# AI Platform: the shared foundation that lets every team build its agents

> Without a platform, every team starts from scratch: model access, security, guardrails, cost tracking. With a platform, it focuses on its business and relies on approved, shared and governed building blocks.

Source : https://dasein-ai.com/en/articles/ai-platform · Dasein · Updated 1 October 2026

## In short

- An AI Platform pools what each team would otherwise rebuild on its own: model gateway, operations, catalogue and governance.
- Each team picks its level of autonomy: use existing agents, assemble its own on the platform, or build independently while following shared standards.
- Dasein helps design this platform and its organisation: federated model, centre of excellence and ground rules between the platform team and business teams.

## 1. Without a platform, every team starts over

The first agents often appear in different teams, each with its own tools. After a few months, the same problems show up everywhere:

- model access keys scattered across code and configuration;
- guardrails reinvented by each team, with uneven security levels;
- costs invisible until the invoice, impossible to attribute;
- agents and tools nobody can find, so they get rebuilt elsewhere;
- no overall view for security, audit or compliance.

## 2. One platform, four blocks

An AI Platform pools whatever has no reason to differ from one team to the next. Teams keep their business, their data and their choices; the platform provides the rest.

*Diagram: The blocks of the AI Platform and the three ways teams use it.*

- **Operations** : Running agents and teams: runtime environments, security and identity, onboarding a new team, cost tracking, observability and evaluation.
- **Catalogue** : Everything reusable: agents, tools and MCP servers, workflows, prompts and skills, applications. Each item has an owner, a version and an approval status.
- **Model gateway** : A single access point to every model, proprietary, open source or customised: routing by need, quotas and cost per team.
- **Governance and standards** : The shared rules: guardrails, usage policies, recommended frameworks and patterns, best practices and reusable assets.

These four blocks govern the agents. What agents understand about your data depends on a layer just below: the semantic foundation, meaning the concepts, definitions and business rules that the platform makes queryable.

Read next : [Semantics: the bridge between your data and your agents](https://dasein-ai.com/en/articles/couche-semantique), Why an agent needs a common language between business and tech, and how to put it in place.

## 3. Three audiences, one platform

One platform serves three audiences, each asking a different question. It has to answer all three at once.

|  | Consumes | Assembles | Governs |
| --- | --- | --- | --- |
| Who | The business user | The use-case owner | The IT and platform team |
| Their question | “Does it save me time every day?” | “Can I build my use case without coding?” | “Do I control what leaves the information system?” |
| Their needs | Talk to an agent in natural language, get a reliable, sourced result, produce professional deliverables | Build an agent for their business, test, iterate, measure value, go to production when it works | Expose APIs as MCP servers and govern them, ensure security, compliance and audit, run the platform |
| Their tools | AI front end, Teams, Slack | Agent studio, LLM gateway, API management | VS Code, coding agents, MCP, command line |

> One platform, three entry points. IT governance does not slow business teams down: it protects them.

## 4. Three ways to use the platform

Teams have neither the same needs nor the same skills. A good platform does not force one model on them: it offers several levels of autonomy.

| Level | The team… | The platform provides… | Typically |
| --- | --- | --- | --- |
| Use | uses agents and applications from the catalogue, and exposes its data as tools | everything else | Business teams without developers |
| Assemble | builds its own agents, tools and applications with the platform’s building blocks, then publishes them to the catalogue | runtime, gateway, security, observability, guardrails, memory | Product or data teams with a few developers |
| Build independently | builds its own technical stack, independent of the platform core | the standards and governance to follow, and the catalogue to feed | Mature engineering teams, very specific needs |

> What stays the same at every level: everything goes through the catalogue and follows the shared governance. That is what lets one team reuse another team’s agent.

## 5. Three gateways, three governances

Every flow goes through a gateway, but not the same one. Model calls, tool calls and agent-to-agent calls have neither the same contracts, nor the same rules, nor the same maturity.

*Diagram: Three gateways: to models (LLM), to tools (MCP) and between agents (A2A).*

> Why not a single component? Different contracts, different governance units, different observability and different technology maturity. Merging them would force unacceptable trade-offs.

## 6. The federated model

Two traps lie in wait. Centralising everything in one AI team that builds it all creates a bottleneck. Decentralising everything brings back the initial chaos. The federated model splits the roles: application teams keep their applications, orchestration and data in their own environment; the platform team provides and runs the shared foundation.

*Diagram: The federated model: a platform team provides the foundation, application teams build on it.*

Two worlds, one interface contract: applications consume the platform’s capabilities through a stable contract, without knowing its internal layout. Several platform teams can even coexist, as long as they follow the shared contract set by the centre of excellence. Local autonomy speeds things up; central governance keeps them consistent.

|  | Centralised | Decentralised | Federated |
| --- | --- | --- | --- |
| Who builds the agents | One central AI team | Each team, alone | The teams, on a shared foundation |
| Strength | Consistency, control | Speed, close to the business | Both at once |
| Risk | Bottleneck | Duplicates, cost, security gaps | Needs a solid platform team |

## 7. The centre of excellence

Next to the platform team, a small centre of excellence carries the rules and the know-how:

- set the standards: frameworks, patterns, approved control middleware;
- approve models before they are made available;
- own the responsible AI framework: allowed uses, sensitive data, human approval;
- produce reusable assets: agent templates, skills, prompts, examples;
- support team onboarding and measure adoption and value.

> A good centre of excellence equips more than it polices: it makes the right path easier than the wrong one.

## 8. Where does MCP fit?

MCP and A2A are the standard plugs connecting agents to tools and to other agents. They make the platform’s life easier, but they are only one building block: the platform decides which plugs are allowed, for whom, and under which rules. Controls sit in two complementary places: in the gateways, for every agent at once, and in each agent’s middleware, closest to its decisions.

Article : [MCP: the protocol, its limits, and what it needs around it](https://dasein-ai.com/en/articles/mcp), What MCP brings, its use cases, its limits, the four identity patterns, the A2A and AG-UI protocols, and the solutions on the market.

## 9. Where to start

- Set up the model gateway: one access point, with cost tracking per team from day one.
- Open a minimal catalogue: a few approved agents, tools and prompts, each with an owner.
- Plug in central observability and evaluation.
- Onboard a pilot team at the “use” or “assemble” level, then industrialise onboarding for the next ones.
- Set up a light centre of excellence: standards, model approval, responsible AI.

## Further reading

- [AWS: Generative AI operating models in enterprise organizations](https://aws.amazon.com/blogs/machine-learning/generative-ai-operating-models-in-enterprise-organizations-with-amazon-bedrock/)
- [AWS: Build a multi-tenant generative AI environment for your enterprise](https://aws.amazon.com/blogs/machine-learning/build-a-multi-tenant-generative-ai-environment-for-your-enterprise-on-aws/)
- [AWS: Bedrock AgentCore overview](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html)
- [Microsoft: AI gateway capabilities in Azure API Management](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities)
- [Microsoft: Use a gateway in front of model deployments](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend)
- [Microsoft: Establish an AI Center of Excellence](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/ai/center-of-excellence)
- [Google Cloud: Agentic AI architecture guides](https://docs.cloud.google.com/architecture/agentic-ai-overview)
