AI/ML

Codifying your documentation reorg: playbooks as the shared interface for humans and AI teammates

on restructuring engineering documentation with an AI teammate.The messy truth about restructuring engineering docs with an AI teammate - linkStitching five documentation frameworks into one coherent engineering wiki - linkYour Confluence should be a derived read model over your repo - linkCodifying your reorg: playbooks as the shared interface for humans and AI teammates - A playbook is one document. A human on their first day can read it and do the work. An AI agent, given the same document,...

Read

The AI-Ready Enterprise: Preparing Data for the Age of AI

A practical framework for building data systems that AI can find, understand, trust, and use.Conversations around enterprise AI are moving rapidly from models to applications. Foundational models are becoming increasingly capable, and organisations are experimenting with retrieval augmented generation (RAG), tool calling, AI agents and multi-agent systems to bring intelligence into their business processes. Yet, as these systems move closer to production, a familiar constraint emerges: the data they need was rarely designed for AI consumption. Enterprise data has traditionally been...

Read

Your Confluence should be a derived read model over your repo

on restructuring engineering documentation with an AI teammate.The messy truth about restructuring engineering docs with an AI teammate - linkStitching five documentation frameworks into one coherent engineering wiki - linkYour Confluence should be a derived read model over your repo - Codifying your reorg: playbooks as the shared interface for humans and AI teammates - [coming soon]Six weeks into Beacon's reorg, we opened "catalog-service - API reference" in Confluence and found a POST /variants/bulk-upsert endpoint documented in careful detail. That...

Read

Building the Next-Generation Data and AI Platform for SiteMinder

SiteMinder is the global leader in hotel commerce, with 56,000 hotel customers that use its platform to generate more than AU$85 billion in revenue each year. As a category leader, maintaining its competitive edge was important and so it embarked on a journey of pioneering advanced AI capabilities, including an intelligent "Room Nights Forecasting" engine for its groundbreaking Dynamic Revenue Plus product, which uniquely provides hotels live market intelligence as local demand changes.The company faced significant bottlenecks upfront: Firstly, SiteMinder needed...

Read

Agentic AI: Building the Right Mental Model for System Design

AI agents have evolved from Large Language Models (LLMs) that primarily generate responses to systems capable of reasoning and dynamic decision-making. By interpreting goals, inferring what is needed, and integrating external capabilities such as APIs and databases, the LLM serves as the decision-making core of an agent. Agentic AI refers to systems built around these intelligent agents.An AI agent extends beyond a simple prompt by combining an LLM’s reasoning capability with functional layers such as tools, memory and orchestration. Tools...

Read

Stitching five documentation frameworks into one coherent engineering wiki

on restructuring engineering documentation with an AI teammate. 1. The messy truth about restructuring engineering docs with an AI teammate - link 2. Stitching five documentation frameworks into one coherent engineering wiki - 3. Your Confluence should be a derived read model over your repo - [coming soon] 4. Codifying your reorg: playbooks as the shared interface for humans and AI teammates - [coming soon] There is no shortage of framework retrospectives. Sequin wrote a widely-read post on how they...

Read

Story Points Stopped Working the Day AI Started Writing Code

Why estimates now mispredict in both directions, and a framework that measures what actually constrains delivery A few sprints ago I sat in a planning session where the team spent twenty minutes debating whether a story was a 5 or an 8. It was a genuinely tricky piece of matching logic, the kind of story that would have earned its 8 points in any planning poker session over the last two decades. After the meeting, the developer pointed Claude at...

Read

Driving a 10% Production Increase: Sahaj-built Connected MES Platform Standardizes Operations for Asia’s Leading Automaker

Beyond cost savings, the platform provides complete vehicle traceability for regulatory compliance, optimizes production sequencing, and ensures consistent quality and efficiency through standardized workflows across all assembly lines. Our client is an industry-leading automotive manufacturing company in Asia that manufactures approximately one million vehicles each year. They have manufacturing and assembly lines that are geographically spread across multiple plants in the region. Additionally, each plant is used to manufacture different vehicle models and its variants. Historically, they used off-the-shelf MES (Manufacturing...

Read

Observability for AI-Assisted Development

Developers using AI estimate they’re 24% faster. A randomised controlled trial measured them at 19% slower.That’s from METR’s 2025 study. These were experienced open-source developers working on their own codebases with tools they chose. Their self-assessment was off by over 40 percentage points.If your perception of AI’s impact is that unreliable, what are you actually measuring?If you didn’t measure before AI, measuring with AI won’t work.You can’t attribute improvements to AI if you don’t know what “before” looked like. Cycle...

Read

The Judgement Pyramid: Reasoning vs Measurement

A team I was talking to had built a code-review skill in Claude Code. It looked good: a careful prompt, a set of rules, and examples. Then it shipped a PR with a nested recursive loop inside another recursive loop. Cyclomatic complexity any static analyser (PMD, radon, ESLint’s complexity rule) would have flagged in milliseconds. The skill missed it.The team’s response was to iterate the skill. More examples. More rules. A few more lines of prompt. The context window kept...

Read