About

Baked goods feed billions. The plant that makes them should not run on memory.

Doughex exists to move the craft of industrial baking into reliable, auditable AI, so every loaf, roll and biscuit is safer, higher-yield and less wasteful. The bakery runs itself; the people who know dough decide how far.

Independent product companyDesign stageBakery only

run_scn_01 · agent graph · scenario 10 nodes · 1 approval gate
01 · orchestrator order.receive ✓ SUCCEEDED 02 · orchestrator twin.simulate ✓ SUCCEEDED 03 · dose_mix mix.dose ✓ SUCCEEDED 04 · ferment_proof proof.hold ✓ SUCCEEDED 05 · makeup_deposit deposit.trim ✓ SUCCEEDED 06 · orchestrator approve.human ◆ APPROVAL 07 · bake_cool bake.zone ✓ SUCCEEDED 08 · defect_inspect inspect.line ✓ SUCCEEDED 09 · robot_handling handle.pack ✓ SUCCEEDED 10 · quality_conf release.genealogy ✓ SUCCEEDED

Illustrative scenario: Plant run · one bread line, flour-lot change at the silo · shared oven. Not a measured run.

Why

Why we are building this

Baked goods are among the highest-volume foods on earth, produced on continuous, high-speed lines feeding billions daily. Running an industrial bakery is still one of the most craft-bound, energy-intensive and waste-heavy processes in food manufacturing, because dough is a living, variable, temperature- and time-sensitive biological system.

Flour, water, yeast and ingredients are dosed and mixed to exact dough development, fermented and proofed to exact rise, made up and deposited to exact weight and shape, baked to exact colour and moisture, cooled, sliced and packed, and inspected for colour, shape, holes, foreign bodies and seal faults. A drift at any step is waste, downgrade, giveaway or a recall.

Most plants run this on fixed recipes and oven profiles, spot checks and the judgment of a shrinking pool of bakers. The tools they have measure and log. None of them act. That is the gap.

Why now

  • The packaged-food and convenience demand boom
  • The premium, health, gluten-free and high-protein shift, and private-label growth
  • Sustainability and energy mandates on ovens
  • Food-safety and allergen pressure
  • A baker and process-operator shortage on lines that never stop
  • Machine vision, inline moisture and weight sensing, edge AI, robotic handling, oven control and process twins finally mature for high-speed baking
Principles

How we build

Trust before autonomy

Grounding, audit, human-in-the-loop and graduated control come before any write to a line.

Every correction trains the system

A process engineer's correction is a labelled training event, not a complaint.

Land narrow, expand relentlessly

One line and one number first. The plant and the group follow the number.

Food safety is not a variable

Kill steps, metal detection, allergen changeover and release decisions stay with the plant's HACCP plan and its people.

Tenant isolation is a design rule

Recipes and customer specs never cross a customer boundary. On-prem is an option, not an exception.

Evaluation gates every change

Golden datasets and model-as-judge evaluations gate model and prompt changes in CI.

Run timeline

What we are actually building

Every Doughex run is an ordered, inspectable sequence. This is run_scn_01, an illustrative scenario: Plant run · one bread line, flour-lot change at the silo · shared oven. Scenario complete · every stage inside spec · one human approval at the oven.

run_scn_01 scenario · not measured SUCCEEDED
  1. 01 order.receive SUCCEEDED 0.8 s

    Plant Orchestrator · Pulled the product spec, the recipe, the HACCP plan with its bake kill-step and metal-detection control points, the allergen status of the line and the new flour lot's certificate from MES and the lab system; locked the target envelope for the run.

  2. 02 twin.simulate SUCCEEDED 38 s

    Plant Orchestrator · Simulated 24 candidate profiles across mix, proof, deposit and oven on the Bakesim as-baked twin for the new flour lot; ranked them on colour and moisture margin, weight margin, energy per unit and takt, and discarded every candidate that thinned the bake kill-step margin.

  3. 03 mix.dose SUCCEEDED 12 m 40 s

    Dose-and-Mix · Adjusted hydration and mix energy for the new lot's absorption so dough temperature and development landed on target; dough state was handed to the proofer with its predicted rise curve.

  4. 04 proof.hold SUCCEEDED 58 m

    Ferment-and-Proof · Predicted the rise curve from inline height, temperature, humidity and CO2, then trimmed proofer humidity and dwell so rise and volume landed on target instead of running fast on the fresher lot.

  5. 05 deposit.trim SUCCEEDED continuous

    Makeup-and-Deposit · Fused checkweigher readings with dough state and divider feedback and trimmed the divider in real time so portion weight sat at the minimum safe margin above the declared weight, with the underweight guardrail armed.

  6. 06 approve.human APPROVAL 1 m 36 s

    Plant Orchestrator · The twin's lowest-energy candidate wanted a zone-three temperature outside the site's bounded envelope. Held for the shift process engineer, who approved the step with a tighter colour alarm.

  7. 07 bake.zone SUCCEEDED continuous

    Bake-and-Cool · Ran the oven against the twin's colour and moisture prediction; stepped zone temperatures and band speed toward the minimum-energy profile while predicted crust colour and crumb moisture stayed inside spec and the core-temperature kill step was verified on every reading.

  8. 08 inspect.line SUCCEEDED continuous

    Defect-and-Inspect · 12 camera streams at oven exit, cooler exit and packing at the plant edge: colour, shape, holes, cracks, foreign-body and seal checks on every unit; two pale-top rejects were attributed to a draught at zone one and the oven agent was notified.

  9. 09 handle.pack SUCCEEDED continuous

    Robot-and-Handling · Robotic depanning, tray transfers and packaging handling paced to the line, with rejected units diverted off the belt and the safe zone around each cell monitored.

  10. 10 release.genealogy SUCCEEDED 1 m 05 s

    Quality-and-Conformance · Lot released: flour lot, recipe, mix and proof setpoints, portion weights, oven profile, kill-step readings, inspection rejects and every human decision written to the genealogy and checked against spec and the HACCP plan.

Focus

What kind of company this is

What we are

  • An independent startup building original physical-AI software for bakery manufacturing
  • A product company: recurring software, priced per line, per plant and per group
  • GPU-essential by design: edge vision and sensing inference, oven CFD twins, synthetic rare defects, model training
  • Bakery only, from dosing to packing

What we are not

  • Not a consultancy, systems integrator or outsourced development firm
  • Not a reseller or a division of an equipment OEM
  • Not a dashboard; a system that acts, with a person above the threshold
  • Not claiming customers, results or certifications we do not have
Accelerated computing

Physical AI, at the plant edge

Dough is alive and the lines never stop, so perception has to be local and fast. Doughex runs GPU inference at the plant edge and keeps training, simulation and optimisation in the cloud, in a private cloud or on-prem. Items marked planned are on the roadmap, not running.

Jetson Orin / Thor · DeepStream · Holoscan · TensorRT

Edge perception

8 to 24 cameras per line plus inline moisture, weight, thermal and metal or X-ray streams. Design target: sub-100 ms reject decisions, 10 to 60 FPS per station, offline-tolerant operation at the plant edge.

Triton · NIM

Model serving

Bake-prediction, defect, weight, shelf-life and bakery-reasoning models behind one orchestrator, with version routing by product, line and station. Plants run many lines, SKUs and models at once.

DGX / HGX · NeMo · RAPIDS

Training (planned)

Vision, time-series, multimodal and bakery-process models fine-tuned from batch telemetry, images, engineer corrections and lab outcomes. Initial design target: 50 to 200 GPU-hours per product family per release.

Omniverse · Modulus · OVX

Digital twin (planned)

GPU-accelerated oven CFD, proof heat and humidity dynamics, dough rheology and deformation, and robot cells, run as-baked before the run to find quality-safe, low-energy profiles.

Cosmos · Omniverse Replicator

Synthetic data (planned)

Rare foreign-body, under- and over-bake, blistering, cracked-top, hole, deformation and seal or fill scenarios, generated with domain randomisation and validated against real plant events before use.

cuOpt

Optimisation

Oven and changeover scheduling, energy allocation across zones and lines, proof dwell allocation and line balancing, recomputed on the GPU when the line is disrupted.

Isaac · Jetson

Robotic handling

Pan loading and unloading, tray transfers, reject diversion and packaging handling, with perception and motion policies built in Isaac Sim before they touch the line.

Market

The market

Bakery manufacturing automation, mixing, proofing and oven control, depositing and forming systems, inline quality and foreign-body inspection, food-safety systems, bakery MES and factory software. Autonomous proofing and baking control, defect and foreign-body sensing and bakery digital twins are the fastest-growing segments.

$15B Total addressable market: bakery automation, mixing, proofing and oven control, depositing and forming, inline quality and foreign-body inspection, food-safety systems, bakery MES and factory software
$3.7B Serviceable market: autonomous proofing and baking control, defect and foreign-body sensing and bakery digital twins at industrial bakeries
$230M Obtainable within three years through land-and-expand across mixing, proofing and baking lines
~11% Annual growth of the addressable spend
Team

Who is building it

Doughex is led by its founder and CEO, Matthew Sinclair, and its CTO, Eric Donovan. The profiles below describe what each of them owns and the ground they cover.

Founder & CEO

Matthew Sinclair

Matthew runs the company and owns the design-partner relationships, the pilot structure and the commercial model. He decides which bakery and which line go first, what waste, giveaway or energy number a pilot is judged on, and who in the plant signs off on the baseline.

Focus: industrial bakery operations, food-manufacturing economics, plant partnerships and go-to-market.

CTO

Eric Donovan

Eric owns the plant-edge runtime, the dough, bake and inspection models, the as-baked product twin, and the audit architecture behind every Doughex agent. He is accountable for the bounded, logged write-back into mixers, proofers, depositors and ovens, and for every agent starting in shadow mode.

Focus: edge computer vision, process control, simulation and digital twins, safety-critical industrial software.

Hiring

The roles we are building around are on the careers page. We look for people with hands-on bakery or food-manufacturing operations, applied AI at the edge, and experience shipping regulated, safety-critical software or hardware.

The roles we are building around

The name and the mark

Doughex is built on dough, the raw heart of baking, with an ending chosen to stand apart from the rest of the portfolio it belongs to. The mark is a scored loaf on the oven band: a domed loaf with three diagonal score cuts, the slashes a baker makes before the oven, over the dark bar of the belt the loaf travels on in an industrial line. Scoring is a small, exact, process-defining action, which fits a company that controls dough development, proofing and bake.

Golden crust for the product rather than the machinery, and the oven band beneath it.

Writing

Recent notes

Origin

Where bakeries lose margin they cannot see

Talk to a plant director and the same costs surface. Depositors overshoot the target weight to avoid ever going underweight, so giveaway bleeds out gram by gram…

From the plant floor

Who this is built for

The three people in an industrial bakery whose week changes when the line runs itself, and what each of them needs from Doughex.

Economic buyer

Plant or Operations Director

Owns production rate, quality, waste, giveaway and yield, energy and food safety. Wants a bakery that holds spec at higher rate with fewer interventions, and a number that justifies the spend.

Champion

Bakery or Process Engineer

Owns recipes, dough development, proof and oven profiles, process windows and yield. Approves and corrects the agents in recommend mode; those corrections train the models.

Approver

Quality and Food-Safety Manager

Owns HACCP, FSMA, BRCGS, ISO 22000 and allergen conformance, foreign-body and defect conformance, and lot genealogy. Needs every action grounded, cited and written to an immutable record.

IT/OT and sustainability leads approve the deployment. There are no customer quotes on this site yet; design partners will speak for themselves when they choose to.

Guardrails

An agent that can move a setpoint needs a leash

Doughex writes to production equipment in a food plant. Every capability is scoped, every write is policy-checked, every output is cited, and every action is written to an append-only audit log the plant owns.

  • Bounded action space. Each agent can only write to an explicit tag allow-list, inside per-tag rate and magnitude limits, at the autonomy level the plant has set.
  • Critical control points are read, never written. The bake kill step, metal detection and X-ray rejects, allergen changeover and release decisions stay with the HACCP plan and the people who own it.
  • Policy engine before every write. Autonomy level, interlock state, product, allergen status, shift and operator presence are evaluated before a setpoint moves.
  • Grounded and cited. Every recommendation carries a citation to the recipe, spec or procedure it relied on. Retrieval is tenant-isolated and permission-aware.
  • Immutable audit log. Append-only, exportable and retained on the plant's own storage, aligned to HACCP, FSMA, BRCGS and ISO 22000 record-keeping.
  • Hard fallback. If the edge node, the network or a model stops, the line keeps running on its existing PLC and SCADA control and interlocks.
  • Tenant and IP isolation. Recipes, customer specs and tolerance models never cross a customer boundary. On-prem deployment available.

Assurance posture

Assurance and certification status
ItemScopeStatus
SOC 2 Type ICloud control plane QUEUED Roadmap, first 6 months
SOC 2 Type IICloud control plane QUEUED Roadmap, 6 to 12 months
HACCP · FSMA · BRCGS · ISO 22000 · allergenGrounding and record-keeping RUNNING Design basis for retrieval and the audit log
Per-tenant isolationData, memory, models RUNNING Design rule
On-prem deploymentRecipe-sensitive bakeries RUNNING Design option

Doughex supports your food-safety records. It is not a certification and it does not replace your HACCP plan.

Read the security overview

FAQ

Straight answers

The questions plant directors, process engineers and quality managers ask in the first meeting.

Only at the autonomy level your plant has set, and only to an explicit allow-list of low-risk loops inside explicit limits. Every design partner starts in observe mode, where Doughex predicts and writes nothing. Recommend mode follows, where a process engineer approves each move. Bounded autonomy on oven, depositing and inspection loops comes after the food-safety and ROI gates agreed up front.

Get started

Come build the bakery's operating system

Design partners, future colleagues and the people who sell to bakeries: the first conversation is about one line.