Accelerator ยท June 2026
Enterprise AI Architecture Sprint
A public-safe accelerator that converts enterprise AI potential into reviewable system evidence: architecture, governance, security, validation, and customer-delivery readiness.
First principle
Enterprise AI delivery is proven by a system package with architecture, governance, deployment, security, validation, and customer-delivery evidence, not by a model demo alone.
Course sequence
AI Gateway Architecture Evidence
Day 1 turns a model-centric LLM demo into a system-centric enterprise AI architecture exercise. The learner produces architecture evidence before Day 2 implementation.
Agent Governance Framework
Day 2 extends AI Gateway evidence into agent registration, ownership, task scope, tool/data/memory boundaries, policy gates, message mediation, audit events, evaluation hooks, and red-team seeds.
Red Teaming Framework
Day 3 is reserved for turning gateway and agent governance assumptions into red-team test cases, regression checks, and reviewable safety evidence.
Evidence definition
- architecture view
- minimum viable output
- validation checklist
- failure modes
- linked module or lab path
- next implementation gate
Expansion mechanism
- Each course day lives in one `day-NN-topic/` directory inside the handbook accelerator.
- Student-facing website pages are generated from the `days` entries in `src/lib/content/site.ts`.
- Future Day 2, Day 3, and later pages become public when their day object is marked `published: true` and given a stable route.
Source boundary
The website publishes the student-facing learning path and public-safe summaries. The handbook repo remains the canonical home for worksheets, instructor guides, rubrics, reference answers, handoffs, and detailed source packages.
Canonical source: ai-systems-engineering-handbook/accelerators/enterprise-ai-architecture-sprint/