Horizon LabsHorizon Labs

Insights

Product, design, AI, and engineering perspectives from our team.

Caching Strategies for LLM Applications: Reducing Latency and Cost
AI in production23 June 2026

Caching Strategies for LLM Applications: Reducing Latency and Cost

Caching is one of the most underused levers for reducing cost and latency in production LLM applications. This article covers prompt caching, semantic caching, and response caching — what each layer does, when to use it, and how to think about invalidation and observability.

11 min readChris Kerr
Kubernetes for AI Workloads: When It's Worth the Complexity
AI in production6 June 2026

Kubernetes for AI Workloads: When It's Worth the Complexity

Kubernetes is worth the complexity for AI workloads when you are serving multiple models in production, managing GPU scheduling across workloads, and have platform engineering capacity to operate it. For teams at earlier stages, managed services are the more pragmatic starting point. This guide helps technical leaders make the call clearly.

7 min readChris Kerr
Open-Source vs Proprietary LLMs: When to Self-Host
AI in production6 June 2026

Open-Source vs Proprietary LLMs: When to Self-Host

Self-hosting open-weight models like Llama or Mistral gives Australian teams data residency, cost control at scale, and deployment flexibility — but it comes with real infrastructure and operational tradeoffs. This post works through when each approach makes sense, with a practical framework for mid-market teams deciding between open-weight self-hosting and proprietary APIs like GPT-4 or Claude.

10 min readChris Kerr
Vector Database Guide: Pinecone vs Weaviate vs pgvector
AI in production9 Apr 2026

Vector Database Guide: Pinecone vs Weaviate vs pgvector

Compare Pinecone, Weaviate, and pgvector for Australian AI applications. Practical guidance on choosing the right vector database for RAG systems, data sovereignty, and scaling requirements.

7 min readSarah Mitchell
Vector Database Architecture for RAG Applications in Australia
AI in production2 Apr 2026

Vector Database Architecture for RAG Applications in Australia

Vector databases form the backbone of RAG applications, but selecting the right architectural approach requires understanding trade-offs between managed services, open source solutions, and PostgreSQL extensions. Australian organisations must also consider data sovereignty and compliance requirements when making these decisions.

6 min readSarah Mitchell