Iain Macaskill

Delivery and digital transformation leader with 17+ years leading large-scale change in Agile and lean environments. These days I spend my spare hours proving what one non-developer can ship with AI: practical, well-governed tools, built by describing the outcome in plain English.

About

I am a delivery manager and servant leader. I create the conditions for teams to deliver value: collaboration, self-organisation, transparency, and the discipline to measure results rather than guess at them.

I cannot write code, and that is rather the point of this site. Everything below was built by describing outcomes clearly to AI tools, then governing what came back: testing it, documenting it, and deciding what it is not allowed to do. The same question decides whether any AI is worth trusting at work: not "how much can it produce?" but "what is it not allowed to do, and who signs it off?"

Projects

Local AI Job Hunter

A free, local-first job search assistant: it finds and scores roles, tracks every application, and drafts tailored CVs only for roles you choose to pursue. The guardrails are the product: it will not spray generic applications, it will not claim a skill you cannot defend in an interview, and nothing goes out unread.

View on GitHub

Minecraft with Claude Code: a parent's guide

A one-page guide to running a safe family Minecraft server at home, with an AI builder that turns "build us a waterpark" into a real one in twenty minutes. Real logins only, a guest list I control name by name, and every join logged.

Read the guide

Wing foil performance analysis

Six months of my own Garmin GPS data (around 110,000 points across 22 sessions) turned into a measured answer: my longest unbroken flight went from 78 seconds in January to 23 minutes in June. Flight detection, speed analysis and real offshore wind data, matched and visualised without writing a line of code.

Second brain pipelines

Local, zero-cost pipelines that turn meeting audio and podcast archives into searchable, linked knowledge bases: automatic transcription with speaker recognition, then ingestion into a structured vault an LLM can query and maintain.

Writing

I write on LinkedIn about AI adoption from a delivery perspective: governance before headcount, measurement before spend, and what non-developers can now build for themselves. Follow along here.