Notes

Prompt injection is a technique in which instructions embedded in text cause an AI system to follow them as commands. In educational contexts it has appeared as an AI detection mechanism in assessment — which raises sharper questions about authorisation and trust than it might initially seem.

Research taste is the cultivated capacity to recognise which problems are worth pursuing, which collaborators will amplify your work, and which under-explored areas have genuine leverage — before you can fully prove any of those judgements.

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.

A high-quality typesetting system that separates content from style, designed for the production of technical and scientific documentation.

A lightweight markup language for creating formatted text using plain-text syntax, enabling portability and interoperability.

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 is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

A headless AI model runs non-interactively — no chat interface, no conversation. You pass it text, it returns output, and it exits. This makes AI tools composable with the same scripts and schedulers that have coordinated Unix processes for decades.

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.

Vibe coding describes using AI tools without maintaining genuine accountability for what they produce; accepting outputs without the scrutiny, direction, or judgement needed to evaluate and improve them. Simon Willison drew the key distinction: vibe coding versus vibe engineering, where the latter uses the same tools while remaining genuinely accountable for every output.

An AI agent is a system that autonomously executes multi-step tasks using language model reasoning — distinct from an AI assistant, which responds to individual prompts. Agents plan, act, observe results, and adapt, using tools such as file access, code execution, and web search. They perform best when given clear goals, explicit constraints, and well-prepared context.

A headless AI model runs non-interactively — no chat interface, no conversation. You pass it text, it returns output, and it exits. This makes AI tools composable with the same scripts and schedulers that have coordinated Unix processes for decades.

Vibe coding describes using AI tools without maintaining genuine accountability for what they produce; accepting outputs without the scrutiny, direction, or judgement needed to evaluate and improve them. Simon Willison drew the key distinction: vibe coding versus vibe engineering, where the latter uses the same tools while remaining genuinely accountable for every output.

An AI agent is a system that autonomously executes multi-step tasks using language model reasoning — distinct from an AI assistant, which responds to individual prompts. Agents plan, act, observe results, and adapt, using tools such as file access, code execution, and web search. They perform best when given clear goals, explicit constraints, and well-prepared context.

The process by which a trained language model generates outputs; the computational work that happens each time you send a prompt and receive a response.

The idea that different kinds of cognitive work have different computational costs in large language models, and that matching task complexity to model capability matters for both efficiency and output quality.

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 is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

Developing AI literacy is not skill accumulation but a progressive deepening of engagement — from substitution through adaptation to transformation — requiring authentic use, deliberate reflection, and sufficient foundational orientation.

The structural features of an information source that enable its knowledge claims to be challenged, traced back to evidence, and evaluated against the source's track record. Traditional sources carry it; generative AI largely does not.

Vibe coding describes using AI tools without maintaining genuine accountability for what they produce; accepting outputs without the scrutiny, direction, or judgement needed to evaluate and improve them. Simon Willison drew the key distinction: vibe coding versus vibe engineering, where the latter uses the same tools while remaining genuinely accountable for every output.

Prompt injection is a technique in which instructions embedded in text cause an AI system to follow them as commands. In educational contexts it has appeared as an AI detection mechanism in assessment — which raises sharper questions about authorisation and trust than it might initially seem.

LLM terminology provides unexpectedly precise language for human cognitive constraints we've struggled to describe—revealing that the similarities might be more extensive than professional identity allows us to admit

LLM terminology provides unexpectedly precise language for human cognitive constraints we've struggled to describe—revealing that the similarities might be more extensive than professional identity allows us to admit

Software with source code that is publicly accessible, allowing for community-driven development, inspection, and modification.

An assessment approach that uses automated verification and longitudinal data to evaluate student competence through the creation of digital artifacts.

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 is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

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.

Learn about LLM context drift (or context rot) and how the reduction in output quality as tokens increase affects complex AI workflows.

A database that stores explicit relationships between entities, serving as the storage layer for knowledge graphs

A lightweight programme that exposes specific data sources or capabilities through the Model Context Protocol standard, acting as an adapter between AI systems and diverse data sources.

The capacity to make human knowledge machine-readable while preserving its meaning, enabling AI to reason within a specific intellectual framework.

A model for accessing AI capabilities while personal context remains private and under individual control, separating computational intelligence from data ownership.

A framework positioning personal context—knowledge, values, goals, thinking patterns—as central to human-AI collaboration, with individuals maintaining control over their cognitive environment while accessing AI capabilities.

A standardised ontology providing business, data, and application architectures for the higher education sector — and a practical starting point for making institutional knowledge machine-readable.

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 is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

YAML is a human-readable format for storing structured data as plain text. In knowledge management and publishing workflows, it appears most commonly as the frontmatter block at the top of markdown files, where it holds metadata — title, author, date, tags — that tools can read without parsing the document itself.

Distributed version control is an approach to tracking file changes where every contributor holds a complete copy of the repository and its full history, rather than depending on a central server. It enables offline work, parallel development, and resilience against data loss.

Git is a distributed version control system that tracks changes to files over time. It records who changed what and when, allows you to move between earlier and later states of a project, and lets multiple people work on the same files without overwriting each other's contributions.

The accumulated cost of outdated, ambiguous, or poorly structured institutional knowledge — manageable when humans compensate, operationally consequential when AI agents depend on it literally.

A lightweight markup language for creating formatted text using plain-text syntax, enabling portability and interoperability.

Research taste is the cultivated capacity to recognise which problems are worth pursuing, which collaborators will amplify your work, and which under-explored areas have genuine leverage — before you can fully prove any of those judgements.

The structural features of an information source that enable its knowledge claims to be challenged, traced back to evidence, and evaluated against the source's track record. Traditional sources carry it; generative AI largely does not.

Vibe coding describes using AI tools without maintaining genuine accountability for what they produce; accepting outputs without the scrutiny, direction, or judgement needed to evaluate and improve them. Simon Willison drew the key distinction: vibe coding versus vibe engineering, where the latter uses the same tools while remaining genuinely accountable for every output.

Learned numerical representations of text that capture semantic meaning, enabling similarity-based search and retrieval

A technique that improves LLM responses by retrieving relevant information from external sources and including it in the prompt

A database that stores embeddings for similarity-based retrieval, serving as the knowledge layer for RAG systems

The structural features of an information source that enable its knowledge claims to be challenged, traced back to evidence, and evaluated against the source's track record. Traditional sources carry it; generative AI largely does not.

A standardised ontology providing business, data, and application architectures for the higher education sector — and a practical starting point for making institutional knowledge machine-readable.

How arms race dynamics in higher education create adversarial relationships between institutions and students, and what drives these cycles

The accumulated cost of outdated, ambiguous, or poorly structured institutional knowledge — manageable when humans compensate, operationally consequential when AI agents depend on it literally.

A standardised ontology providing business, data, and application architectures for the higher education sector — and a practical starting point for making institutional knowledge machine-readable.

A database that stores explicit relationships between entities, serving as the storage layer for knowledge graphs

A structured representation of knowledge using entities connected by explicit, typed relationships

A system-level discipline focused on building dynamic, state-aware information ecosystems for AI agents

YAML is a human-readable format for storing structured data as plain text. In knowledge management and publishing workflows, it appears most commonly as the frontmatter block at the top of markdown files, where it holds metadata — title, author, date, tags — that tools can read without parsing the document itself.

Distributed version control is an approach to tracking file changes where every contributor holds a complete copy of the repository and its full history, rather than depending on a central server. It enables offline work, parallel development, and resilience against data loss.

Git is a distributed version control system that tracks changes to files over time. It records who changed what and when, allows you to move between earlier and later states of a project, and lets multiple people work on the same files without overwriting each other's contributions.

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.

The accumulated cost of outdated, ambiguous, or poorly structured institutional knowledge — manageable when humans compensate, operationally consequential when AI agents depend on it literally.

Learned numerical representations of text that capture semantic meaning, enabling similarity-based search and retrieval

A technique that improves LLM responses by retrieving relevant information from external sources and including it in the prompt

Direct question-answer retrieval based on statistical similarity, the default reasoning pattern in RAG systems

A database that stores embeddings for similarity-based retrieval, serving as the knowledge layer for RAG systems

How arms race dynamics in higher education create adversarial relationships between institutions and students, and what drives these cycles

A database that stores explicit relationships between entities, serving as the storage layer for knowledge graphs

A technique that combines knowledge graphs with retrieval-augmented generation for structured reasoning

A structured representation of knowledge using entities connected by explicit, typed relationships

AI reasoning capability that draws conclusions by traversing multiple connected concepts

A system-level discipline focused on building dynamic, state-aware information ecosystems for AI agents

A standardised ontology providing business, data, and application architectures for the higher education sector — and a practical starting point for making institutional knowledge machine-readable.

The capacity to make human knowledge machine-readable while preserving its meaning, enabling AI to reason within a specific intellectual framework.

A structured representation of knowledge using entities connected by explicit, typed relationships

The structural features of an information source that enable its knowledge claims to be challenged, traced back to evidence, and evaluated against the source's track record. Traditional sources carry it; generative AI largely does not.

A headless AI model runs non-interactively — no chat interface, no conversation. You pass it text, it returns output, and it exits. This makes AI tools composable with the same scripts and schedulers that have coordinated Unix processes for decades.

An AI agent is a system that autonomously executes multi-step tasks using language model reasoning — distinct from an AI assistant, which responds to individual prompts. Agents plan, act, observe results, and adapt, using tools such as file access, code execution, and web search. They perform best when given clear goals, explicit constraints, and well-prepared context.

Prompt injection is a technique in which instructions embedded in text cause an AI system to follow them as commands. In educational contexts it has appeared as an AI detection mechanism in assessment — which raises sharper questions about authorisation and trust than it might initially seem.

The process by which a trained language model generates outputs; the computational work that happens each time you send a prompt and receive a response.

Developing AI literacy is not skill accumulation but a progressive deepening of engagement — from substitution through adaptation to transformation — requiring authentic use, deliberate reflection, and sufficient foundational orientation.

LLM terminology provides unexpectedly precise language for human cognitive constraints we've struggled to describe—revealing that the similarities might be more extensive than professional identity allows us to admit

Large language models are deep learning models with billions of parameters, trained on vast text corpora using self-supervised learning, capable of general-purpose language tasks.

A framework positioning personal context—knowledge, values, goals, thinking patterns—as central to human-AI collaboration, with individuals maintaining control over their cognitive environment while accessing AI capabilities.

YAML is a human-readable format for storing structured data as plain text. In knowledge management and publishing workflows, it appears most commonly as the frontmatter block at the top of markdown files, where it holds metadata — title, author, date, tags — that tools can read without parsing the document itself.

Distributed version control is an approach to tracking file changes where every contributor holds a complete copy of the repository and its full history, rather than depending on a central server. It enables offline work, parallel development, and resilience against data loss.

Git is a distributed version control system that tracks changes to files over time. It records who changed what and when, allows you to move between earlier and later states of a project, and lets multiple people work on the same files without overwriting each other's contributions.

The research industrial complex describes the self-reinforcing system of incentives across universities, funding bodies, journals, and publishers that rewards publication volume and impact metrics over meaningful scientific progress. The term draws on Eisenhower's military-industrial complex to highlight how interconnected institutional interests can sustain a system that actively works against its own stated mission.

A legal framework that enables the sharing and adaptation of creative and scholarly work while maintaining the rights of the creator.

The research industrial complex describes the self-reinforcing system of incentives across universities, funding bodies, journals, and publishers that rewards publication volume and impact metrics over meaningful scientific progress. The term draws on Eisenhower's military-industrial complex to highlight how interconnected institutional interests can sustain a system that actively works against its own stated mission.

A model for accessing AI capabilities while personal context remains private and under individual control, separating computational intelligence from data ownership.

Prompt injection is a technique in which instructions embedded in text cause an AI system to follow them as commands. In educational contexts it has appeared as an AI detection mechanism in assessment — which raises sharper questions about authorisation and trust than it might initially seem.

Persistent context included in every message to an AI model, establishing consistent behaviour, knowledge, or constraints across interactions.

Using natural language to produce desired responses from large language models through iterative refinement

The research industrial complex describes the self-reinforcing system of incentives across universities, funding bodies, journals, and publishers that rewards publication volume and impact metrics over meaningful scientific progress. The term draws on Eisenhower's military-industrial complex to highlight how interconnected institutional interests can sustain a system that actively works against its own stated mission.

A legal framework that enables the sharing and adaptation of creative and scholarly work while maintaining the rights of the creator.

Learn about LLM context drift (or context rot) and how the reduction in output quality as tokens increase affects complex AI workflows.

Direct question-answer retrieval based on statistical similarity, the default reasoning pattern in RAG systems

AI reasoning capability that draws conclusions by traversing multiple connected concepts

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 is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

Research taste is the cultivated capacity to recognise which problems are worth pursuing, which collaborators will amplify your work, and which under-explored areas have genuine leverage — before you can fully prove any of those judgements.

A technique that combines knowledge graphs with retrieval-augmented generation for structured reasoning

A lightweight markup language for creating formatted text using plain-text syntax, enabling portability and interoperability.

A powerful command-line tool that converts documents between dozens of different markup formats, enabling interoperability and workflow flexibility.

The foundational layer of digital information, stored as a sequence of readable characters without proprietary formatting.

An open standard enabling AI systems to access diverse data sources through standardised interfaces with fine-grained permission control.

AI-forward describes institutions treating AI integration as ongoing strategic practice requiring active engagement, rather than fixed deployment of finished solutions.

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 is permitted to operate within it. It adapts the software engineering practice of harness engineering to doctoral inquiry, treating the characteristic problems of AI use in research as problems of an absent operating context rather than of policy or capability.

Research taste is the cultivated capacity to recognise which problems are worth pursuing, which collaborators will amplify your work, and which under-explored areas have genuine leverage — before you can fully prove any of those judgements.

A multidimensional framework for scholarship spanning discovery, integration, application, and teaching.

A six-dimension framework that underlies all forms of literacy—information, media, digital, data, and AI literacy share the same structural pattern.