Horizon LabsHorizon Labs

Insights

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

Designing Agent-Ready APIs for AI Agents and MCP
17 Nov 2026

Designing Agent-Ready APIs for AI Agents and MCP

AI agents and the Model Context Protocol are changing what counts as a well-designed API. Here's how engineering teams should approach authentication, rate limiting, documentation and observability so agent traffic can be safely integrated.

7 min readChris Kerr
AI-Powered Warranty, Returns & Claims Automation for Retail
15 Nov 2026

AI-Powered Warranty, Returns & Claims Automation for Retail

A practical guide to how AI can automate warranty validation, returns triage, and claims assessment for Australian retail and e-commerce operators — covering fraud risk, customer experience trade-offs, and integration with existing order management systems.

5 min readChris Kerr
AI Agent Marketplaces: Build vs Integrate Decision Guide
10 Nov 2026

AI Agent Marketplaces: Build vs Integrate Decision Guide

Integrate a marketplace agent when the task is standardised and your data already lives with the vendor. Build custom when the agent is core to your product. Here's the framework, plus how security review should shape the call.

6 min readChris Kerr
How to Decommission Legacy ML Models Safely
6 Nov 2026

How to Decommission Legacy ML Models Safely

Decommissioning a legacy ML model safely requires dependency mapping, a staged rollback plan, and clear communication to affected teams — not just switching the service off. Here's how to do it without breaking what you didn't know was connected.

6 min readChris Kerr
AI Dynamic Pricing for SaaS and E-Commerce
4 Nov 2026

AI Dynamic Pricing for SaaS and E-Commerce

Dynamic pricing can lift revenue, but a poorly designed system creates unfair outcomes and billing chaos. This decision guide covers the data, guardrails, and billing integration patterns product and data leaders need before building an AI pricing engine.

7 min readChris Kerr
AI-Assisted Estimation for More Predictable Software Delivery
29 Oct 2026

AI-Assisted Estimation for More Predictable Software Delivery

AI-assisted estimation tools can sharpen sprint planning by surfacing historical patterns and outliers in delivery data — but they cannot replace the judgement calls at the heart of estimating genuinely uncertain work. Here's a practical look at where these tools help, and where they don't.

6 min readChris Kerr
Feature Flagging and Progressive Delivery for AI Rollouts
28 Oct 2026

Feature Flagging and Progressive Delivery for AI Rollouts

AI features fail differently to normal software — unpredictably, not consistently. Here's how growing engineering teams use feature flags, canary releases and staged rollouts to limit the blast radius when that happens.

6 min readChris Kerr
Trust and Safety AI: Moderation and Fraud for Marketplaces
17 Oct 2026

Trust and Safety AI: Moderation and Fraud for Marketplaces

A practical look at where AI genuinely helps marketplace platforms detect listing fraud, fake reviews, and account abuse — and where human review has to stay in the loop. Includes how this differs from customer-support chatbot use cases and what Australian governance guidance expects.

7 min readChris Kerr
Observability for AI Agent Pipelines in Production
AI in production10 Oct 2026

Observability for AI Agent Pipelines in Production

Multi-step AI agents fail in ways infrastructure metrics can't explain. This guide covers how to instrument chained model and tool calls with distributed tracing and structured logging so engineering teams can actually debug production failures and latency.

7 min readChris Kerr