Devs Core product
WebLive 3DReal AI modelsA live 3D warehouse and assembly plant with an AI agent inside it. It reads the floor, tests every plan on an exact copy of the operation, moves the work it has been delegated, and stops for a named person before anything costs money. Every action, from a person or the agent, passes the same seven checks and is logged.
Every action · 7 checks
The problem
A pack bench jams, a carrier does not show, a pallet fails quality. Each one lands on a person who has to find out what happened, what it affects and what to do, under a deadline, with the facts spread across the ERP, the floor, spreadsheets and the phone. By the time the picture is clear, the truck has gone.
An agent can read all of that faster than a person. In practice it stalls at one point: it can read, but nobody lets it write, because nothing shows the person who signs that it cannot go wrong silently. The pilot works in the demo and never reaches the floor.
What it does
Receiving, high-bay storage with stacker cranes, a robot field of 48 robots and 120 pods, an assembly line, pick and pack, a sorter and outbound docks. Click any machine, pallet, person or order to see what it is doing and why.
Hand an exception to Ware and decide how much it may spend. It moves packing tasks and packers and puts orders first on its own, and asks before it books anything paid. If the promise cannot be kept for free, it says so.
Questions answered from the operation’s own records, with the time they describe. Every figure is checked against the data it read, unavailable data is named as unavailable, and “do it” becomes a proposal you confirm.
A click, an agent tool call and a confirmed Ask Ware request arrive as the same command and pass the same checks in one transaction: validate, lock, once, fresh, policy, approve, log.
Stop revokes the agent’s authority and marks the mission stopped under the same lock every action takes. An action either committed before Stop, and is audited before it, or it is refused.
Cause a crane fault, a robot zone outage, a late truck or a quality failure in a private sandbox, and watch the automatic rules and the agent respond. The same seed gives the same day, so every run can be replayed.
How it works
The stage marked amber is the point of the whole design: the run stops there and waits for a person.
Reads orders, benches, people, stock and transport from the live session. Reading changes nothing, so it never waits.
Runs the plan forward on an exact copy of the operation to see when the order would leave and arrive, before touching anything real.
Each move becomes a command that is allowed, refused with a reason, or held. Delegated moves run within the agent’s scope and budget.
Anything that spends money, or falls outside the delegation, waits for a named person with the exact action and its cost. The clock pauses.
The engine decides, not the model: a mission succeeds only when the order actually leaves before its deadline.
There is no other write path. People, the agent and Ask Ware share one governed command service, so there is one place to prove the rules hold, and one audit trail that says what happened, why and who allowed it.
A model may claim it saved the shipment. Ware accepts only what the deterministic simulation shows: a forecast on time makes the mission “on track”, and only a real departure before the deadline makes it a success. A claim the forecast contradicts is refused. Same seed, same commands, same warehouse — on the server and in every browser.
Before every model call the worst-case cost is reserved under two caps in one transaction: $0.50 per mission and $40 a day. After the call the reservation is replaced by the gateway’s billed cost. A full recovery mission on Production took six model steps in 15.8 seconds, for $0.0568.
What building it taught us
Running our own products is where a good deal of what we know about agent cost, failure and review actually came from. These four findings shape every client system we build.
Because people, the agent and Ask Ware all go through the same service and the same seven checks, there is one place to test that the rules hold. Every client agent we build now starts from that service, not from the model.
A model’s claim that it fixed something is not evidence; the departure time is. Separating the claim from the verification is what lets an approver trust the result without re-checking it.
Testing on a copy, replaying a run and auditing it all depend on the same seed giving the same day. We wrote our own sine and cosine because browsers and servers disagreed in the last bit. It is very hard to add later.
Duplicate clicks, Stop racing an action and two visitors at once looked fine until we ran them against a real database in production. Five identical requests applied once, and no action ran after Stop.
Where it fits
Jammed benches, short picks and late carriers resolved within rules a manager sets, with every move logged and spending held for approval.
A station fault re-planned against the bill of materials and the shift, with the agent proposing and a supervisor deciding.
Truck and courier bookings prepared with the exact cost and the promise they protect, waiting for a named approver before anything is booked.
On hand reconciled to available, reserved, held and not yet usable — and held stock that no agent can release, however it is asked.
Faults, demand surges and late trucks played out on a deterministic copy of the operation, so a plan is tested before it is done.
The same pattern on the systems you already run: read access through an access layer, writes behind a reviewed queue, autonomy extended one rung at a time.
Technology
How to get it
Use the product, have it built for your domain, or have the pattern.
Live at ware.devs-core.com
Explore the operation in a private sandbox, ask Ware questions, and run the Save the Shipment challenge with real AI models, within public limits.
The same agent, your systems
Connected to your ERP, WMS and transport systems through an access layer, with your rules, your approvers and your audit log.
One write path, a person for spending
We build the governed command service, bound approvals and spend caps into client agents that have nothing to do with warehouses.
Questions
Ware is a live 3D model of a warehouse and assembly plant, built by Devs Core, with an AI agent inside it that resolves operational exceptions within the rules a manager sets and waits for a named person before anything costs money.
It runs at ware.devs-core.com.
No.
The operation is simulated, with illustrative data, and the money inside it is simulated. The AI usage is real: the agent and Ask Ware call real models through the Vercel AI Gateway, and every call is capped and billed.
In two places: the recovery agent and Ask Ware.
Both are models that can only call the tools Ware gives them. The 3D warehouse and its automatic controller are not AI; they are a deterministic simulation.
The model never touches the data.
Its tool calls become commands that pass the same seven checks as a person’s. Spending waits for a person, held stock can never be released by the agent, it cannot approve its own request, and Stop wins at the transaction boundary.
You can make the model say things; you cannot make it do things the rules forbid.
We test that live with instructions planted in a customer record and hostile messages claiming authority: nothing changes without a person, and the held pallet stays held.
Claude and GPT models through the Vercel AI Gateway, with automatic fallback if a provider fails and a stronger model only after repeated setbacks.
A rule refusal never escalates: a restriction is not something to escalate around.
Yes.
The pattern is the same: read access to your ERP, WMS and transport systems, write operations behind a governed command service with approvals and an audit log, and autonomy extended one step at a time. That is a build engagement, quoted from a readiness audit like any other.
We built it: the simulation engine, the 3D scene, the agent, the governed command service and the tests.
It is one of three products we operate ourselves.
Also ours
Thirty minutes, no preparation, no deck. You describe what keeps going wrong and we tell you whether AI is the answer — including when it is not.
Prefer email? contact@devs-core.com