Features

Everything a bakery needs to trust software that acts.

Autonomy in a food plant is a set of features that make action safe: cited reasoning, graduated control, bounded writes, an immutable audit log, lot genealogy and a twin that rehearses the profile first. This page lists them one by one.

Cited outputsGraduated autonomyImmutable audit log

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.

Core

The features that make autonomy safe

Each of these exists because an industrial bakery is food-safety-critical, allergen-critical and continuous.

Perception

Inline sensing and vision

Dough temperature, rise, portion weight, moisture and crust colour from inline sensors and checkweighers; colour, bake, shape, hole, foreign-body and seal vision at line speed.

Prediction

Prognostics with lead time

Dough running fast or slow, weight drift, colour and moisture excursions, mixer, proofer and oven wear, predicted early enough to act.

Control

Adaptive setpoints and profiles

Closed loops on hydration and mix energy, proof dwell and humidity, depositor trim and oven zones, inside explicit limits, at the autonomy level you set.

Rehearsal

Profile before the run

Bakesim ranks candidate profiles on colour and moisture margin, weight margin, energy and takt, and discards any that thin the kill-step margin.

Evidence

Cited reasoning

Every recommendation carries a citation to the recipe, spec, HACCP plan or allergen procedure it relied on, through tenant-isolated retrieval.

Record

Audit log and genealogy

Every reading, recommendation, write, approval and release in an append-only log, assembled into the lot genealogy for release.

Memory

Craft capture

Per-bakery yield-and-quality history and per-engineer corrections, versioned and scoped per tenant, so the next lot starts from what the last one taught.

Attribution

Defect to cause

Each inspection reject is attributed to the upstream agent and state that caused it, closing the loop across the line.

Optimisation

Yield, energy, giveaway, takt

cuOpt sequences products, oven schedules and changeovers under energy constraints and rebalances the moving line when it is disrupted.

Run timeline

One scenario run, step by step

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.

Tool calls

The agent shows its work

Every tool invocation, argument and result is written to an immutable, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the plant. The log below is the scenario run, not a measured one.

tool-call stream · run_scn_01
  1. 04:40:02mes.read_order({ line: "BR-2", product: "SANDWICH-800", flour_lot: "F-3312" })
  2. 04:40:02ok spec locked · HACCP plan v6 · CCPs: bake kill step, metal detection
  3. 04:40:03lab.read_results({ lot: "F-3312", test: "flour_certificate" })
  4. 04:40:03ok protein and absorption read · lot accepted at the silo
  5. 04:40:04twin.simulate({ candidates: 24, horizon: "shift" })
  6. 04:40:42ok best profile #7 · kill-step margin held · lowest energy per unit
  7. 04:40:43policy.evaluate({ profile: 7, level: "bounded" })
  8. 04:40:43ok 8 writes permitted · 1 write requires human approval
  9. 04:40:44plc.write_setpoint({ tag: "MIX1.ENERGY", basis: "lot absorption + dough temp" })
  10. 04:53:24ok dough temperature on target · development inside window
  11. 04:53:25plc.write_setpoint({ tag: "PRF1.DWELL", basis: "rise curve + humidity" })
  12. 05:51:30ok rise and volume on target · proof not running fast
  13. 05:51:31plc.write_setpoint({ tag: "DIV1.TRIM", mode: "min_safe_margin" })
  14. 05:51:31ok portion weight at minimum safe margin · underweight guardrail armed
  15. 05:51:33approval.request({ action: "oven.zone3", reason: "outside bounded envelope" })
  16. 05:53:09ok approved by the shift process engineer · tighter colour alarm set
  17. 05:53:10plc.write_setpoint({ tag: "OVN1.ZONE3_T", mode: "min_energy" })
  18. 05:53:10ok predicted colour and moisture inside spec · kill step verified
  19. 05:53:11vision.stream({ cameras: 12, models: ["colour_shape", "foreign_body", "seal"] })
  20. 06:21:48reject: pale top · unit 2231 · attributed to draught at zone one
  21. 06:21:49defect.attribute({ event: "pale_top", cause: "oven.zone1_draught" })
  22. 06:21:49ok oven agent notified · second reject at 06:23:12 · zone one corrected
  23. 06:21:50robot.execute({ cell: "DEPAN-1", mode: "guarded", pace: "line" })
  24. 06:21:50ok depanning and tray transfer paced · rejects diverted · safe zone clear
  25. 08:14:20mes.release_lot({ lot: "BR2-3312", genealogy: "full" })
  26. 08:15:25ok lot released · scenario complete

Reasoning trace

Goal, plan, thought, action, observation, exactly as the orchestrator would record it.

GoalStart flour lot F-3312 on bread line BR-2, hold development, r…

Start flour lot F-3312 on bread line BR-2, hold development, rise, weight, colour and moisture on target through the change, and release the lot with full genealogy.

PlanSimulate the whole profile on the twin first. Lead with the mi…

Simulate the whole profile on the twin first. Lead with the mixer so the proofer gets dough with a known rise curve and the divider gets dough with a known density. Verify the bake kill step continuously. Let the oven chase minimum energy only inside the bounded envelope; hold anything beyond it for a person.

ThoughtThe standing recipe overshoots portion weight and runs the ove…

The standing recipe overshoots portion weight and runs the oven hot to protect against lot variability. With continuous dough-state, weight and colour estimates the margins can sit at their minimum safe values. The saving is giveaway and energy, not safety margin: the kill step is never a candidate for optimisation.

Actiontwin.simulate(candidates=24) → profile #7: minimum safe weight…

twin.simulate(candidates=24) → profile #7: minimum safe weight margin, kill-step margin unchanged, lowest predicted energy per unit.

ObservationProfile #7's zone-three temperature sits outside the site's bo…

Profile #7's zone-three temperature sits outside the site's bounded envelope. The policy engine routes that single write to the shift process engineer and permits the other eight.

ActionExecute profile #7 at the bounded level: mixer, proofer and di…

Execute profile #7 at the bounded level: mixer, proofer and divider writes proceed; the zone-three write waits.

ObservationApproval granted at 05:53:09 with a tighter colour alarm. Two …

Approval granted at 05:53:09 with a tighter colour alarm. Two pale-top rejects at oven exit were attributed to a draught at zone one and corrected by the oven agent.

OutcomeScenario complete. The lot released with flour lot, setpoints,…

Scenario complete. The lot released with flour lot, setpoints, kill-step readings, inspection events and the human decision in the genealogy. No measured plant result is claimed; this is the run the platform is designed to execute.

In depth

Three features worth the detail

Latency

Decisions at the line, not in the cloud

A reject decision is only useful if it arrives before the unit leaves the station, and an oven-zone recommendation is only useful if it arrives before the next band of product. The design targets are under 100 ms for rejects, sub-second zone recommendations and 1 to 5 second supervisory intervals, on plant-edge GPUs, with the cloud used for training and simulation.

Latency design targets
DecisionDesign target
Reject at inspection<100 ms
Oven-zone recommendation<1 s
Proof, bake, deposit supervisory interval1–5 s
Cameras per line8–24
Evidence

Nothing is recommended without a citation

The orchestrator retrieves over recipes, proofing and bake specs, food-safety standards (HACCP, FSMA, BRCGS, ISO 22000, allergen) and quality and genealogy procedures. Retrieval is multi-tenant isolated and permission-aware, and every output is traceable to a source.

  • Citation and grounding checks on every output
  • Schema and safety guardrails
  • Golden datasets and model-as-judge evaluation in CI
  • Immutable, assurance-grade food-safety audit log for every action
Rehearsal

The twin discards what the line should never try

Bakesim simulates the product as it will actually be baked, across the coupled physics of oven heat and airflow, proof heat and humidity, and dough rheology and deformation. Candidates that save energy but thin the kill-step margin never reach the agents.

  • Multi-objective ranking: colour, moisture, weight, safety margin, energy, takt
  • Safe control envelopes handed to the agents
  • Twin-versus-actual reconciliation every lot
  • Validated synthetic rare defects for training
Multi-agent handoff

Agents negotiate, they do not collide

Two agents will want the same actuator. The orchestrator arbitrates on the run goal, with food safety above everything, and the handoff is logged like any other step.

Contested move: oven band speed

  1. 01yield_takt.request(band +4%) SUCCEEDED0.2 s

    Yield-and-Takt wants a faster band through the oven so the line clears the proofer backlog and the packing hall is not left waiting.

  2. 02bake_cool.request(band hold) SUCCEEDED0.2 s

    Bake-and-Cool requires the band speed that keeps core temperature above the kill-step threshold for the full dwell. That is the HACCP critical control point.

  3. 03orchestrator.arbitrate SUCCEEDED0.4 s

    Food safety outranks takt under every run goal. The critical control point wins the actuator; the request for more speed is logged with its score and the reason it lost.

  4. 04yield_takt.handoff(resequenced) SUCCEEDED90 s

    Yield-and-Takt recovers the schedule by trimming proofer dwell on the next batch within its window and resequencing the changeover. Takt is met without touching the kill step.

Arbitration rules

  • Run goal first. Every request is scored against the declared goal, not against the requesting agent's local objective.
  • Food safety outranks everything. A critical control point is never an optimisation variable. A kill-step or foreign-body escape is a recall; a takt miss is a schedule.
  • Time-boxed ownership. An agent holds a contested actuator for a bounded window, then must re-justify.
  • Everything is logged. The losing request, the score and the reason all appear in the run record.
  • Deadlocks escalate to a person rather than resolving by timeout.

See the agent roster

Autonomy

Five levels, set per loop

A bakery does not go from manual to bounded control in one step. Doughex makes the level explicit per loop, auditable and reversible at any time, and some decisions never leave the person.

Autonomy levels and the human role at each
LevelWhat the agent doesWhat the person doesWhen
ObservePredicts rise, weight, colour, moisture and defects; writes nothingRuns the bakery as today; compares predictions to QA checksFirst phase with every design partner
RecommendProposes mix, proof, deposit and oven moves with the evidence behind eachA process engineer or baker approves or corrects each oneAfter accuracy is proven against the baseline
Approve to applyPrepares the write; applies it only on a named person's approvalApproves per move; reviews the shift recordOnce recommendations are trusted
BoundedWrites low-risk oven, depositing and inspection setpoints inside explicit limitsApproves anything above the limits; reviews exceptionsAfter the food-safety and ROI gates agreed up front
ExceptionsEscalates anything outside its envelope, CCP-adjacent moves and release decisionsAlways decides these; the agent never doesPermanent
How it works

A goal becomes a plan becomes a run

Nothing about a Doughex run is implicit. The goal is declared, the plan is rehearsed on the twin, each step is typed, and the outcome is written to the lot genealogy.

Active path

The orchestrator plans, the agents act

A run starts as a goal, becomes a plan, and executes as a graph of typed steps. The active path is always visible, always logged, always reversible.

RUNNING APPROVAL SUCCEEDED
Perceive Cameras, checkweighers, moisture and colour sensing, PLC and SCADA, meters
Predict Rise, weight, colour, moisture, defects, shelf life, takt
Act Bounded setpoint and profile moves, with a person above the threshold
Record Audit log and lot genealogy, retrained from every correction
Human in the loop

Autonomy is a dial, not a switch

Observe, recommend, approve to apply, bounded, exceptions. Each plant sets the level per loop, and anything above the threshold, every critical control point and every release decision waits for a named person.

Design targets

Feature design targets

The numbers Doughex is engineered against, from the GPU utilisation plan.

<100 ms reject decisions for inspection at the plant edge
10–60 FPS vision inference per station, depending on the station
8–24 synchronised cameras per high-speed line
1–5 s supervisory control interval for proof, bake and deposit loops
50–200 GPU-hours of fine-tuning per product family per release
100k–1M synthetic rare-event images per defect family, validated before use

Design targets from the GPU utilisation plan. Nothing on this page is a measured plant result; measurements start when the first design-partner line runs in observe mode.

Developers

Every action is a record

There is no SDK to download yet. What design partners get is the integration surface: connectors, an autonomy policy declared per loop, and an audit record for every reading, recommendation, write and approval. This is the shape of one record, illustrative.

What the surface gives you

  • Connectors to PLC and SCADA, checkweighers, moisture and colour sensing, MES, cameras and meters, with declared allow-lists and limits
  • An autonomy policy per loop: level, tags, rate and magnitude limits, named approvers
  • Citations on every recommendation to the recipe, spec or procedure it relied on
  • Model versions named in every record, with rollback by version
  • Export of the audit log and lot genealogy to your quality system

What the docs cover Developer overview

audit record · illustrative
// one write, as the audit log would hold it
{
  "run": "run_scn_01",
  "step": "deposit.trim",
  "agent": "agent.makeup_deposit",
  "level": "bounded",
  "action": { "tool": "plc.write_setpoint", "tag": "DIV1.TRIM" },
  "limits": { "max_step": "declared per tag", "per": "declared per tag" },
  "evidence": ["checkweigher.read", "depositor.read_feedback"],
  "citation": "spec:SANDWICH-800 declared weight v3 §2",
  "policy": "permitted",
  "models": { "weight": "versioned", "policy": "versioned" },
  "human": null,
  "outcome": "inside spec · minimum safe margin"
}
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.

Integrations

It speaks plant, not cloud

Doughex reads and writes through the systems already on the floor. No parallel historian, no new HMI, no rip-and-replace. Connectors are built against each design partner's stack first; long-tail integrations are out of scope for the first release.

Plant automation

PLC and SCADA of mixers, proofers, dividers and depositors, ovens, coolers and slicers

Setpoint reads, guarded writes, interlocks untouched

Inline sensing

Checkweighers, inline moisture and NIR, thermal cameras, dough height, temperature and humidity

Continuous product and process state

Safety detection

Metal detectors and X-ray systems

Read and verified; reject interlocks stay the plant's

Bakery MES

Orders, recipes, product specs, lot genealogy, allergen status

Targets in, release records out

Vision

Multi-camera stations at oven exit, cooler exit, slicer and packaging

Frames, defect events, reject commands

Energy

Plant and oven-level gas and electricity meters

Hard constraints for the oven profile and schedule

Robotics

Isaac-driven depanning, tray transfer and packaging cells

Perception and motion for pans, trays and packs

Identity (planned)

SSO and role-based access; SOC 2 on the roadmap

Named approvers, scoped roles

See all integrations

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

Enterprise

Standardise autonomy across the group

One policy model, one audit trail and one set of yield, waste, giveaway and energy benchmarks across every bakery in the group, with each site's recipes and tolerance models kept private to that site.

Talk to us Enterprise details

  • Multi-site plant-edge fleet with shared model governance
  • Custom recipe, product and tolerance models per site
  • SSO and role-based access, named approvers (roadmap, 6 to 12 months)
  • Model versioning, validation reports and rollback
  • On-prem or private-cloud deployment
  • SLAs and outcome-based components on the highest-value workflows
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

See these features on your line

Observe mode shows the perception, prediction and evidence features before any control feature is enabled.