--- a/tests/test.ts
+++ b/tests/test.ts
@@ -21,11 +21,13 @@ test('home page presents both ends of the dau platform', async ({ page }) => {
 		page.getByRole('heading', { name: 'A configuration loop that improves around real work.' })
 	).toBeVisible();
 	await expect(page.getByText('explicit fallback', { exact: false })).toBeVisible();
-	await expect(page.getByText('dpv1 · Proven')).toBeVisible();
-	await expect(page.getByText('dpv2 · Scaling now')).toBeVisible();
-	await expect(page.getByText('dpv3 · Design program')).toBeVisible();
-	await expect(page.getByText('Concept platform')).toBeVisible();
+	await expect(page.getByText('dpv1 · Where it started')).toBeVisible();
+	await expect(page.getByText('dpv2 · Current platform')).toBeVisible();
+	await expect(page.getByText('dpv3 · Planned')).toBeVisible();
+	await expect(page.getByText('In design')).toBeVisible();
 	await expect(page.getByText('39% lower per-query latency', { exact: false })).toBeVisible();
+	// the current platform's measured result, not just the origin story
+	await expect(page.getByText('11.5 ms', { exact: false })).toBeVisible();
 	await expect(page.getByRole('link', { name: 'Become a design partner' })).toBeVisible();
 });