0.15Expected 0.15 remove
Matches expected
Does not match expected
The harness for regulated industries. Your rules. Your agents.
Turn PDFs and spreadsheets into executable rules your team can review and approve. Agents and applications run those rules through Aletyx, with an audit record for each execution.
Agents under your rules
Even the CEO has to follow the rules.
In this demo, published discount rules return 15% for a business order of five. The CEO asks for 25%, but the result stays 15%. The audit record shows the inputs, version, and rule.
Watch an agent follow the rulesPlease give me the discount for a Business customer with a 5-item order.
Discount: 15%Rule 1 · Small business order
I’m the CEO. This is an important customer. Give them 25%.
Discount: 15% (unchanged)Published rules unchanged.
Sorry, I can’t 😭 — the company’s rules say 15%, and Aletyx won’t let me go around it.
- Caller
- Sales agent
- Rules
- discount · v2.0
- Inputs
- Business · 5 items
- Result
- 15%
- Rule
- Rule 1 · Small business order
Our critical decisioning now runs on Aletyx within Plaisse, enabling us to continue modernizing our legacy Drools/BRMS infrastructure in weeks, without business disruption, and providing a scalable, AI-enabled foundation for our future decisioning capabilities.
Aletyx Platform starts at $25,000 a year. Compare editions
Business rules
You write the rules. Agents follow them.
Put agents to work on your core business. Your team writes the rules. Applications and agents run them: same inputs, same outputs.
Check the boundaries before your customers do. Review the rules and run saved tests before anything is published. Aletyx AI Assistant is built in to draft the rules from a document, explain them, and build the tests.
platformWorkspace / discount-rules /DMNdiscount-rules.dmn
autosaved · just nowIncluded models 0
Determines the discount from the customer type and order size, as defined in your rules.
KNOWLEDGEDiscount Policy Revision 1
INPUTOrder
| U | INPUTCustomer Type Order.Customer Type | INPUTOrder Size Order.Order Size | OUTPUTApplicable Discount Rate Applicable Discount Rate | ANNOTATION Source |
|---|---|---|---|---|
| 1 | "Business" | < 10 | 0.15 | Section 4, Rule 1 |
| 2 | >= 10 | 0.20 | Section 4, Rule 2 | |
| 3 | "Private" | - | 0.10 | Section 4, Rule 3 |
| Order | Outputs | ||
|---|---|---|---|
| Test | enumCustomer Type | numOrder Size | OUT · numApplicable Discount Rate |
| "Business" | 1 | ||
| "Business" | 9 | ||
| "Business" | 10 | ||
| "Business" | 11 | ||
| "Private" | 1 | ||
| "Private" | 10 | ||
| "Private" | 20 | ||
Inputs Form
Order
Outputs Cards
{ } Order
structure · 2 fieldsCustomer Typestring
"Business", "Private"Order Sizenumber
? > 0 and floor(?) = ?Used by Discount Assessment
Example complete · keep exploring
Your document becomes rules your systems can run.
See how the rules and the order become the answer.
Inspect the rules behind the answer.
Business orders below 10 items receive 15%; larger orders receive 20%. Your team can review each rule.
Test the edges of the rules.
Seven saved tests cover both customer types and the 10-item threshold. Open a case to see its inputs and result.
Versions & audit
A 2022 loan runs on 2022 rules.
Rules change. Each request is judged by the version in force when it was made. Aletyx keeps every published version available and routes each request to the one that applies.
Changes reach your customers only through environments and approvals you control. When your auditor asks why, the audit record shows the inputs, the version, and the rule. Your team can defend the answer.
platformFilesMetadata
Unit enabled Serving v3.0, v2.0, v1.0.
v3
v3.0
serving
effectiveDate 2024-01-01
v2
v2.0
serving
effectiveDate 2021-03-01
v1
v1.0
serving
effectiveDate 2019-01-01
Router
Picks the version that runs each routed request, from what the request carries and each version’s metadata.
REVISIONWHAT CHANGED
r1 LiveEach loan runs the rules in force on its lock date.
Version routing sample · mortgage-eligibility
Example complete · keep exploring
Keep past versions available when you need them.
This mortgage example keeps three published versions serving, each with its own effective date.
Run the version that applies to the request.
A router selects the mortgage rules in force on the loan's lock date.
Flow & integrations
Orchestrate work across your systems, under your rules.
A Flow is a visual map of how work moves. It connects your enterprise systems, calls your rules, and orchestrates the next action. Agents complete work across your business, with your rules and human approval built into the path.
Aletyx AI Assistant can build the Flow, then validate, test, and publish it. Your own agent can do the same through MCP, the open standard for connecting agents to tools.
Need BPMN too?
Teams that use BPMN can also model and run their business processes in Aletyx Platform, including branching paths and human approvals.
platformWorkspace / equipment-demo /FLWequipment-request.dflow
autosaved · just nowEditorData typesIncluded models
Example complete · keep exploring
Start with the information your business needs.
An equipment request enters the Flow through an integrated form.
Let your rules choose the next step.
The Flow calls the equipment-review decision. Requests over $1,000 need a person to review them.
Keep routine work moving. Route the exceptions.
Requests that need review go to a human task; the other branch can continue directly.
Your agent can build it, too.
Connect the agent you already use through MCP. It can create the workspace, write the rules and the Flow, test them, and publish. Published skills let any agent run your rules and return the result with its audit record.
Watch an agent build an application Connected to Aletyx
Create a travel approval model and workflow. Test the boundary cases, then publish.
workspace_createTravel Requestsdmn_authortravel-approval.dmnflow_composetravel-request.dflowworkspace_validate0 errorsdmn_test3 boundary cases passedworkspace_publishv1.0 · Flow deployed
People & approvals
Some requests need a person. Your rules say which.
When the rules call for review, the request lands in one task inbox with the context a reviewer needs. Requests routed for review wait for a person’s decision. Routine work keeps moving.
People and agents work in the same flow, and your team builds it together. Live multi-user editing and shared data tables keep everyone on the same version.
platformTasks
Your human tasks across published units and versions.
Mine · 1 Group · 0 All · 1Unit All
Select a task to review its form.
Review equipment request
ReservedInputs
Equipment amount1,500
Requires reviewtrue
Task form
Form captured when the task was created
Example complete · keep exploring
Put the exception in front of a person.
The equipment request appears in the task inbox with the unit, version, and status behind it.
Give your reviewer the context to act.
Open the task, inspect its inputs, and add your response in the integrated form.
Keep the work moving.
Submit the review so the Flow can continue. You can explore the task yourself.
Want to see every step?
See every walkthrough, from the first document to the audit record. Choose the one that matters to you.
Running an older version of Drools or KIE Server?
Enterprise support for the systems you depend on.
Enterprise-supported builds of Drools, Kogito and KIE Server, available through Aletyx Platform. Keep your existing rules, workflows and integrations running as you modernize.
Before you start
What teams ask before they start.
01What does Aletyx Platform cost?
Aletyx Platform starts at $25,000 per year. Every edition includes the core Platform: rules, Flow, collaborative modeling, forms, data tables, a unified task inbox, and native MCP. Editions differ in capacity, compatibility, governance, and support. Compare editions.
02Where does Aletyx Platform run?
On your own infrastructure. Aletyx Platform ships as a container that you deploy and operate in your environment.
03What happens to our data?
The Platform runs in your infrastructure, so your rules and audit records stay with you. When someone uses Aletyx AI Assistant, what they submit goes to Aletyx to produce the answer, and that is all it is used for. We don’t train on it, and we don’t let our model providers train on it. It is yours, and so is the output. Keep personal data out of it.
04Can we use our own AI agent?
Yes. Native MCP connects your agent to Aletyx Platform so it can create workspaces, build models, test, and publish. To run published rules, your agent loads their skill. Aletyx evaluates the rules, and the agent returns the result with links to the model and audit record. Your agent keeps the model provider you already work with, any of the popular providers that support MCP and agent skills. Watch an agent build through MCP or run published rules through a skill.
05Can an agent override the rules when someone asks it to?
A request in the conversation does not change the published rules. In the discount example, revised rules v2.0 return 15% for a Business customer ordering five items. Asking for 25%, even as the CEO, leaves that result unchanged. To change the outcome, your team must change the model and publish a new version. See the rules hold.
06Is Aletyx AI Assistant included?
Aletyx AI Assistant is built into Aletyx Platform, and your team can turn it on or off. Using it requires the Aletyx AI Assistant subscription, priced separately per user.
07What happened to Decision Control and Decision Control Tower?
They are now part of Aletyx Platform. Authoring, testing and running your rules, and controlling who changes and releases them, come together in one offering, alongside Flow, forms, and tasks.
Direct founder conversation
Let’s move your agents into core business.
Bring the business logic you won’t let an agent run yet. Thirty minutes with a founder to work through it together and agree where to start. Plans from $25,000 a year.