Allow-list
An agent can only write to tags declared for it.
Security and food safety
Software that can move a setpoint in a beverage plant needs more than a good model.
Brewira is designed around three facts: beverages are food-safety-critical, recipes are intellectual property, and the plant's existing automation must keep running if Brewira stops. This page is the design posture; certifications are on the roadmap and not claimed.
Illustrative scenario: Plant run · one lager batch from brewhouse to can · brewhouse, cellar, filler, tunnel pasteurizer. Not a measured run.
Defense in depth
Six layers between a model and a setpoint
Limits
Per-tag rate and magnitude limits, declared and versioned, inside documented recipe, quality, food-safety, equipment and rollback bounds.
Stage
Shadow, assist or bounded, set per loop; nothing writes in shadow.
Policy engine
Interlock state, brand, package, shift and operator presence evaluated before every write; changes that violate HACCP, FSMA, FSSC 22000 or BRCGS controls are blocked.
Human gate
Anything above the threshold, every CCP-adjacent move and every release waits for a named person.
Fallback
If Brewira stops, the plant runs on its existing PLC and SCADA control and interlocks.
Tool calls
Every call, on the record
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.
- 04:50:02mes.read_order({ batch: "L-0931", brand: "LAGER-33", package: "CAN-330" })
- 04:50:02ok recipe locked · HACCP plan v6 · CCP: tunnel PU 15–20
- 04:50:03lab.read_results({ yeast_lot: "Y-2207", test: "viability" })
- 04:50:03ok viability inside window · lot accepted for pitching
- 04:50:04twin.simulate({ candidates: 24, horizon: "batch" })
- 04:50:42ok best plan #7 · PU margin held · lowest CO2 and energy per hl
- 04:50:43policy.evaluate({ plan: 7, stage: "bounded" })
- 04:50:43ok 7 writes permitted · 1 write requires human approval
- 04:50:44plc.write_setpoint({ tag: "BH1.BLEND_RATIO", basis: "gravity+recipe" })
- 04:53:24ok wort gravity on recipe · utilization held
- 05:10:00ferment.predict_curve({ tank: "FV-12", lot: "Y-2207" })
- 05:10:00ok attenuation curve predicted · finish day 5 · crash timed
- 05:10:01plc.write_setpoint({ tag: "FV12.TEMP_RAMP", window: "brewmaster_approved" })
- 05:10:01ok ramp applied · no stuck or runaway ferment flagged
- 06:02:10plc.write_setpoint({ tag: "CARB1.CO2_DOSE", basis: "co2+do+turbidity" })
- 06:05:25ok CO2 on package target · clarity inside spec · backwash timed
- 06:05:26vision.stream({ cameras: 16, models: ["fill_level", "seam_cap", "label_ocr", "foreign_body"] })
- 06:31:48reject: low fill · can 20417 · attributed to filler valve 14 drift
- 06:31:49defect.attribute({ event: "low_fill", cause: "filler.valve_14" })
- 06:31:49ok fill_seal notified · valve 14 trimmed inside window · two more rejects, then clean
- 06:31:50plc.verify_pu({ tag: "TUN1.ZONES", profile: "validated" })
- 06:31:50ok PU inside profile · readings → audit log
- 06:31:52approval.request({ action: "cip.window", reason: "overlaps next brand start" })
- 06:33:44ok approved by the shift quality manager · PU profile untouched · tighter release check
- 09:12:30mes.release_batch({ batch: "L-0931", genealogy: "full" })
- 09:13:35ok batch released · scenario complete
Reasoning trace
Goal, plan, thought, action, observation, exactly as the orchestrator would record it.
GoalBrew batch L-0931 to recipe gravity, ferment it to target atte…
Brew batch L-0931 to recipe gravity, ferment it to target attenuation, carbonate and fill it to spec at line speed, pasteurize it on the validated PU profile and release it with full genealogy.
PlanSimulate the whole batch on the twin first. Lead with gravity …
Simulate the whole batch on the twin first. Lead with gravity so the cellar gets the right wort and the filler gets the right CO2. Verify the pasteurization critical control point continuously. Let the filler chase target level only inside the approved window; hold anything beyond the envelope for a human.
ThoughtThe standing practice over-fills to avoid low fills and over-g…
The standing practice over-fills to avoid low fills and over-gasses to avoid flat product. With continuous fill-level estimation and inline CO2 the filler and the carbonator can sit at target. The saving is giveaway, not safety margin: the pasteurization CCP is never a candidate for optimization.
Actiontwin.simulate(candidates=24) → plan #7: gravity on recipe, fin…
twin.simulate(candidates=24) → plan #7: gravity on recipe, finish day 5, CO2 at package target, PU margin unchanged, lowest predicted CO2 and energy per hectoliter.
ObservationPlan #7 wants the pasteurizer CIP in a window that overlaps th…
Plan #7 wants the pasteurizer CIP in a window that overlaps the next brand's start. The policy engine routes that single move to the shift quality manager and permits the other seven writes.
ActionExecute plan #7 at the bounded stage: brewhouse blend, tank ra…
Execute plan #7 at the bounded stage: brewhouse blend, tank ramp, CO2 dosing and fill-valve writes proceed; PU is verified continuously; the CIP move waits.
ObservationApproval granted at 06:33:44 with the PU profile untouched and…
Approval granted at 06:33:44 with the PU profile untouched and a tighter CIP release check. Three low-fill rejects were attributed to filler valve 14 and corrected by Fill-and-Seal inside the approved window.
OutcomeScenario complete. The batch is released with gravity and atte…
Scenario complete. The batch is released with gravity and attenuation curves, yeast lot, CO2 and clarity, fill and seal outcomes, PU readings, CIP release and the human decision in the genealogy. No measured plant result is claimed; this is the run the platform is designed to execute.
Guardrails
An agent that can move a setpoint needs a leash
Brewira 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 stage the plant has set.
- Critical control points are read, never written. Pasteurization units, CIP release checks and batch release decisions stay with the HACCP plan and the people who own it.
- Policy engine before every write. Autonomy stage, interlock state, product, 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, FSSC 22000 and BRCGS record-keeping.
- Hard fallback. If the edge node, the network or a model stops, the plant keeps running on its existing PLC and SCADA control and interlocks.
- Tenant and IP isolation. Recipes, supplier data and tolerance models never cross a customer boundary. On-prem deployment available.
Assurance posture
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Roadmap, first 6 months |
| SOC 2 Type II | Cloud control plane | QUEUED Roadmap, 6 to 12 months |
| HACCP · FSMA · FSSC 22000 · BRCGS | Grounding and record-keeping | RUNNING Design basis for retrieval and the audit log |
| Per-tenant isolation | Data, memory, models | RUNNING Design rule |
| On-prem deployment | Recipe-sensitive producers | RUNNING Design option |
Brewira supports your food-safety records. It is not a certification and it does not replace your HACCP plan.
Autonomy
Four stages, set per loop
A plant does not go from manual to bounded control in one step. Brewira makes the stage explicit per loop, auditable and reversible at any time, and some decisions never leave the person.
| Stage | What the agent does | What the person does | When |
|---|---|---|---|
| Shadow | Predicts gravity, attenuation, carbonation, fill and seal faults, contamination and takt; writes nothing | Runs the plant as today; compares predictions to lab, QA and PLC outcomes | First phase with every design partner |
| Assist | Recommends bounded brew, fermentation, carbonation, fill and seal, pasteurization and CIP moves with the evidence | A brewmaster, process engineer or quality manager approves or rejects each one | After accuracy is proven against the baseline |
| Bounded | Writes low-risk filling, carbonation and inspection setpoints inside documented recipe, quality, food-safety, equipment and rollback limits | Approves anything above the limits; reviews the shift record | After the food-safety and ROI gates agreed up front |
| Exceptions | Escalates anything outside its envelope, CCP-adjacent moves and release decisions | Always decides these; the agent never does | Permanent |
Assurance
Certification status
Stated plainly. Items on the roadmap are roadmap items.
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Roadmap, first 6 months |
| SOC 2 Type II | Cloud control plane | QUEUED Roadmap, 6 to 12 months |
| Food-safety and sustainability assurance packages | Design partners | QUEUED Roadmap, 6 to 12 months |
| HACCP, FSMA, FSSC 22000, BRCGS | Grounding and records | RUNNING Design basis; not a certification of Brewira |
| IP-safe deployment | Recipes, supplier data | RUNNING Design rule; on-prem option |
OT safety
Failing safe is a design requirement
- Supervisory, not primary. Brewira sits above existing PLC and SCADA control; it never replaces an interlock or a safety system.
- Critical control points are read-only. Pasteurization units and CIP release checks are verified and logged, never written.
- Release is human. The conformance agent assembles the genealogy and checks it against spec; a person releases the batch.
- Loss of Brewira is loss of advice. The plant degrades to the way it runs today, not to a stop.
What leaves the plant, and when
| Data | Where it stays |
|---|---|
| Recipes, specs, tolerance models | Tenant-scoped; on-prem option |
| Supplier, yeast and raw-material data | Tenant-scoped |
| Audit log and genealogy | The plant's own storage, exportable |
| Rare-defect and drift patterns | Federated, IP-isolated transfer across similar lines (planned, opt-in) |
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: tunnel pasteurizer belt speed
-
01yield_takt.request(belt +5%) SUCCEEDED0.2 s
Yield-and-Takt wants more belt speed through the tunnel pasteurizer so the filler is not held back and the shift meets takt.
-
02pasteurize_cip.request(belt hold) SUCCEEDED0.2 s
Pasteurize-and-CIP requires the belt speed that keeps every container inside the validated PU profile. That is the HACCP critical control point.
-
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.
-
04yield_takt.handoff(resequenced) SUCCEEDED90 s
Yield-and-Takt recovers the schedule by pulling the next changeover earlier and shifting the CIP window instead. Takt is met without touching the CCP.
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 optimization variable. An under-pasteurized or contaminated batch 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 human rather than resolving by timeout.
Enterprise
Standardize autonomy across the group
One policy model, one audit trail and one set of yield, loss, giveaway, water and energy benchmarks across every plant in the group, with each site's recipes and tolerance models kept private to that site.
- 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, brewmasters and quality managers ask in the first meeting.
Only at the autonomy stage your plant has set, and only to an explicit allow-list of low-risk loops inside documented limits. Every design partner starts in shadow mode, where Brewira predicts and writes nothing. Assist mode follows, where a brewmaster or process engineer approves each recommendation. Bounded autonomy on filling, carbonation and inspection loops comes after the food-safety and ROI gates agreed up front.
Critical control points are not optimization variables. The pasteurization PU profile, the CIP release checks and the batch release decision stay with your HACCP plan and your people. Brewira verifies readings, writes them to an immutable audit log and attaches them to the batch genealogy. It is grounded in HACCP, FSMA, FSSC 22000 and BRCGS procedures; it is not a certification and does not replace your plan.
Brewira sits above your existing automation as a supervisory layer. If it stops, the plant keeps running on its current PLC and SCADA control and the interlocks it already has. A Brewira outage degrades the plant to the way it runs today, not to a stop.
The first phase is shadow mode on one line: Brewira reads your analyzers, PLC history, lab results and MES while you run the plant as usual, and we measure its predictions against your lab, QA and PLC outcomes. Recommendations start when accuracy is proven against that baseline, and improve as plant-specific history and brewmaster corrections accumulate.
Recipes, product specs, tolerance models and supplier data are tenant-scoped and never used to train another customer's models. Retrieval is multi-tenant isolated and permission-aware. Cross-plant learning, where a customer opts in, is federated and IP-isolated. On-prem deployment is available for producers protecting sensitive recipes.
You are, the same as with any control strategy. That is why every write is policy-checked, bounded, logged and reversible, every output carries a citation to the recipe or procedure it relied on, and anything above your threshold waits for a named approver. The audit log records the request, the reasoning, the limits applied and the human decision.
As a design partner, on one line, with one hard metric: fill giveaway and low-fill rejects, leaker and seal faults, attenuation variance and tank time, CO2 use and clarity rejects, or water and energy on pasteurization and CIP. We instrument the line in shadow mode, measure the baseline, move to assist mode when accuracy is proven, and expand only when the number holds.
Full multi-module autonomy across the whole plant, long-tail integrations beyond the design partners' stacks, and self-serve onboarding. The first release is one wedge workflow, its connectors, the agent loop with human checkpoints, the review console and the assurance-grade food-safety audit log.
Get started
Get the security pack
The design posture, the data flows and the roadmap dates, written for a quality manager and an IT/OT lead.