Your AI should belong to your business.
Enterprise AI can touch some of the most valuable information inside a company — customer data, operational knowledge, internal processes and proprietary decision-making.
Margins designs AI and software systems around the principle that customers should retain control over their data, infrastructure and business intelligence.
Your infrastructure. Your data. Your intelligence.
Your business data is not a commodity.
AI becomes substantially more valuable when it understands the company using it.
That information is not simply input for an AI system. It is part of the company’s competitive advantage.
- Its customers.
- Products.
- Processes.
- History.
- Documents.
- Decisions.
- Operational patterns.
- The knowledge accumulated by its people.
Don’t move your business into someone else’s AI environment. Bring AI into yours.
Security decisions start before the first line of code.
Rather than treating security as something added before launch, we consider data boundaries, access, infrastructure and external dependencies when designing the system.
Where does information live?
Understand what information the AI needs, where it currently resides and where it is permitted to move.
What receives that information?
Select models and deployment approaches according to the sensitivity, performance and operational requirements of the use case.
Who and what can interact with the system?
Design authentication, authorization and system boundaries around the actual users and workflows.
Where does the system run?
Deploy according to the customer’s technology environment and requirements rather than forcing every implementation into the same architecture.
Security is an architectural decision before it becomes an operational control.
One architecture doesn’t fit every enterprise.
Different businesses have different requirements around infrastructure, data residency, existing technology and internal control.
Customer cloud
Deploy into the customer’s existing cloud environment and infrastructure.
Private cloud
Use isolated infrastructure where additional separation and control are required.
On-premises
Run components within customer-controlled infrastructure where operational requirements demand it.
Hybrid
Keep sensitive systems or data inside controlled environments while connecting approved external services where appropriate.
Architecture should follow the requirements of the business — not the convenience of the technology provider.
Every AI architecture creates a data path.
Instead of treating AI as a black box, the architecture should make the path clear — from where data originates to what returns to the business.
If a system uses your most valuable information, you should understand exactly where that information goes.
- 01Where data originates
- 02What information enters the AI workflow
- 03Where processing happens
- 04Which models or services receive information
- 05What gets stored
- 06What gets logged
- 07Who can access it
- 08What returns to the business
Use the right model for the data, not just the most convenient model.
Enterprise architecture should allow model choices to be made intentionally. Depending on the use case, a system may use:
For workloads where their capabilities and approved data boundaries make sense.
Where greater infrastructure and information control is required.
Where ownership, customization or deployment flexibility matters.
For prediction, classification, vision or other domain-specific tasks.
Model selection is an architecture decision, not a brand decision.
AI shouldn’t become a shortcut around existing permissions.
An employee shouldn’t gain access to information through an AI assistant that they wouldn’t be permitted to access through the underlying business system. Depending on the implementation, that design principle can involve:
AI should respect the boundaries of the business systems it connects to.
Secure infrastructure is necessary. It isn’t sufficient.
AI systems introduce behaviours that conventional applications don’t always have — so they require controls beyond conventional application security.
- !Outputs can be incorrect.
- !Models can behave unpredictably around unusual inputs.
- !Retrieval can surface inappropriate information.
- !Agents can be given access to tools and actions.
- !Prompt injection can attempt to manipulate system behaviour.
- !Sensitive information can unintentionally enter AI workflows.
- !Model behaviour can change when underlying services change.
- 01Control the input
Understand what information can enter the system.
- 02Control the context
Determine what data the AI is allowed to retrieve.
- 03Control the tools
Limit which systems and actions AI can access.
- 04Control the output
Validate, structure or review outputs where appropriate.
- 05Control the action
Require human approval where the consequences justify it.
- 06Observe
Maintain visibility into what the system is doing in production.
The more autonomy AI receives, the more important the controls around it become.
Not every decision should be delegated to AI.
The right level of autonomy depends on the consequence of being wrong. A content suggestion may need little oversight; a financial decision may require explicit approval.
Assist
AI recommends. Human decides.
Prepare
AI prepares the action. Human approves.
Act + review
AI acts within defined boundaries. Human reviews exceptions.
Automate
AI acts automatically within controlled conditions.
Autonomy should increase with evidence, not ambition.
If AI affects the business, you need to understand what happened.
Production AI should provide enough visibility to investigate system behaviour when something goes wrong — requests, workflow execution, model calls, retrieved information, tool usage, decisions, errors, human intervention and performance.
A system you can’t observe is a system you can’t responsibly operate.
- 09:14:02.118User request“Which customers show declining orders this quarter?”
- 09:14:02.140Access checkRole: Sales manager · Region: North
- 09:14:02.205Context retrieved3 sources · scoped to user permissions
- 09:14:02.891Model callModel routed per policy
- 09:14:03.010Tool usageERP query · read-only
- 09:14:03.420System decision12 accounts flagged
- 09:14:03.433Human interventionReview requested for 2 accounts
- 09:14:03.440Performance1.3 s · within threshold
Trust has to survive production.
The environment changes after launch. That’s why Margins’ responsibility can continue after go-live through Managed AI — monitoring production systems for the signals required to understand whether they remain healthy, reliable and fit for purpose.
Explore Managed AI- Models change.
- Dependencies change.
- Users change.
- Data changes.
- Integrations change.
- New failure patterns emerge.
Visibility and control across production AI.
Rivermind is Margins’ proprietary AI Operations Platform. It connects models, data, tools, business rules and workflows while providing the orchestration and operational control required to manage AI in production.
Explore Rivermind (opens in a new tab)The intelligence you create should compound inside your company.
The more AI understands about your operations, customers, processes and organizational knowledge, the more valuable that intelligence becomes. Margins builds enterprise AI around the customer’s business environment rather than creating unnecessary dependency on a proprietary SaaS workflow.
The objective is not to make your business dependent on Margins. It’s to make your business more capable because of what we’ve built together.
Trust is designed into the system.
- 01Control
Know where your systems, data and AI operate.
- 02Minimization
Give AI access to what it needs — not everything available.
- 03Separation
Maintain appropriate boundaries between users, systems and environments.
- 04Observability
Be able to understand what the system is doing.
- 05Human oversight
Keep people in control where consequences justify it.
- 06Ownership
Build organizational intelligence that strengthens the customer rather than creating unnecessary dependency.
Start with the constraints.
Every enterprise environment is different. Before architecture is finalized, we work to understand the relevant requirements.
- Data sensitivity
- Infrastructure
- Existing cloud environment
- Internal systems
- Identity and access
- Third-party services
- Model providers
- Data residency
- Operational risk
- Human oversight
- Legal and compliance requirements
We don’t assume what your security requirements are. We design around the requirements your business actually has.
Security decisions happen throughout the implementation.
- 01DiscoverUnderstand the business information and processes involved.
- 02DesignDefine architecture, data boundaries, access and deployment.
- 03BuildImplement the system around those controls.
- 04DeployMove into the approved production environment.
- 05TrainEnsure users understand how the system should be used.
- 06AdoptEstablish responsible operational behaviour.
- 07OperateMonitor production performance and system health.
- 08ImproveAdapt as technology and business requirements change.
Security isn’t a gate at the end of delivery. It’s a design constraint throughout it.
One partner across the system.
Security and trust depend on how AI interacts with software, data, infrastructure, integrations, users and business processes. Margins brings those disciplines together.
AI Engineering
Understand the models, agents, retrieval and intelligence.
Software Engineering
Engineer the applications and services around them.
Data & Infrastructure
Design the environments and information flows behind them.
Enterprise Integration
Connect AI to existing systems without treating the business as a greenfield environment.
Training & Enablement
Help employees understand how to use new capabilities appropriately.
Managed AI
Maintain visibility after the system enters production.
One architecture. One accountable engineering partner.
Have security or architecture questions?
If you’re evaluating Margins for an enterprise AI initiative, bring your technical, infrastructure and data requirements into the conversation early. We’ll walk through the proposed architecture, deployment model, data boundaries and operational approach with your technical stakeholders.
Bring AI into your business without giving up control of what makes it valuable.
We’ll work with your technical and business teams to design an architecture around your systems, data, operational requirements and risk profile.
Talk to our teamYour infrastructure. Your data. Your intelligence.