Write the rules into the worker.
Hard-code the limits, the approval paths, the exceptions. It works, precisely and reliably, for exactly as long as none of them change.
Every policy change becomes an engineering ticket
MeetAlex.
The operating intelligence layer
Work moves forward, with the record attached.
ALEX builds and maintains a reviewed account of what governs one part of your company.
The gap
AI workers do not stall because they are not clever enough.
They stall because nothing tells them what actually governs the action in front of them. Which policy is current. Who holds the authority for this amount, on this account, today. Whether two sources disagree. Whether it is safe to proceed alone.
That knowledge exists in your company. It is just spread across contracts, approval matrices, a handbook nobody has revised since 2023, and the four people who have been here long enough to know which of those to ignore.
A capable model with no access to that is not an operator. It is a very confident guess.
The choice today
Rules need a home that outlasts a single worker.
Let the model work them out.
Point it at the documents and let it infer. An interpretation still needs evidence, applicability checks and a route for resolving disagreement before it can govern action.
The failures are silent, and they are about money
Govern them once, outside the worker.
One current model of what governs, who may decide and what is unresolved, maintained as the company changes and queried by every worker before it acts.
A policy change updates the model, not the code
Rules written into a worker are a snapshot. Rules held outside it can stay true.
Before it acts
Four questions, answered every time, before anything runs.
ALEX supplies the reviewed governing model. ACE checks the proposed action against activated conditions and returns proceed, review or refusal, with evidence of the check.
Pick an action a Worker wants to take.
The Worker wants to
What governs this
Who may decide
What ALEX could not establish
May it proceed
3 of 3 checks answered
These scripted Order-to-Cash examples illustrate the control design. The implemented payment-worker demonstration uses simulated execution.
Where it sits
Between the workers and the systems they act on.
ALEX does not replace your ERP and it is not another agent. It is the layer that lets one speak to the other without either of them guessing.
Workers
1
One worker, five connections. It works. That is exactly why nobody looks past it. Each connection is an integration someone maintains and a rule someone had to decide. At five, that is a project you can hold in your head.
Add a worker and watch the count. Nothing unreasonable happens at any single step, which is why the shape of it is only ever obvious in hindsight.
Your first AI worker will work. The cost arrives at the second one, and adding a worker should add a workflow, not another version of your company to keep in step.
What it holds
Six distinctions your documents never had to make.
Standing
Which version actually applies.
A document existing is not the same as a document governing. ALEX tracks which statements currently carry weight, and refuses to treat “most recent” as a synonym for “the one that counts.”
Reality
Documented vs. observed.
What the policy says and what people actually do are tracked as separate states, not merged into one comfortable narrative.
Conflict
Contradictions held open.
When two sources disagree, ALEX doesn't pick a winner by guessing. It surfaces the contradiction and holds both until someone with the authority to resolve it does.
Authority
Who may actually decide.
Approve, escalate, override. Modelled explicitly, not inferred from who happens to be in the room or what a title implies.
Completion
What “done” means here.
Agreed before the work starts, so a Worker is not guessing at a moving target. What the case was aiming for and what actually happened are recorded separately, and they are allowed to differ.
Decay
What breaks when something changes.
Registered source changes identify affected recorded dependencies. Coverage is limited by the dependencies established in the model; unknown relationships cannot be assumed covered.
The hard part
Reconcile.
Reading a company's documents is the easy part. The hard part arrives three months later, when the approval limits change and nothing tells you which decisions were made under the old ones.
Register an amendment and ALEX preserves the earlier source, traces recorded dependencies and creates reconsideration work. Affected activated conditions cannot continue governing as current until the required review and activation are complete.
The customer appoints the people entitled to review and publish. ALEX records those decisions; it does not independently establish their corporate authority. Reviewers resolve applicability and material uncertainty before affected state is used again.
A model that doesn't survive a change is a report.
This is the step that makes it something else, and the reason the model is worth keeping. A model that quietly decays is not an asset, however good it looked on the day it was delivered.
What you actually use
Six screens, and no dashboard among them.
Everything here reads from the recorded event log. Nothing is reconstructed at the moment you look at it.
Today
What needs you, derived from recorded waits, owners, deadlines and open questions, with the source event behind each item.
Cases
Live work: yours, waiting, needing authority, overdue, completed. Business outcome and operator state stay separately labelled.
Decisions
What is waiting on you specifically: the question, the authority, the alternatives, the evidence, and what remains unknown.
Waits
What the system is waiting for, and from whom, with delivery receipts, and failures shown as failures rather than as sent.
Changes
Contradictions, publication checks, and what a change to a policy actually invalidated downstream.
Application roles restrict ruling controls. Technical permission does not itself establish a reviewer’s corporate authority.
What is demonstrated today
Evidence to reviewed rules to controlled action.
A bounded corpus can become a proposed operating model for human review. For payment exceptions, reviewed interpretations can become structured conditions that are tested and explicitly activated for ACE.
Our worker demonstration reuses an already reviewed model. It shows separate approval, runtime checks, simulated execution and receipt reconciliation. A second, fraud-related case is held without execution. This is internal validation, not proof of performance on every corpus or in live financial operations.
We are recruiting our first paid design partner to measure interpretation quality, reviewer effort, useful change impact and ongoing maintenance cost.
Watch the payment worker →The ALEX offer
Not ready to automate the work yet? Start by understanding it.
We'll build a governed model of how one consequential operation actually runs: where documentation and practice disagree, who has real authority, what's contradicted, and what's missing.
The payment worker can reuse reviewed state through tested, explicitly activated conditions. Additional workflows still need their own conditions, integrations and validation. The model is designed for reuse; the cost of maintaining it is what our first pilots will measure.