Tag: context-engineering
34 items with this tag.
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.
AI can only use what it can see
What changes when AI can reach your working context, plus the Taipei summit on AI in physiotherapy.
Context window
The context window is the amount of text a language model can take into account at once, covering its instructions, the conversation so far, and any documents it has been given. It's the model's only working memory, and how full it is, and what sits where in it, shapes the quality of the answer.
Making sense of AI in clinical practice: ATOCP at BOA Congress
An invited talk in the ATOCP session at the BOA Annual Congress 2026 in London. It looks at what AI can already do in clinical work, why the usual responses to it leave clinicians as spectators, and what physiotherapists bring that AI systems don't have, which is context. The second half turns to patients, who are already using AI before they arrive, and asks what changes in the consultation when both sides bring their own context and their own agents. It closes with three things to do the next working day.
Research harness
A research harness is a structured specification, negotiated between a doctoral researcher and their supervisor, of what an AI agent is for in a research project and how it's permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, and treats the characteristic problems of AI use in research as the result of an agent working without a defined operating context.
The research harness: a one-page guide for doctoral researchers
A one-page reference guide for doctoral researchers and supervisors working with AI agents. Condenses the research harness framework into a practical quick-reference card: the seven components of a harness, what each one does, how to start building one, and what material form it takes.
The research harness: a framework for bounded AI use in doctoral work
Current responses to AI use in doctoral research locate the problem either with institutions through policy, or with students through judgement and AI literacy. This essay argues that neither response addresses the structural source of the difficulty. The characteristic problems of AI use in doctoral research are not problems of policy or capability; they are problems of working with an agent in the absence of a defined operating context. Drawing on software engineering practice, it develops the concept of the research harness: a structured specification, negotiated between researcher and supervisor, of what an AI agent is doing in a doctoral project. The harness has seven components — knowledge base, interpretive permissions, tools, authority, scope register, process record, and amendment protocol — and can be entered at a minimal level and developed iteratively alongside the work.
The research harness
A structured specification of an AI agent's operating context in doctoral research. The harness names seven components — knowledge base, interpretive permissions, tools, authority, scope register, process record, and amendment protocol — so that a researcher working with an AI agent stays the analyst, judge, and author of their own inquiry. Published as a preprint and a one-page guide, now developing into a tested intervention.
Making sense of AI in clinical practice: MACP webinar
An invited webinar for the Musculoskeletal Association of Chartered Physiotherapists. Explores what AI means for physiotherapy practice across the full information ecosystem of clinical work — from AI-assisted diagnosis and documentation to patient agency and the therapeutic relationship. The central concept is context sovereignty: AI systems work from professional context, and controlling that context is both the distinctive human contribution and the most practical skill for the AI age. The session covers the evidence for AI performance in clinical contexts, strategies for maintaining professional agency, how to actively support patients in using AI well, and how the therapeutic relationship is changing as practitioners and patients develop persistent AI agents.
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.
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.
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.
Harness engineering
Harness engineering is the practice of building the full architectural scaffolding within which AI agents operate — structured documentation they can reason with, constraints that enforce invariants, and feedback loops that let them know when they've succeeded. It is distinct from prompt engineering, which shapes individual tasks, and from oversight, which monitors outputs after the fact. The harness is the infrastructure that makes delegation coherent at scale.
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.
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.
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 rot
Context rot, also called context drift, is the way a language model's output gets worse as its context fills with drafts, dead ends, and its own earlier mistakes. What causes it, why a larger context window does not fix it, and how to manage it in long pieces of work.
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.
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.
Graph database
A graph database stores entities and the typed relationships between them, and is the storage layer behind a knowledge graph. For a programme team it can hold the curriculum map itself, so questions about how standards, outcomes, and assessments connect are answered by following the links instead of reading the handbooks.
MCP server
An MCP server is a small program that connects an AI assistant to one data source or service, such as a reference library, a folder of notes, or a calendar, through the Model Context Protocol. What the server offers sets the limit of what the assistant can see and do there.
Model Context Protocol
The Model Context Protocol (MCP) is an open standard for connecting AI applications to external data and tools through one common interface, in place of a custom integration for every pairing. It makes connections technically cleaner; whether they are wise ones is still a decision for the people who set them up.
System prompt
Instructions placed in front of every conversation with an AI model, setting how it behaves, what it knows, and what it won't do, usually without the user seeing them.
GraphRAG
GraphRAG combines knowledge graphs with retrieval-augmented generation. Where ordinary RAG returns the passages most similar to a question, GraphRAG extracts the entities and relationships in a document collection and answers by following the connections between them, which is what questions about critiques, influences, or curriculum coverage need.
Knowledge graph
How a knowledge graph differs from a vector database: it stores entities and the typed relationships between them, so AI can reason across connections.
Multi-hop reasoning
Multi-hop reasoning with knowledge graphs: how AI answers questions that take several steps, and why recorded relationships make each step checkable.
Context engineering
How context engineering differs from prompt engineering: building the knowledge and structure a language model needs to reason well about your work.
Context sovereignty
What is context sovereignty? The idea that people should own and author the context they bring to AI (their values, commitments, and ways of making sense of things) so that AI adapts to their thinking. How it differs from data sovereignty and model memory, its three principles, and what it means for students and educators.
Context sovereignty: building human-AI coalitions in physiotherapy
The Chartered Society of Physiotherapy's annual Founders' Lecture, arguing that the question facing the profession is not what AI can do that humans cannot, but how practitioners shape the context in which human-AI collaboration happens. The talk opens with the disorienting evidence that AI now matches or exceeds clinicians on diagnosis, empathy, and ethical reasoning, then rejects the defensive 'sanctuary strategies' this provokes. Its central idea is context sovereignty: because language models are stateless, static, and contextless, the professional context a practitioner brings is not a comfort but a structural necessity — and controlling it is the distinctive human contribution. It closes with the coming shift to patient context sovereignty and the work of meaning-making in an ambiguous moment.
Beyond document management: Graph infrastructure for professional education curricula
Professional curricula are extensively documented but not systematically queryable, creating artificial information scarcity that makes compliance reporting and quality assurance labour-intensive. This essay proposes a three-layer architecture — graph databases as the source of truth for curriculum structure, vector databases for semantic content retrieval, and a Model Context Protocol layer for stakeholder access — that transforms documentation into operational infrastructure. The architecture incorporates temporal versioning for longitudinal evidence, role-based access controls for multi-stakeholder environments, and internal quality audit against institutional policy alongside external regulatory compliance, enabling verification in hours rather than weeks.
Context sovereignty for AI-supported learning: A human-centred approach
This essay proposes 'context sovereignty' as a framework for maintaining human agency in AI-supported learning, arguing that context engineering — not just prompting — is the key to meaningful human-AI collaboration.