Ready-made course · 2 days · Advanced
Architecting Enterprise Generative AI
A two-day course for architects and senior technical leaders: design enterprise-scale AI capability as a platform, not as a sequence of isolated projects.
Organisations that succeed with generative AI rarely do it as a pile of unrelated copilots. They build a small number of shared capabilities — identity, model access, retrieval, evaluation, cost control — and let product teams consume them. This course is about that enterprise shape.
You work through enterprise AI platforms, shared services, model gateways, identity, security, governance and data access. RAG platforms, observability, evaluation and cost management are designed as multi-team services. Vendor abstraction, deployment patterns and the split between platform and product responsibilities are made explicit.
The teaching uses architecture case studies. You design a platform that several product teams could use without each team negotiating a model vendor, a vector database and a logging story from scratch.
The result is an enterprise architecture and an operating model, not a project plan for a single assistant.
- Who it is for
- Architects and senior technical leaders responsible for enterprise AI capability, platform strategy or multi-team enablement.
- Before you start
- Experience with enterprise architecture, platform engineering or large-scale delivery. Familiarity with generative AI is expected. This is not an introductory course.
You will be able to
- Design an enterprise AI platform with shared services for models, retrieval, identity and evaluation.
- Define platform versus product responsibilities so teams are neither blocked nor unsupervised.
- Specify identity, security, governance and data-access patterns that multiple products can share.
- Plan vendor abstraction and model-gateway policy without pretending lock-in is free to avoid.
- Design RAG and evaluation as platforms rather than as features inside one application.
- Establish cost management, observability and enablement for several teams.
- Produce a target architecture and a sequenced path from current isolated projects.
Modules
8 quarter-day modules. Each one can go into a custom course on its own.
From projects to an AI platform
- The shared services every AI project rebuilds.
- Platform scope: what to centralise and what to leave to teams.
- Funding, ownership and a roadmap.
- Exercise: list what your current projects duplicate.
The AI gateway and control plane
- One point of access to every model provider.
- Keys, quotas, routing and fallbacks.
- Logging, redaction and policy at the gateway.
- Build or buy: open-source and managed gateways.
Identity, security and governance for AI
- Acting on behalf of a user: identity through to tools and data.
- Data classification and what may reach which model.
- Audit, retention and regulatory obligations.
- Governance that teams can follow without a committee.
Vendors, contracts and lock-in
- Frontier providers, cloud platforms and open-weight models.
- Data terms, residency and retention in contracts.
- Portability: abstractions that help and ones that only add cost.
- A multi-provider strategy that stays manageable.
Releasing and operating AI systems
- Versioning prompts, models and indexes together.
- Canary releases, shadow traffic and rollback.
- SLOs for quality as well as uptime.
- Model deprecations and provider incidents.
Enablement and the AI operating model
- Centre of excellence, platform team or federated model.
- Templates, guidance and reviews that speed teams up.
- Skills and training across roles.
- Measuring adoption and value.
Cost allocation and FinOps for AI
- Tagging and attributing every model call.
- Budgets, alerts and showback.
- Commitments, provisioned capacity and discounts.
- Cost per outcome, not cost per token.
Workshop: a target architecture
- Current state: systems, data and AI projects already running.
- Target state: platform services, boundaries and owners.
- Gaps, risks and sequencing.
- Output: a target architecture diagram and a first-year plan.
Practical work
Architecture case studies and design work. You critique an estate of isolated AI projects, define shared services, and produce a target architecture, responsibility split and sequenced roadmap. Where possible, the case is your organisation’s.
You take away
- A target enterprise AI architecture
- A platform versus product responsibility matrix
- Gateway, RAG, evaluation and cost-control service definitions
- A sequenced enablement roadmap
Combine it with
- Production AI Architecture · 2 days
- Building Enterprise AI Assistants · 2 days