HomeArticlesProjectsSAALNewsletterConnect
AI Systems as a Layer · v0.4

SAAL Framework.

A model for thinking about AI systems.

Just as software infrastructure decomposed into SaaS and PaaS, AI systems can decompose into layers. Each layer is independently buildable, deployable, and scalable.

Why It Matters

Monoliths fail because everything is coupled.

Most AI systems are built as monoliths. They couple together retrieval, reasoning, orchestration, memory, and output.

When one breaks, everything breaks.

When you want to scale one layer, you scale all of them.

SAAL decouples this.

Modularity enables:

  • Specialization — teams own layers
  • Reusability — layers work across products
  • Scalability — scale layers independently
  • Reliability — failures don't cascade
  • Clarity — systems are understandable
How It Applies

Name the layer. Find the contract.

SAAL is not a prescription. It's a lens for diagnosing where systems break and why.

Start by naming which layer a problem lives in. The act of naming it precisely is half the diagnosis. A retrieval failure that gets misidentified as a reasoning failure gets fixed in the wrong place.

From there: define the contract between layers. What does the retrieval layer owe the reasoning layer? What format? What fallback? What latency budget?

Contracts make failures explicit. Explicit failures are fixable.

01
Retrieval
RAG Axis● Shipping
02
Orchestration
Agiorcx○ Building
03
Reasoning
Auramark○ Building
04
Analytics
Auramark○ Building
05
Social
Cespace● Shipping
The Five Layers

Five surfaces. One system.

01

Retrieval

RAG Axis

How the system accesses knowledge. Retrieval quality determines answer quality. This layer handles chunking, embedding, search, and context selection.

02

Orchestration

Agiorcx

How the system routes, plans, and coordinates work. The control plane for agent behavior. Execution contracts, handoff protocols, failure handling.

03

Reasoning

Auramark

Where inference happens. The model layer — but treated as infrastructure, not magic. Abstracted, swappable, observable.

04

Analytics

Auramark

How the system understands itself over time. Traces, evals, drift detection, re-grounding. The feedback mechanism for continuous improvement.

05

Social

Cespace

How the system interfaces with communities and creators. Community as infrastructure — not a marketing add-on but a product layer.

Building the SAAL Stack

Layer by layer. Problem by problem.

Building layer by layer, as constraints and problems demand solutions. Not all at once.

01
Retrieval
RAG AxisShipping
02
Orchestration
AgiorcxBuilding
03
Reasoning
AuramarkBuilding
04
Analytics
AuramarkBuilding
05
Social
CespaceShipping
Where Systems Stall

Four places production AI breaks.

At Retrieval

Most teams build retrieval as a tuning problem. It's a product surface. When it breaks in production, there's no visibility into why.

At Orchestration

Multi-agent systems work until they don't. Without an explicit contract between agents, handoffs fail silently. Errors compound.

At Analytics

Audit isn't on the roadmap. Engineers want to ship features. Auditing last quarter's behavior feels like overhead. It is the work.

At Social

Community is bolted on. A Discord server added after launch. It doesn't integrate with the product and doesn't drive it.

Case Studies

Seen in practice.

Retrieval

RAG at Scale

A team applying SAAL's retrieval layer principles reduced document ingestion failures by isolating validation at document boundaries rather than chunk boundaries.

Orchestration

Agent Handoff Contracts

Defining explicit execution contracts between agents exposed silent failures at handoffs that had been misattributed to model quality for months.

Use the framework

Free to use. Attribution kind.

SAAL is released under CC-BY 4.0. Use it in your decks, docs, team wiki — no permission needed. A link back is appreciated.

Go deeper