Posts
41 items under this folder.
What's new in Path, and a call for testers
Since July, Path has added an HCPC CPD profile export, the CSP Career Framework, link evidence, an achievement record, Trash and version history, and a complete export. I'm looking for more people to test it, with the understanding that things will almost certainly break.
AI infrastructure for academics: how earlier work makes later requests simple
I gave an AI agent two YouTube links and one sentence, and it returned two catalogued conference talks with slides, transcripts, and appraisal notes attached in Zotero. The request was short because months of earlier work sat behind it, including a fix from March and a tool from September. This post describes that session and an earlier one, and what they show about the difference between using AI to finish a task and using it in a way that leaves your system more capable than before.
A personal design system for scholarly output
Almost everything I produce starts as a markdown file and ends in a different format — a slide deck, a handout, a Word document, this website — and until September 2026 I designed each one from scratch. I've replaced that with a personal design system with one visual language, one identity, and a template for each format, all reading the same token file. This post explains what the system is, how the pieces fit together technically, and what's still unfinished.
What the Quartz graph view reveals about this site
The graph view is one of the reasons I built this site with Quartz, and now that there's enough writing on it the links between pages have started to form a shape. The graph opens from the top bar, shows the site's writing as a network coloured by type, and lets you choose what's on it. This post shows how to read it, and what it reveals about the site: where the ideas cluster, which concepts hold the rest together, and which ones nothing connects to.
A question that replaces "did you write this?"
Supervision has always run on an inference: if the writing is the student's, the work behind it probably is too. That's stopped holding, and detection tools don't repair it, because they're aimed at the document rather than the person. What I think breaks isn't integrity so much as calibration, which is a different, and more serious, problem to address.
Introducing Path, a CPD portfolio app
Path is a CPD portfolio app that shows you what you're missing against the standard you're working towards, rather than only showing you what you've done. It began as a two-weekend prototype and has grown into a real, hosted web app that maps your claims and evidence against any framework — a promotion, a fellowship, a regulator's CPD standard — and shows you the single highest-value thing to do next. It's still a closed, invite-only alpha, and the waiting list is now open.
The verification trap
Institutions everywhere now insist on the same rule — use AI, but always verify its output. Yet verifying AI output is hard, slow, and often inconclusive, even in domains where you're competent to judge it. This post pushes that advice to its limit to see what breaks, and finds that as models improve, the verification mandate quietly trains the opposite of the scepticism it intends.
Building a CPD app with Claude Code
Most CPD tools are built for compliance, not development. I wanted something that started from the gap; what am I missing, and what would close it? I couldn't find the tool I needed so I built one called Path instead. It describes what I think professional development should look like, and what two weekends with Claude Code produced.
What software engineers can teach us about AI in doctoral research
PhD students are using AI across their doctoral work, but current policies focus on permission rather than specification. Drawing on how software engineers solved a structurally identical problem, this post introduces the research harness: a seven-part operating context that makes AI contributions visible, traceable, and supervisable. The harness addresses drift, offloaded thinking, and attribution failures — not by restricting AI use, but by specifying what the agent can and cannot do within the work.
A few thoughts on student use of AI
Tim Fawns published a LinkedIn post setting out 17 points about student use of AI, drawing on his experience as a researcher and educator. The points push back on the framing that positions students as cheating or avoiding learning, and ask for a more sophisticated understanding of what's actually happening. I've formatted Tim's LinkedIn post as a one-page PDF for easier sharing.
We're comparing AI chatbot health advice to the wrong thing
One in seven people in the UK are using AI chatbots for health advice instead of seeing a GP. The institutional response has been to warn them off, but that response applies a standard it doesn't consistently apply to anything else in the system. This post argues that the risk comparison driving those warnings is systematically skewed, and that a more honest accounting points toward an entirely different kind of response.
The PhD is a process of becoming: Reimagining AI and PhD assessment
AI has disrupted doctoral education in two ways: the immediate question of AI-assisted writing, and the deeper question of what the PhD means when AI can conduct research from scratch. This post argues that the thesis was always a proxy for the person; evidence of an identity shift, not the thing being assessed in its own right.
An open scholarship workflow: What academic publishing can learn from open source
Academic publishing treats scholarship as a finished, individually owned artefact. This post describes a writing and publishing workflow built on a different premise: that a scholarly corpus could work like an open source project — readable, contributable, forkable, and never permanently owned by anyone.
Transform documents with AI
Language models can transform documents into interactive tools in minutes. This post walks through a concrete example, turning a 21-page Word questionnaire into a working web app, and reflects on what that capability makes possible.
AI Masterclass for Healthcare Professionals
More than 10,000 healthcare professionals have taken the courses I've created for Physiopedia Plus. This post focuses on the AI Masterclass for Healthcare Professionals Programme — a practical introduction to AI in clinical practice, education, and research. Physiopedia Plus members get full access, and a 30% discount code is included for new sign-ups.
AI assessment scales are taxonomies of containment
AI assessment scales and similar policies are taxonomies of containment that ask how to protect existing assessment practices from AI, not whether those practices remain fit for purpose. This post argues that they're asking the wrong question, and examines what higher education might be asking instead, with particular implications for health professions education.
Designing AI out of assessment should be an academic offence
Academic offences committees are investigating the wrong party. When AI is integral to authentic professional practice, assessment that excludes it does not protect rigour — it tests performance in a professional context that no longer exists. Valid assessment measures what graduates will actually need to do; for most health professions graduates in 2025, that includes thinking well with AI. The accountability for assessment design lies with educators, not students.
Why AI writing sounds convincing, and why that's noise
AI-generated text is easy to read whether or not its content is accurate or well reasoned, and easy-to-read text feels true. Fluency was once a reasonable trace of genuine thinking, since a student who wrote clearly had usually thought clearly, but that relationship no longer holds. The AI literacy response of teaching output evaluation is a temporary fix, because as models improve, output quality converges on expert level across every artefact we care to measure. Spotting today's failure modes leaves open what you'll do when they're gone.
The writing was never the point: AI and academic writing identity
When AI could write everything I'd ever written, I had to ask: what had I been doing all this time? The answer changed how I understand both writing and AI — and what it means to be a scholar in a world where words are cheap.
Building arguments with AI
A field note on building arguments with AI: the brainstorming command I use to engage with any source, with an excerpt showing what a session looks like — Claude surfacing vault notes and Zotero sources, and why the conversation living in markdown matters.
Why AI makes spelling mistakes
Claude produced the word "contribuves" in a piece of writing, which is obviously not a real word. This is a different kind of error than hallucination, and the distinction matters.
How I review a week of reading notes with AI
Every week I annotate articles in Zotero, highlights in Reader, and podcasts in Snipd, all of which is synced to Obsidian. By Friday I have a week's worth of material, tagged and structured, but unreviewed. This post describes the weekly review command I built to surface what matters and create a reason to engage with it.
Building AI personas for professional practice
Most advice on AI effectiveness focuses on prompt engineering. The real leverage comes from somewhere less obvious; knowing your professional commitments clearly enough to turn them into context an AI can work within. This post describes how to build AI personas for professional practice — structured documents that compress your values, frameworks, and evidence into a form an AI agent can actually use.
Claude deleted my file. It was my fault. But Claude took the blame.
A field note on the time Claude deleted my file. The agent followed my instructions precisely and that was the problem. A reflection on a different kind of AI failure mode, and what the model's apology reveals about where responsibility actually sits.
Preparing lecture slides with AI agents
I've been writing lecture slides in markdown for several years, mostly because I enjoyed working in structured formats and plain text. That decision turned out to matter in ways I didn't anticipate. When AI agents have access to your local filesystem, the format your teaching materials live in determines what's possible.
AI dependency in practice: When the tools become infrastructure
A field note on what the recent Claude outage revealed about where I am on the dependency curve, and what the difference between a session limit and an outage tells you about infrastructure.
AI agent governance in higher education: Building the institutional harness
The previous posts described what makes agentic workflows coherent at the individual level: a plan, documentation as infrastructure, and domain expertise that can evaluate outputs. Together, these form an informal harness; the conditions within which delegation stays accountable. At institutional scale, a personal harness is not enough: multiple people directing agents without shared constraints produce compounding drift that no amount of human oversight can track. This post examines what AI agent governance in higher education actually requires, and why a harness, not better oversight, may be the right frame.
Working effectively with AI agents
What does it actually take to work with AI agents in a disciplined way, and how does someone get there from where they are now? This post draws on thinking from developers who've been working through this question longer than most academic knowledge workers have, and translates the hard-won lessons across. Three prerequisites emerge: planning before handoff, documentation treated as infrastructure rather than record, and domain expertise sufficient to evaluate what agents produce. The path in isn't a course or a tutorial — it's building something real with stakes attached.
AI agents for academic workflow
For the last few months, my screen has been split between Obsidian and a terminal, with two or three AI agents running in parallel tabs. This post describes what that shift in academic workflow looks like and what made it possible. The change is not simply additive: the work has shifted from execution to direction. What that distinction means in practice — and why it matters for those of us working in knowledge-intensive academic roles — is what I try to work out here.
Seven principle for collaborating with AI
Seven principles for extended AI collaboration, distilled from a week-long project to restructure a large note collection using Claude Code. The principles cover goal-setting, understanding what AI can and cannot contribute, investing in planning conversations, adaptive planning, safety infrastructure, treating AI output as drafts, and expecting to learn something about your own thinking. Offered not as rules to follow but as patterns to recognise.
Building an AI-ready knowledge base
A detailed account of a week-long project to restructure 5,819 Obsidian notes using AI as a working partner. The project involved building a 23-category taxonomy, migrating thousands of legacy notes to a consistent metadata structure, and generating AI-written descriptions for every note in the collection. The piece describes not just what was done, but how extended planning conversations, external project documentation, and careful human review at each phase made the work tractable. The most unexpected outcome was that building infrastructure for a note collection required articulating, for the first time, precisely how I think about my academic field.
Is a smaller AI model good enough?
A field note on switching my default in Claude Code from Opus 4.6 to the smaller Sonnet 4.6, testing it on a task I'd normally give the larger model, and finding it good enough so far.
The hidden inefficiency in how we work with AI
Most academics use one AI model for everything, but different models suit different kinds of cognitive work. Choosing the right AI model for each step of a task can improve both efficiency and output quality. Michael Rowe describes how he noticed this in his own workflow, what splitting one workflow across three models looks like, and why the same logic applies when a university plans its AI strategy.
Querying the Zotero database with AI
What happens when you query Zotero with AI and treat your whole reference library as context, instead of searching it one document at a time? This field note describes a proof of concept in which Claude Code reads the Zotero database file directly. The approach works, and what breaks shows how much your metadata practices matter. It also sets out the privacy trade-off of sending query results to a cloud-based model.
Context engineering for educators: infrastructure, not just policy
Most universities have responded to AI by rewriting assessment policies and running prompt-writing workshops. Context engineering asks for something different: decisions about system prompts, memory, retrieval, and connectivity that commit an institution to a direction for years. This post sets out what context engineering involves, why integrative, longitudinal, and values-based clinical education needs it, and why the gap between changing words and changing structures is where most institutions are stuck. It ends with three questions a programme team can ask about the AI tool it already uses.
The quality of the challenge: AI as a thinking partner
Most discussions of AI in writing focus on output. This post describes using AI as a thinking partner while revising a theoretical framework paper for journal submission, asking it for critique, arguing back where it was wrong, and testing the draft against my own voice. The exchange changed the paper's structure and how it describes its methodology, and showed that the value lay in the quality of the challenge.
Organising your notes for AI: why retrieval isn't enough
Most advice on organising notes for AI treats it as a retrieval problem, as if the AI only needs to find the right documents. The harder problem is translation, making the relationships in your thinking machine-readable without losing what makes them yours. This post explains why search and retrieval fall short, shows what a typed link between two notes looks like, and suggests one small way to start.
Building an AI workflow for academics with structured documentation
Most advice on building an AI workflow for academics concentrates on writing better prompts. After several weeks of restructuring years of scholarly output with Claude Code, I've found the leverage lies in the structured context around the model — documentation that works as external memory, a cycle of testing rules and locking in the ones that hold, and the discipline of making implicit connections explicit. The same applies to institutions, where AI tools are only as reliable as the information architecture they're given.
Similarities between AI and human thinking: What if we're the language models?
Discussion of AI and human cognition usually dwells on the differences. Turn the question around and the terminology of language models describes human thinking surprisingly well: context windows, biased training data, tokenisation, temperature, hallucination, system prompts, and pattern matching all have human counterparts, some of which health professions education already has names for. The similarities say something about our own cognitive architecture, and the strength of our resistance to them says something about what our professional identities depend on.
Hidden prompts in assignments: the security theatre of AI detection
Some lecturers now hide prompts in assignment materials so that any AI system reading them adds tell-tale keywords to its output. This post looks at what those tripwires assume about assessment, and why what they detect is carelessness with AI, not the absence of learning. The technique also invites students to turn it on AI marking, and starts an escalation neither side can win. The alternative is to ask what assessment is for when producing the artefact takes seconds.
A bitter lesson for higher education
Rich Sutton's "bitter lesson" from AI research is that general methods using computation beat decades of carefully encoded human expertise. Higher education faces a parallel lesson about AI and assessment validity. Essays, reflective accounts, and other artefacts worked as evidence of learning mainly because they were hard to produce, and detailed briefs and rubrics now read as ready-made prompts for a language model. Handwritten exams, proctoring, and AI use scales all try to make artefacts hard to produce again, when the question worth asking is how we recognise learning at all.