On-premise AI
Local AI, under your control.
Three architectures to run AI models inside your own infrastructure. No data, prompt or response leaves your network: all three options give the same privacy guarantee and differ in scale, availability and governance.
Why on-premise
When data is sensitive, the model goes to the data
Not the other way around. Four reasons companies bring AI into their own infrastructure.
Privacy and sovereignty
Prompts, documents and responses are processed on your servers, with no third parties and without your data training anyone else’s models.
Regulation
Data protection laws (in Mexico, the 2025 LFPDPPP) and your industry’s regulators require knowing where data lives and who touched it.
Predictable cost
You invest in your own capacity instead of paying per token, with a cost you can budget.
Control and continuity
You decide which model version to use and when to update it. The platform keeps running without an internet connection.
Three options
Three architectures, one principle
The same privacy guarantee, with different levels of scale, availability and governance.
| Criterion | Option 1 · Local Node | Option 2 · Private Platform | Option 3 · Governed Sovereign AI |
|---|---|---|---|
| Who it is for | Mid-sized company with a first use case | Upper mid-market or enterprise with several teams | Regulated enterprise: banking, insurance, healthcare, government |
| Technology base | Open source: vLLM or Ollama on Docker Compose, LangGraph, pgvector, LibreChat, Langfuse | Red Hat OpenShift AI 3: llm-d + vLLM, Models-as-a-Service, EvalHub, NeMo Guardrails, GitOps | IBM watsonx (watsonx.ai, watsonx.data, watsonx.governance) on Red Hat OpenShift AI |
| Availability | One server with cold backup | High-availability cluster | Two sites with disaster recovery, disconnected (air-gapped) environment |
| AI governance | Traces and evals | Adds per-team metered usage, evaluation and platform guardrails | Adds model inventory, risk and regulatory evidence |
| Time to launch | 4 to 6 weeks | 8 to 12 weeks | 12 to 20 weeks |
Timelines and capacities are reference ranges: they are confirmed during discovery with your use cases, users and real volumes.
Option 1
Local Node: private AI on a single server
The shortest path to production for a mid-sized company with a first use case: one GPU server inside your network, with open-source components deployed with Docker Compose.
Limit: no high availability. The server is a single point of failure and is protected with cold backup.
Option 1 components and their licenses
| Component | Role | License |
|---|---|---|
| vLLM | Inference | Apache 2.0 |
| Ollama | Inference | MIT |
| LangGraph | Agents | MIT |
| pgvector | Vector store | PostgreSQL License |
| LibreChat | Chat interface | MIT |
| Langfuse | Traces and evals | MIT (core); enterprise features under a commercial license |
| Docker Compose | Deployment | Apache 2.0 |
Licenses verified in November 2026; they are confirmed at the start of each project. Each open-weight model has its own license, which we review for your use.
Option 2
Private Platform: AI as an internal service
For upper mid-market and enterprise companies with several teams: a cluster that serves several models to the whole organization, with high availability, per-team metered usage and declarative GitOps operations.
Requires a platform team, your own or managed by SISCON.
Option 3
Governed Sovereign AI: evidence for the regulator
For regulated enterprises —banking, insurance, healthcare, government—: end-to-end model governance (inventory, risk, lineage and audit) across two sites with disaster recovery and disconnected operation.
Higher investment and change management; justified by regulation or criticality. Disconnected operation is confirmed per product and version during design.
Security
Controls common to all three options
Present in all three; depth and evidence grow from Option 1 to Option 3.
No internet egress
Models and updates come in through a controlled internal registry, after their integrity is verified.
SSO with your directory
Access always goes through your corporate directory, with role-based permissions.
Permissions inherited from the user
The agent only sees what the user can see; document search is filtered by their permissions.
A log of every interaction
Every prompt, response and agent action is recorded and available for audit.
Guardrails
Filters for personal data and injection attempts, usage policies and escalation to a person in edge cases.
Encryption
In transit and at rest, with the keys under your control.
Decision
How to choose and how to grow
Start where you are today; the architecture grows when the business asks for it.
Start with Local Node if…
you have a clear, well-scoped use case and want results in weeks with a contained investment.
Scale to Private Platform if…
several teams are asking for AI, you need high availability and want to offer models as an internal service with metered usage.
Go to Governed Sovereign AI if…
a regulator or an audit requires evidence: model inventory, lineage, risk control and two-site continuity.
Evolution path: nothing you build is thrown away
Agents, document search (RAG) and evals move from one option to the next, because everything runs in containers and uses OpenAI-compatible APIs. You can start with one server and grow without rebuilding.
- 1 · Local Node
- 2 · Private Platform
- 3 · Governed Sovereign AI
Methodology
Six phases, from discovery to operations
The same path for all three options: measure before buying hardware and validate with a real case.
- F1
Discover
Use cases, sensitive data, regulatory framework and infrastructure. The output is the scope and the recommended option.
- F2
Design
We evaluate open models with your data, size GPUs, storage and network, and the architecture and its controls are approved.
- F3
Develop
We install the platform, integrate it with your directory and build the first use case.
- F4
Validate
Quality tests against a reference set, plus security, load, and verification that the network has no internet egress.
- F5
Deploy
Staged go-live, training, and handover of the runbook and the evidence of controls.
- F6
Optimize
Measured operations with KPIs, continuous evals and new use cases.
Evals are the exit criterion: nothing goes to production if it degrades measured quality.
FAQ
Frequently asked questions
Are open models good enough for my use case?
It depends on the case, which is why it is measured before committing scope: in the Design phase we compare open models with your own data, not with public benchmarks.
Do I need to buy GPUs before starting?
No. Models are evaluated first and hardware is sized with your real users and concurrency; the purchase comes after design.
Does an on-premise platform make me compliant with data protection law or my regulator?
Not on its own. It provides controls —data inside your network, permissions, logs and encryption— and evidence for your compliance program. Compliance is determined by your organization and its auditors.
Can I start with one server and grow later?
Yes. Agents, RAG and evals are built in containers with compatible APIs, so they move to the Private Platform or to Governed Sovereign AI without being rebuilt.
Does Option 1 have no license costs?
Its components are open source and each has its own license (Apache 2.0, MIT, PostgreSQL License); open-weight models have theirs too, which we review for your use. Options 2 and 3 include Red Hat and IBM subscriptions.
Can IA Factory run inside my network?
Yes, on any of the three options. With local models, scope is committed after measuring their quality with evals on your own code.
Next step
Choose the option with your numbers
A free 60-minute discovery session to review your use cases, sensitive data and infrastructure, and recommend where to start.