Three products, running live in your browser.
Interactive stand-ins for AI features I've shipped — a virtual try-on, multimodal part identification, and an adtech request inspector. Each is drawn procedurally on a canvas and scripted to mirror the real pipeline's timings and outputs. No photos, no uploads, no network calls — just the shape of the product, playable.
Voilae — a try-on button on every product page.
Pick a garment and hit generate. The first render is a cold miss — a live
inference call that takes a beat and costs a few cents. I cache the result, so every render after is instant and
$0.00. This is a pixel-art stand-in for Voilae's runTryOn() pipeline, rendered live
here — no photos, no uploads.
A stylized stand-in — the figure and garments are drawn procedurally, and the timings/costs mirror fal.ai's real numbers ($0.075/render). In Voilae the same path runs FASHN v1.6 with fal.ai failover and a real result cache.
modr — point the camera, get answers, not guesses.
Two sides of modr's multimodal vision. Decode a diagram — feed an exploded view
and modr labels every component, writes a step-by-step repair procedure, and flags the cautions. Or
identify a part from a single photo — a clean shot resolves to an exact OEM number and high
confidence, while a blurry one lands under the 60% floor, where modr returns Unknown
instead of inventing a number. Pixel-art stand-ins for the real diagram vision and analyze-part()
calls, rendered live here.
A stylized stand-in — the part is drawn procedurally and the analysis is scripted. In modr the same path sends the photo to Gemini 3 Pro vision and returns this exact strict-JSON shape (name, partNumber, category, oem, confidence, alternates); anything under the confidence floor is routed to a clarify step rather than guessed.
A stylized stand-in — the diagram and its analysis are scripted. In modr the diagram API sends the image to Gemini 3 Pro vision (flash fallback) and returns strict JSON: components with bounding boxes, step-to-part mappings, a parts glossary, and an executive summary with cautions.
AdFlow — load a page, watch the ad chain unfold.
Hit capture and the article's 300×250 slot runs a live header-bidding auction — four SSPs bid, a winner renders. Alongside, AdFlow captures every request, names the vendor and stage of each, and flags its signature bug: a viewability beacon firing before the impression it measures. Capture stays local until you click Explain with AI — then a Claude session summary streams in. A stand-in for the real inspector, rendered live here — no network, no HAR file.
A stylized stand-in — the page and creative are drawn procedurally and the auction is scripted (CPMs and the beacon timing mirror a real programmatic call). In AdFlow the same path intercepts live traffic, recognizes 200+ vendors, decodes OpenRTB, and streams the summary from Claude (Haiku 4.5) — the capture never leaves your machine until you ask.