The loop is built with you.

xAutonomics is a service for building tailor-made optimization runtimes for resource, energy, and process systems. We work from your existing equipment and a small local computer, shaping a system around the way your site actually operates.

Mica helps turn your goals, devices, and limits into a clear specification. We review and refine that specification with you, then build and validate the runtime. Once deployed, the loop can propose, act, measure, learn, and repeat within the boundaries we agree together.

We bring this pattern to everyday systems: irrigation, HVAC, and industrial processes. AI accelerates the work; two humans stay in the loop where context, judgment, and accountability matter.

Designed together in the Studio.
Built and overseen by us.

Autonomica Studio is the design-time environment — a web and desktop application where you describe the system you want to improve, guided by our AI agent Mica. Mica helps gather devices, objectives, and limits into a formal, inspectable specification. We review and refine it with you before any build begins.

We then build, validate, and deploy a containerized Runtime to your local compute — a mini PC or industrial gateway. It includes the optimization engine, device interfaces, monitoring, and safety layers, with us overseeing the deployment and its early operation.

Start with a conversation.
Refine it with us.

Mica is the AI agent inside the Studio. Instead of forcing you to fill out engineering forms, Mica conducts a structured interview — the questions a good controls engineer would ask — then we review what it discovers with you:

From the interview, the Studio produces a formal optimization problem definition — variables, objectives, constraints, device mappings — which you inspect and edit visually. We review and refine it with you, and use the approved specification to build the Runtime.

No API?
Not a problem.

The Runtime integrates devices without requiring APIs or vendor cooperation — three pathways cover nearly everything that can be sensed or switched:

• App automation — an emulated Android environment with ADB drives devices that are controllable only through a phone app.
• Web automation — a headless browser with Playwright drives devices that expose web dashboards or cloud UIs.
• Direct hardware — an Arduino Opta Pro connects RS-485/Modbus devices. AI models draft the MicroPython integration from the device's datasheet and register map; we review it, then it passes the same validation pipeline as everything else before it touches the microcontroller.

This is what makes "readily available components" real: the phone app or web dashboard the device already ships with becomes its control interface.

AI assists.
We verify.

We use a mixture of open-weight language models for reasoning, code generation, vision, UI understanding, and document extraction. AI accelerates the build, while we review the resulting specification and implementation before it reaches your equipment.

The differentiating stage is Lean-based auto-formalization: the optimization problem definition and the control code built around the Bayesian optimization core are formally verified. The constraints and safety bounds you set in the Studio are translated into formal statements, and the logic is checked mathematically alongside human review.

Code review, static analysis, and simulation replay against recorded device behavior complete the validation process. We use the same quality bar for every Runtime, then oversee its deployment and early operation.

Observe first.
Act later.

A Runtime we build does not immediately start changing things. We take it through a staged, trust-building lifecycle with you:

1. Observation period — passive monitoring only. The Runtime collects data on the system's normal behavior across its operating conditions. No control actions.
2. Model convergence — observation continues until the internal model's predictions reliably match observed behavior. Only then does the deployment advance.
3. Experiment proposal — the Bayesian optimization core generates candidate "experiments": parameter changes that explore promising optimization paths, all within your defined constraints.
4. Review and approval — the specification and proposed experiments are presented to you and reviewed with us before anything touches the real system.
5. Supervised operation — with approval, the closed loop runs: act, measure, learn, propose next — while we oversee the deployment and hard limits, watchdogs, and failsafes stay enforced at the execution layer.

The optimizer explores.
The envelope holds.

Exploration and enforcement are separate layers. The Bayesian optimization core is honest about what it knows: a model with explicit uncertainty, which narrows around every measured sample. Where uncertainty hides potential value, it proposes the next experiment.

But no proposal — however promising — can leave the envelope you defined. Hard limits, watchdog timers, and failsafe behaviors are enforced at the execution layer, independent of the optimizer, and stay active even when devices become unreachable or behave unexpectedly. The optimizer proposes; the enforcement layer disposes.

The stack, layer by layer.

Where does the value hide?

Wherever a system runs on settings someone chose once and never revisited. Thermostat schedules set years ago. Irrigation timers set by the installer. Compressor pressures set "to be safe." Charge windows that ignore today's tariff.

Every one of those is a candidate for a Runtime we can build around your site. Below are examples of the work: a Studio conversation with Mica, a problem definition we review together, and a Runtime we build, deploy, and oversee for the system in front of us.

Battery, solar, tariffs, EV, heat pump — finally on the same team.

Your home already makes half a dozen energy decisions per hour: when to charge the battery, when to sell back, when to run the heat pump, when the EV should draw. Each device optimizes selfishly, or not at all. Meanwhile the economics have inverted: with collapsed feed-in tariffs, self-consumed solar is now worth several times what exported solar earns — yet most systems still run the inverter's factory mode.

The Runtime fuses them: tariff data, the inverter, the heat pump's app, the charger's Modbus meter — one objective, minimum cost of comfort. It learns the house itself — thermal inertia, real morning demand, how your panels actually perform under your sky — and schedules energy flows against tomorrow's prices. Not a rule engine; a model of your house.

The honest numbers: field-credible studies put whole-home optimization around 16% cost / 22% energy savings — and co-optimization is exactly where that comes from: optimizing HVAC alone yielded 8% in the same study that reached 16% when battery, PV, and shading were folded into one loop. Battery-plus-tariff arbitrage alone is worth on the order of £700–950 a year on a 10 kWh pack under a dynamic tariff.

Water when the plants need it — not when the timer says so.

A clock timer keeps watering through a rainstorm, waters a cool cloudy week like a July heatwave, and gives the shaded clay corner the same minutes as the sun-baked sandy knoll. The EPA estimates as much as half of residential outdoor water is wasted this way — and outdoor use is more than 30% of household water, up to 60% in arid regions.

The real control problem is a soil-water balance run forward in time: the root zone is a leaky bucket, filled by irrigation and rain, drained by evapotranspiration. The Runtime waters on evidence — soil-moisture probes, the ET and rain forecast, per-zone soil and planting — and treats new trees, established shrubs, and turf as genuinely different buckets. Because it experiments, slightly earlier here, slightly less there, it discovers what your soil and microclimate actually respond to. "Safe" schedules routinely turn out substantially over-watered.

Measured, not marketed: weather-based control lands around 16% average savings in landscape studies (21–50% across sites in the Irvine ET-controller study), WaterSense-certified control is at least 20% better than a clock, and soil-moisture-guided turf programs run 20–40% — the difference between surviving a mandated drought cutback and losing the greens. Flow and pressure telemetry doubles as the safety layer: a stuck valve or burst lateral triggers shutoff instead of a flooded zone.

The algorithms already beat the experts.

A greenhouse is the textbook coupled system: opening a vent dumps heat and humidity and the CO₂ you just injected. Every actuator — vents, screens, heating, lighting, fertigation — moves several variables at once, and the variables fight each other. That coupling is precisely what defeats rule-based climate control, and precisely where co-optimization pays.

The proof point is public: in Wageningen's Autonomous Greenhouse Challenge, AI teams have repeatedly out-yielded and out-profited professional growers while using less energy — one winning entry posted +27.8% net profit, and in recent editions every algorithm team beat the professional reference. Energy is a grower's #1–2 operating cost, with 20–40% documented savings on the table — thermal screens alone are worth 30–75% of heating.

Deployment is an overlay, not a rip-out: the Runtime reads state from and writes setpoints to the climate computer you already run, respecting its interlocks. You set the strategy — crop, targets, limits; the loop runs the tactics, day and night.

One 15-minute spike sets your bill.

For commercial and industrial customers, demand charges are 30–70% of the bill — set not by how much energy you use, but by your single worst 15-minute interval. On many tariffs that spike ratchets: one bad afternoon when the compressor, the CNC, and the AC all kick on together can raise your bill for the next eleven months.

That asymmetry is exactly where anticipatory control beats reactive rules. The Runtime watches the interval meter, forecasts the coincident peak, and schedules flexible loads apart: pre-cool the cold room ahead of the window, stage the compressors, discharge the battery into the peak — while food-safe temperatures and process constraints hold as hard limits, not suggestions.

Documented outcomes: peak-shaving programs cut C&I bills 20–40% with 3–6-year paybacks; supermarket-style refrigeration control shifts 5–12% of load out of peak windows for only ~2% more energy; EV depots save tens of thousands per year on demand management alone. The hardware — interval meter, inverters, rack controllers — is usually already installed. The missing piece is the loop.

Consulting & development for your project.

We take on agent, automation, and software integration projects on a consulting basis or as turnkey contracts with an agreed scope and delivery. Bring us a workflow to improve, equipment to connect, or a system to build.

We work with you to define requirements, assess the existing system, and agree on engineering deliverables and operational criteria. AI models assist development; we review the work and take responsibility for its delivery.

Have a project in mind? Tell us what you want to achieve, what you already have, and where you need help. We reply personally to discuss fit and scope.