---
id: "action-build-orchestration-layer"
type: "action-item"
source_timestamps: ["§ Training for a Marathon When You Can Only See Two Feet Ahead"]
tags: ["architecture", "security"]
related: ["concept-ai-orchestration-layer"]
action: "Develop an internal orchestration layer to securely route prompts across multiple commercial LLMs."
outcome: "Maintains data security while allowing rapid, near-real-time adoption of new LLM features."
speakers: ["Steve Tulenko"]
sources: ["execution"]
sourceVaultSlug: "hbr-seg-execution"
originDay: 8
articleStem: "hbr-cl-93-legacy-financial-all-in-genai"
sourceUrl: "https://hbr.org/2025/03/how-a-legacy-financial-institution-went-all-in-on-gen-ai"
sourceTitle: "How a Legacy Financial Institution Went All In on Gen AI"
---
# Build a Multi-Model Orchestration Layer

## Action — Build a Multi-Model Orchestration Layer

**Do:** Develop an internal **low-code/no-code orchestration layer** that sits on top of **multiple commercial foundation models**. It securely routes prompts based on **cost and capability** while keeping all interactions inside the company's secure infrastructure.

**Outcome:** Maintains **data security** while allowing **rapid, near-real-time adoption** of new LLM features (e.g., PDF interrogation, image analysis within hours).

### Connections
- The concept: [[concept-ai-orchestration-layer]]; depends on [[prereq-secure-infrastructure]] and [[entity-microsoft-azure]].
- Enables the strategy in [[claim-proprietary-models-not-competitive-advantage]].