AYEQ · OPTICAL EXPEDITER SYSTEM REC /SENECA /ANE · ON-DEVICE /22:41:08

LIVESeneca · every dinner service · on-device

Watches every plate
at the pass.

…and catches what’s wrong before it leaves the kitchen.

An overhead camera reads every plate, checks it against the live Toast ticket, and flags a mismatch the moment before it goes out. Silent when it’s right.

“Caught at the pass.”

● TRACKING PLATE · 0.98
FIG. 01 — THE PASS Hero footage / still overhead view · 16:9 · drop in assets/media/hero.mp4 or hero.jpg
▸ What AyeQ sees at the pass — every plate, against every ticket.
See how it works

§01 The idea

01

Guardian of the pass

The last line of defense — it catches the wrong or incomplete plate before it reaches the guest. Watchful and protective, never a spy on the line.

02

Invisible intelligence

You see the outcome — the right plate. The AI is a quiet engine underneath, trusted because it’s trained on your menu, not a generic model.

03

Quietly confident

Clean, understated, precise. A high-end instrument that respects the craft of the kitchen, and earns its place at the pass.

§02 The problem

A wrong plate is expensive. Every single time.

During the rush, the expediter is only human. A missing sauce, the wrong side, a plate sent to the wrong table — each one is a comp, a remake, a slower ticket, a one-star review. And the one nobody can afford: an allergen on a plate it should never be on. The pass is the last line of defense, and tonight it rests entirely on one busy person catching every error, every time.

§03 How it works

Four steps, every plate. In well under a second.

  1. 01

    Watches every plate

    An overhead camera above the expo line sees each plate the moment it lands — no scanning, no extra step for the kitchen.

  2. 02

    Reads the dish & its parts

    A two-stage on-device pipeline names the dish, then verifies its components — sauces, sides, garnishes — down to the plate.

  3. 03

    Checks the live ticket

    Each plate is matched against the open Toast order, so AyeQ knows what should be there — not just what is.

  4. 04

    Flags the mismatch

    Right plates pass in silence. A miss raises a quiet overlay: what was expected, what was seen, one tap to flag.

AyeQ component detection on a burger plate at Seneca — french fries, pickle, ketchup and bun each detected with a confidence score; four for four, plate cleared
▸ Every component on the plate, named and scored — four for four.
AyeQ matching a Lamb Lollipops plate to its Table 5 ticket — including the 'no tzatziki' modifier — and clearing it to run to the table
▸ A correct match, confirmed at the pass — Lamb Lollipops to its ticket, ‘no tzatziki’ modifier and all.

§04 The catch, in action

The plate that was about to go out wrong.

This is the whole product in one moment: a plate at the pass, the live ticket beside it, and the one thing that’s missing — caught before it ever reaches the table.

▸ MISS CAUGHT SAT 23:42
FIG. 04 — THE SAVE A real catch from service the overlay · the ticket · the save · assets/media/the-catch.mp4
▸ A live catch: the overlay shows what the ticket expected against what reached the pass.

§05 Allergens

The same eye that catches a missing sauce catches an allergen on the wrong plate.

AyeQ knows your menu — and what’s in each dish. When a plate carries something a guest flagged an allergy to, the expo sees it at the pass, live. It’s the wedge that turns accuracy into safety. Running today at Seneca.

And it doesn’t guess at allergens. The vision probe detects the ingredients actually on the plate; each one resolves through a deterministic parser — the explicit, auditable ingredient-to-allergen map behind AyeQ’s allergy assistant — and is checked against what the ticket flagged. The detection is the model’s job; the allergen call itself is a fixed rule, not a prediction.

  1. Ingredient detected
  2. Deterministic allergen parser
  3. Matched to the ticket
  4. Flagged at the pass
AyeQ allergen overlay at the pass — 'Tree nut: pistachio butter detected, verify' on a Coal Roasted Beets plate for Table 4
▸ A real catch at Seneca: pistachio butter (tree nut) flagged on the plate — a positive sighting to verify against the ticket, never a clearance.

§06 The technology

Why it can do this. On a standard iPad, right at the pass.

01

On-device, always

Both vision models run on the iPad’s own Neural Engine. Every live check happens on the device — no cloud round-trip, no network to wait on mid-rush, and nothing streamed out of your kitchen in real time.

02

A model per restaurant

Each kitchen runs its own model, fine-tuned to its exact menu and plating. It sharpens every night from your own service — data kept in storage that’s private to your restaurant, never pooled with anyone else’s.

03

Built on proven vision

A fast, proven detector finds every dish on the pass; a second model verifies its components down to the plate — sauces, sides, garnishes. Both run as pure on-device inference, with nothing to post-process.

04

Plugged into Toast

AyeQ reads the live ticket straight from your POS, so the check is against the real order, in real time — not a guess about what the plate should be.

Instrument readout

06·1
0.95
mAP50 — detection accuracy on Seneca’s live menu
06·2
~13ms
per detection, on the iPad Neural Engine
06·3
2-stage
on-device CoreML pipeline — detector then probe
06·4
76
components AyeQ can recognise on a plate
06·5
Real-time
matched against the live Toast ticket as it’s plated
06·6
100%
empty-pass frames cleared with zero false alarms (3,517 tested)

Measured on Seneca’s live menu and hardware; on-device inference, no cloud round-trip on the live check. Service-accuracy figures — plate-to-ticket match — are reported separately, with their method and false-alarm rate.

§07 The operator

The kitchen behind it.

AyeQ runs at Seneca every dinner service — an overhead camera at the pass, checking every plate against the ticket before it leaves the kitchen. It’s been live for months, sharpened night after night against a real rush. Not a pilot staged for a demo; the working kitchen it earns its keep in.

“On a Saturday rush, it catches plates my expediter misses.”

Mike Spain — founder, AyeQ · owner, Seneca
● OPERATOR
FIG. 06 — THE OWNER Mike at the pass 3:4 portrait · assets/media/founder-mike.jpg

§08 Honest about what it is

What AyeQ is. And what it isn’t.

AyeQ is

  • A second set of eyes at the pass
  • Trained on your exact menu and plating
  • Honest about its false alarms
  • Private to your restaurant — your data is never pooled with anyone else’s

AyeQ isn’t

  • A replacement for your expediter
  • A generic, one-size-fits-all model
  • A claim of perfection
  • A live video feed streaming your kitchen to the cloud

It flags what it can see. It never clears a plate as safe.