Creative technologist Email →

Alessio
Bevilacqua

Directs cinematic AI content and builds the workflows that make it repeatable.

Brief in, finished spot out, with every element, prompt and run written down so it can be run again.

Selected work
01

The Signal

Spec commercial · Heineken · 2026

A spec spot for Heineken. At dusk, Ray pops a cap on his porch and three neighbourhood dads answer from their windows without a word. Each one sneaks out, each one gets caught, and behind the fence they clink as quietly as they can. Then a second pop from the other side: the wives were never fooled. I built every character, location and prop as an element (23 of them), so the bottle never morphs and the faces hold in every shot.

Seedance 2.5Seedream 5.0 ProRecraft V4.1Magnific SpacesFinal Cut Pro2 days, brief to film
02

Heirloom

Spec brand film · Di Paolo & Co. · 2026

A spec film for Di Paolo & Co., a Toronto atelier that remakes heirloom jewellery. One ring follows a bride from a 1965 church in Italy to her granddaughter's wedding in Canada, remade at the jeweller's bench along the way. I wrote it and built every character, hand, prop and location as an element (21 of them), so the ring stays the same ring for sixty years.

Seedance 2.5Soul CinemaSeedream 5.0 ProElevenLabsFinal Cut Pro2 days, brief to film
03

13th Floor: FW Drop

Brand-approved spec · 2026

I pitched 13th Floor a late-'90s editorial for their bomber and denim, shot like it was on film: five cities, five people, one look. The owner approved it for release, and I built every character and city as an element so the product and the grade hold in every shot.

Seedance 2.5Soul CinemaSeedream 5.0 ProFinal Cut Pro37 generations
See how it was made ↓
04

The Last Fig

Action-comedy short · 2026

Four guys steal a fig, cut like a Nolan heist: establishing wides, a binocular POV, extreme close-ups, over-the-shoulders. I wrote it, blocked it with Blender previz and staging diagrams, generated it in Higgsfield and cut it in Final Cut.

Seedance 2.5Seedream 5.0 ProSoul 2.0Nano Banana Pro148 generations
See the process on Higgsfield →

Also: Spider-Man: RAF Vol.1, fan film, sound design & foley (682K views)

Ego Death, music video: writer, sound design, artist; assisted on the edit

How I work

Every film runs through the same pipeline. Here it is, with the proof.

Claude Code drives my own local studio on the Higgsfield API, over an MCP server I wrote. Seedance 2.5 and Soul Cinema run through Higgsfield; the character sheets are Seedream 5.0 Pro.

01

Brief to locked plan

13th Floor started as a voice memo. It became a script where every decision is marked locked, agreed or open, and the look is picked before anything is generated.

“A high-end Vogue editorial commercial… a late '90s, 2000s kind of vibe. I want it shot on a film camera… old school grungy, but brought back in an expensive way.”From the voice memo, Sep 22
02

A look, turned into a recipe

I wrote the reference look (late-'90s fashion film on 16mm) as two locked lines of text: one closes every location prompt, one closes every video prompt. The grain and the crushed blacks held in every city with no lens words in the prompts.

Tokyo plate
Tokyo
New York plate
New York
Toronto plate
Toronto
São Paulo plate
São Paulo
London plate
London
late-1990s 16mm fashion-film texture: coarse moving film grain, crushed murky blacks, warm skin against cool cyan-green shadows, softly glowing practical lights, gentle gate weave, 24fps motion cadence, candid handheld energy

The video half of the recipe, as it closes every prompt.

03

Elements first

The product sheets are built from the client's real product photos, not AI. Every model and every city is saved as a tagged element before any video runs, so the zip, the patch and the grade come out right in every shot. The Toronto model is me, built from a selfie.

Reference sheet for the 13th Floor hooded workwear bomber
@prop_tf-bomber
Character sheet for the Tokyo model in the bomber and jeans
@char_TF_tokyofw
04

One generation, ten cuts

Every city is written in the same ten-cut order, so one 30-second generation gives a full pool of coverage and five cities cut together as one campaign. São Paulo and London were cut to seven for budget.

Ten frames from one New York generation: establishing, walk, sleeve detail, dice crew, dice, patch, slow shutter, knee pleats, front pose, back pose
New York, one generation: all ten cuts landed in order
05

Test, fix, write it down

Runs get a verdict. New York's back pose came out cropped at the shoulders, so I rewrote the camera line and Toronto came out head to heels. A fix only becomes a rule once a failed generation proves it.

Left: New York back pose cropped at the shoulders. Right: Toronto back pose, full length
Before: “three metres behind him … full length”  /  After: “five metres behind him … from the head to the heels, the ground showing”
06

Block it before paying for it

On The Last Fig I blocked the opening scenes in Blender with stand-in figures and gave Seedance one frame per shot. The staging held. Later scenes used staging diagrams instead.

Top row: three Blender previz frames with stand-in figures. Bottom row: the matching generated shots from The Last Fig
Top: Blender previz  /  Bottom: the generated shot
The system behind it
Studio

My own studio, agent-driven

A local studio on the Higgsfield API with an element library and a run log. I wrote its MCP server, so Claude Code can generate, save elements, pull runs and file them into projects on its own.

Any workflow I repeat becomes a skill agents can rerun, from brief to locked script, to element sheets, to shot prompts.

  • 18MCP tools9brief-to-film skills30+skills in all
By the numbers

What a film actually costs

Four films, start to finish: how long, how many generations, how many Higgsfield credits.

  • The Signal 0:31
    2 daysbrief to film47generations
  • Heirloom 1:07
    2 daysbrief to film196generations
  • 13th Floor 0:55
    1 dayvoice memo to film37generations
  • The Last Fig 1:58
    10 daysto make148generations2,700+credits
Client loop

Brief, build, train, ship

On my own product, Recevia, an AI receptionist live on the App Store and Google Play, I set up each client one on one: wrote their spec, trained the owner, took it live, then shipped what they ran into as the next release. 4,800+ calls answered for real businesses.

About
Alessio Bevilacqua

I make cinematic AI films and build the Claude Code pipelines behind them.

I came up in music as a songwriter and producer: a placement on Drake's For All the Dogs, 143M+ streams across credits. I've been making videos since I was 10. Eight years doing this professionally, the last two-plus hands-on with gen-AI.

I also co-run SelfieBooth, an event production company: 125+ events for clients including Scotiabank, BMO and CBRE, working with their event teams from brief to delivery.