Skip to content

The Cleo Team

The Workshop

Notes on building an AI marketing operating system. Architecture decisions, technical challenges, and the craft of making something that thinks.

4 min read

The Model Is Not the Product

Choosing which AI model to use is the least important architectural decision in an AI product. The context assembly, the tool design, the output handling, the error recovery - everything around the model is what makes the product.

aiarchitecturephilosophy
4 min read

What Your AI Cannot See

When an AI system produces the wrong output, the instinct is to add more instructions. But the problem is usually not that the model ignored the rule. It is that the model could not see the information it needed to follow it.

aiarchitectureengineering
4 min read

Rules as Codebase

The quality of AI output is determined less by the model and more by the constraints you give it. Building a rule system is building a second codebase - one that governs behaviour instead of functionality.

aiarchitectureengineering
3 min read

Isolation as a Guarantee

In a platform where AI processes business-sensitive marketing data, tenant isolation is not about compliance. It is about the fundamental promise that your data is yours alone.

securityarchitecturephilosophy
3 min read

Building Email from First Principles

We could have integrated an existing email marketing platform. Instead, we built email into Cleo from the ground up. The decision came down to what AI-native email marketing actually requires.

emailarchitectureproduct
3 min read

Search Beyond Keywords

Keyword search answers the question "which documents contain these words." Semantic search answers a fundamentally different question: "which documents are about this idea." The distinction reshapes how an AI platform organises knowledge.

architecturesearchai
3 min read

Security as Architecture

In AI products where natural language can trigger data operations, security is not something you add. It is something you build into the structure of every layer.

securityarchitectureengineering
3 min read

Orchestrating Multiple Minds

Cleo uses different AI models for different tasks - not because we could not standardise, but because specialisation produces better results. Here is our philosophy of multi-model orchestration.

architectureaimodels
3 min read

Context Is Information Architecture

The quality of an AI system is determined less by the model and more by what information reaches the model at the right time. Context assembly is the discipline that makes everything else work.

architectureaicontext
3 min read

The Service Boundary

Between our AI and our data sits a disciplined layer of typed services. This boundary is the single most important architectural decision in the entire platform.

architectureservicesengineering
2 min read

Why One Mind Beats Many

The industry is building swarms. We built a single intelligence with full platform control. Here is the reasoning behind that architectural decision.

architectureaiphilosophy