Autonomous knowledge curation and truth maintenance for agentic ontologies
What mechanisms exist, or are under active research, to enable Artificial Intelligence (AI) agents to autonomously curate which extracted knowledge is worth retaining in a long-term ontology, detect a…
Autonomous forgetting and information curation for long-term agent memory
How can Artificial Intelligence (AI) agents implement autonomous forgetting mechanisms and information-curation policies that preserve long-term memory utility while preventing retrieval quality, late…
Episodic-to-semantic memory consolidation architectures for agents
What architectures most effectively consolidate raw episodic traces into reusable semantic knowledge for Artificial Intelligence (AI) agents, and which triggers, review loops, and intermediate represe…
Migration trade-offs from vector Retrieval-Augmented Generation to…
What are the performance, cost, scalability, and practical trade-offs of migrating from traditional vector-based Retrieval-Augmented Generation (RAG) systems to ontology-backed Knowledge Graph Retriev…
What benefits, risks, and lifecycle costs of shadow Information Technology (IT)…
What benefits, risks, and lifecycle costs of shadow Information Technology (IT) and custom local tooling are documented, and which governance approaches successfully transition covert local solutions…
Plato's Forms and the 'Map Is Not the Territory'
What are the core tensions and possible symbiosis between Plato's claim that Forms are the truest reality and the modern semiotic claim that representations (maps, symbols, images) are not the territo…
Domain Emergence in Semantic Networks, Cognition, and Organizational Structure
How do dense semantic graph structures, attractor-like concept stabilization, and distributed ownership or interpretation jointly drive the emergence and persistence of conceptual domains in enterpris…
Similarity algorithms and growth policy for a file-based controlled theme…
Which similarity algorithms are appropriate for detecting near-synonym themes in a controlled vocabulary of 20–40 slug-based labels, and what growth policy prevents both vocabulary explosion and colla…
What capabilities, sub-capabilities, architectural patterns, and maturity…
What are the key capabilities, sub-capabilities, architectural patterns, and maturity dimensions for tool-using, semi-autonomous Semantic Knowledge Management (SKM) systems that integrate automated ha…
What is the most practical enterprise design for a five-pillar knowledge…synthesis
What capability architecture, control model, and operating system of work best implement a five-pillar agentic, meaning tool-using and semi-autonomous, Knowledge Management (KM) model for Artificial I…
What Institutional Designs Create Low-Cost Help-Seeking Without Embarrassment,…
Which institutional design choices create persistently low-cost help-seeking spaces where workers can ask questions, admit uncertainty, and seek guidance without expecting embarrassment, punishment, o…
How Do Formal Governance Structures Distort Cross-Department Knowledge Flows?
How do formal governance mechanisms such as hierarchy, reporting lines, and mandatory protocols reshape cross-department knowledge flow, and when do they unintentionally raise cross-department transac…
Which Network Structures Bottleneck or Accelerate Knowledge Flow?
Which social-network topologies, the recurring patterns of ties among people, concentrate
knowledge flow into fragile bottlenecks, and which topologies enable fast cross-boundary
transfer of tacit kno…
What Are the Micro-Transaction Costs of Internal Knowledge Sourcing?
What micro-transaction costs are borne by knowledge seekers and providers during internal peer-to-peer transfers, and how do these costs shift the choice between self-solving ("make") and help-seeking…
Why Do Trust-Based Institutions Outperform Incentive Schemes for Knowledge…
Why do explicit transactional incentives for sharing often decay or backfire, while trust-based institutions, stable rules and norms that make repeated sharing safe and expected, sustain lower long-ru…
How Do Asset Specificity and Information Asymmetry Block Knowledge Transfer?
How do highly specific expert knowledge assets, knowledge investments whose value depends heavily on a particular context or relationship, create information asymmetries, situations where experts know…
Datasets for measuring conversion from demand for local workaround tools to…
What public or internal datasets can validly measure the rate at which demand for local workaround tools, such as local apps, flows, lists, or spreadsheets, is converted into formal central Informatio…
LLM-First Policy Clarification and Institutional Knowledge Atrophy
How does shifting from peer policy clarification to Large Language Model (LLM)-first interaction affect institutional memory transfer, mentoring, and long-term policy expertise?
Kona and Aleph at their core, with Lean and unifying concepts
What are Kona and Aleph at their core, what do they each do in practice, how does Lean (the theorem prover) relate to them, and which unifying concepts explain where they overlap and differ?
Microsoft Copilot Studio
What is the complete set of features, functions, and capabilities offered by Microsoft Copilot Studio, and how do those capabilities support enterprise-grade Artificial Intelligence (AI) agent develop…
Temporary Automation Demand Persistence and Core Capability Investment…
What evidence exists that temporary automation workarounds displace investment in core software delivery, and what is the observed persistence rate of those workarounds after the underlying systems ca…
Universal Entity Lifecycle Governance Framework (UELGF) 8-layer organisational…
What is the most suitable knowledge representation architecture for evolving the Universal Entity Lifecycle Governance Framework (UELGF) 8-layer organisational context model from static classification…
Ontology landscape for curated lexical and structured enterprise context
For a curated corpus that mixes lexical documents, structured artifacts, application programming interface (API) landscapes, access controls, infrastructure definitions, schemas, and process documenta…
Project-Based Demand Governance With Product-Structured IT Teams
What failure modes have been empirically observed in organisations where demand is managed through a project-based model while information technology (IT) teams are structured and operated as product…
Customer-Segment Demand Prioritisation Against Domain-Based IT Teams
What failure modes have been empirically observed when organisations prioritise information technology (IT) work through customer segments, for example consumer, enterprise, or government cohorts, but…
Overlapping and Absent Accountability at Strategic and IT Layers
What failure modes have been empirically observed in organisations where accountability is either overlapping, two or more parties hold the same accountability, or absent, no party owns a given area,…
Graph database landscape
For the hosted graph database platforms identified in the 2026 Software-as-a-Service (SaaS) knowledge-ontology research, Neo4j AuraDB, Amazon Neptune, Stardog Cloud, Ontotext GraphDB, and Memgraph Clo…
Web ontologies in production Knowledge Graphs for multi-step Artificial…
How should web ontologies, Resource Description Framework (RDF), Web Ontology Language (OWL), RDF Schema (RDFS), Simple Knowledge Organization System (SKOS), and Schema.org, be selected, composed, and…
Knowledge Graph lifecycle management for multi-step software agents
What are the best practices for maintaining and evolving a Knowledge Graph (KG), a structured graph of entities and relationships, that serves multi-step software agents, covering schema versioning, e…
Data product ontology
What is the data product ontology, which organisations and communities use it, how is it applied in practice within data mesh and data management architectures, and is it still current relative to com…
Hosted Software-as-a-Service (SaaS) graph database options for knowledge…
Which hosted Software-as-a-Service (SaaS) graph database platforms are suitable for building and querying a knowledge ontology, and how do they compare on data model support, query language, pricing,…
Control Objectives for Information and Related Technologies (COBIT) and…
What minimum process-definition conditions do COBIT 2019 and CMMI require before mitigation of workforce-process risk can be considered effective and sustainable?
What systematic review methodologies and Artificial Intelligence (AI)-assisted…
What systematic review methodologies, Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA), Cochrane review, narrative synthesis, meta-ethnography, and realist synthesis, and wh…
What structured approaches and Artificial Intelligence (AI) agent workflow…
What structured approaches, from academic writing pedagogy, Artificial Intelligence (AI)-assisted writing tools, and agent workflow design, exist for converting synthesised research findings into poli…
What are the established norms from academic pre-print repositories and…
What are the established norms and practical conventions from academic pre-print repositories (arXiv, Social Science Research Network (SSRN), Open Science Framework (OSF)) and Personal Knowledge Manag…
What structured knowledge-gap tracking and automatic backlog-promotion patterns…
What structured knowledge-gap tracking and automatic backlog-promotion patterns exist in Personal Knowledge Management (PKM) systems (linked-note methods such as Zettelkasten, Obsidian, Roam Research,…
Ubiquitous Language in Artificial Intelligence (AI)-augmented development
How significantly does maintaining a living Ubiquitous Language (UL), in the Domain-Driven Design (DDD) sense of a shared, precise domain vocabulary used consistently in both code and conversation, im…
How do academic and scientific publishing systems handle post-publication…
How do established academic and scientific publishing systems (journal publishers, preprint servers, living review platforms) handle post-publication corrections, amendments, retractions, and formal c…
Governance-as-moat thesis and prior research implications
How does the thesis advanced in the April 2026 Liam Hyland and Leonis Capital ServiceNow analysis, that governance is the durable, non-replicable value layer in AI-augmented enterprise technology stac…
Permission-safe Retrieval-Augmented Generation (RAG) in enterprise information…
What are the technical constraints on permission-safe Retrieval-Augmented Generation (RAG) in an enterprise information architecture with incoherent access controls, collaboration groups created ad ho…
What is Microsoft 365 Copilot Cowork and what are its enterprise governance…
What is Microsoft 365 (M365) Copilot Cowork, how does it technically differ from custom Microsoft Copilot Skills, and what are the governance, legal, and shadow Information Technology (IT) risks it in…
Knowledge curation governance as an enterprise AI capability in regulated…
What operational models exist for governing authoritative knowledge as a managed enterprise capability for Artificial Intelligence (AI) consumption in regulated financial institutions, covering domain…
Recall competitive landscape and clone feasibility
What core capabilities does Recall provide, who else is building similar products (including projects in the davidamitchell GitHub organization and relevant open-source tools), what components can we…
Harness-level selection and use of tools, agents, skills, prompts, and…
When should teams choose tools, agent definition files, skills, prompts, instruction files, and AGENTS.md, and what verifiable best practices align with how major harnesses actually select and apply e…
Artificial Intelligence (AI)-assisted daily productivity digest
What are the established patterns and tooling approaches for using Artificial Intelligence (AI) to generate actionable daily and weekly productivity digests from personal task management systems?
Sup…
The Unknowability of the Universe
What does JB Manchak's treatment of General Relativity (GR) and Zen Buddhism reveal about the epistemological limits of human knowledge: specifically, is the universe fundamentally unknowable, and if…
The role of AGENTS.md in a repo using .github/copilot-instructions.md as the…
`AGENTS.md` has emerged as the cross-tool convergence format for agent project instructions, supported by OpenAI Codex, GitHub Copilot, Claude Code, Cursor, Aider, Gemini Command Line Interface (CLI),…
Agent instruction loading and skills access
Given the current repo setup -- instructions in `.github/copilot-instructions.md`, skills submodule at `.github/skills/`, no `AGENTS.md` at root, no `CLAUDE.md` at root -- what does each agent actuall…
The measurement asymmetry
Why is measuring opportunity cost systematically harder than measuring direct costs, and what cognitive and structural mechanisms cause organisations to destroy value while claiming efficiency gains?
Customer contact as strategic signal
When customers contact a business, what are they actually seeking — and how should organisations decide between self-service automation and human interaction to maximise long-term customer value?
Against bureaucracy: dismantling control systems to focus on value and…
What does the synthesis of the Anti-Bureaucracy Manifesto and James Burnham's *The Managerial Revolution* reveal about how organisations can dismantle control systems and system waste while refocusing…
Bureaucracy growth and the boomer generation hypothesis
Who has written or researched the idea that the growth of bureaucratic functions — specifically Human Resources (HR), Finance, and Procurement — was led or significantly amplified by the baby boomer g…
How to best use awesome-copilot in this repo and across personal repos
What resources from `davidamitchell/awesome-copilot` — GitHub Copilot (GHC) instructions, skills, agents, workflows, hooks, and plugins — provide the most leverage when applied to this Research repo a…
Code Architecture Inspection Across Repositories
What practical implementation approaches exist for automatically inspecting and understanding how a set of repositories is architected, how they relate to and couple with each other, and whether they…
Tracking How Work Travels Across Organisational Systems
Can we track how a unit of 'Work' -- an idea or concept -- travels across organisational systems (SharePoint, Confluence, Azure DevOps (ADO)/Jira, Git, monitoring systems, and data platforms), and wha…
Coding AI Agent Skills Survey
What actively maintained, publicly available agent skills, prompt libraries, instructions files, and system prompts exist — from vendors such as Microsoft and from the Open Source Software (OSS) commu…
Technology Capability Models
What established and emerging IT capability models define a complete, multi-level set of technical capabilities - such as authentication, networking, Application Programming Interface (API) gateways,…
Dependency Mapping Across .NET Codebases, Terraform, Dynatrace, Confluence, Log…
What practical tools and methodologies are being used to map dependencies across .NET codebases, Terraform configurations, Dynatrace Application Performance Management (APM) monitoring, and solution d…
Layered Organisation Large Language Model
Is it technically feasible and economically viable for an organisation to build a customised Large Language Model (LLM) layer that injects and optimises over organisation-specific context - internal k…
Explore to exploit: the synthesis step that makes exploitation pay off
When technology is moving fast, what is the synthesis step between exploration and exploitation, why is it so commonly skipped, what are the costs of skipping it, and what strategies allow organisatio…
Artificial Intelligence (AI) Memory Systems
What is the current state of Artificial Intelligence (AI) memory systems — across Retrieval-Augmented Generation (RAG) research, commercial AI vendor implementations (GitHub Copilot, Gemini, Claude, a…
Trusting Trust and AI Corpus Contamination
Ken Thompson's "Trusting Trust" argument shows that you cannot verify a compiler by reading its source code if the compiler was compiled by a compromised toolchain — the contamination lives in the bin…
Aligned Decision-Making
What framework should an organisation adopt to ensure that AI agents making or supporting decisions have access to the right layered organisational context — spanning regulatory boundaries, values and…
Latent Concept Extraction from Confluence
What are the best approaches for extracting latent concepts from a Confluence wiki, representing them as word embeddings in a vector database (VDB) and as a knowledge graph (KG), and how can the resul…
Context Compression and RAG Techniques for Organisational Knowledge
What are the current best practices and bleeding-edge techniques - including Retrieval-Augmented Generation (RAG), context compression, and context architecture - for selectively surfacing the rig…
Ricardian Contract model
What is the Ricardian Contract model proposed by Ian Grigg in 1996, how has it evolved over the past three decades, who is actively building with it today, and what does the latest academic and applie…
Can organisational intent be expressed as a formally structured specification…
Can organisational intent — mission, values, strategy, resource allocation — be expressed as a formally structured specification from which human-readable artefacts are derived, and against which Obje…
Exploration-synthesis gap
During periods of rapid exploration — such as the current wave of Artificial Intelligence (AI) / Large Language Model (LLM) adoption inside organisations — individuals and teams routinely duplicate ef…
The DIKW pyramid: transformation functions from data to information to…
What are the transformation functions that move between the levels of the DIKW pyramid — Data → Information → Knowledge → Wisdom? What cognitive, computational, and organisational mechanisms perform e…
YouTube transcripts via third-party transcript APIs (AssemblyAI / Supadata)
Can a third-party transcript API (AssemblyAI, Supadata, Kagi, or similar) retrieve YouTube
transcripts from a GitHub Actions runner, bypassing YouTube's IP-based block on the
internal transcript endpo…
Interface and delivery
Once research is complete and outputs are produced, how should they be surfaced and delivered to the people (or agents) who need them? What interfaces make research outputs most usable?
Telegram bot as mobile memory capture and retrieval channel
Can a Telegram bot serve as a low-friction mobile capture and retrieval surface for the Memory-System? Specifically: (a) message received → file written to GitHub repo via API, (b) messages starting w…
Slack as a mobile memory capture and retrieval channel
Can a Slack bot in a personal or team workspace serve as a memory capture and retrieval surface? What is the minimum viable setup: slash command vs bot, incoming webhook vs Socket Mode, and does a fre…
Better Business Cases
What is the Better Business Cases (BBC) Five Case Model framework, what are the requirements and standards for each of the five cases, and how should an AI agent apply this framework to author, review…
ServiceNow Process Mapping
What options exist within ServiceNow for documenting, mapping, and maintaining business and IT processes — and which approaches are sustainable enough in practice to stay meaningful, current, and actu…
ServiceNow AI: Knowledge Management, RAG Pipelines, and Agent Frameworks
How is ServiceNow evolving its platform to support AI-powered knowledge management, retrieval-augmented generation (RAG), and agent frameworks — and what should an organisation investing in ServiceNow…
Emergent Patterns in Software Engineering Prompts and SDLC Guidance
What are the current and emergent best practices for crafting AI agent prompts and tooling guidance tailored to each phase of the Software Development Life Cycle (SDLC) — covering discovery, requireme…
iOS Shortcuts + GitHub API
Can an iOS Shortcut write a timestamped `.md` file directly to a GitHub repo via the Contents API (`PUT /repos/{owner}/{repo}/contents/{path}`) with a stored Personal Access Token (PAT), with enough r…
Inbox folder pattern
Does removing the folder-selection decision from the capture path meaningfully reduce friction? Design and evaluate an `inbox/` folder pattern where: (a) any capture tool writes unstructured notes to…
Slack and MS Teams integration for research delivery and capture
What is the most practical way to integrate the research corpus with Slack and/or Microsoft Teams — for both outbound delivery (notifying when new research is completed) and inbound capture (receiving…
Coverage gaps in automated research review skills, peer review patterns for…
What review methodology is required to reliably move from information gathering through to applied knowledge and wisdom — and which of those steps can be automated in a CI pipeline versus requiring hu…
iOS Shortcuts for research capture and query
What iOS Shortcuts workflows provide the most value for a personal research system hosted on GitHub — covering both low-friction research capture (adding a URL or idea to the backlog from anywhere on…
An Integrative Framework for Agent Decision-Making
How can the DIKW (Data → Information → Knowledge → Wisdom) progression be operationalised within agentic systems to produce intent-aligned, context-aware decisions that reconcile conflicting knowledge…
Conversational and chat interface for querying the research corpus
What is the best approach to expose the `Research/completed/` corpus as a queryable, conversational interface — so that a user (or an AI agent) can ask "what do I know about X?" and receive a grounded…
YouTube transcripts via yt-dlp audio + Whisper transcription
Can we bypass YouTube's IP-based transcript block by downloading the **audio track** with
`yt-dlp` (a different endpoint from the transcript API) and then transcribing it with
OpenAI Whisper?
YouTube transcripts via Gemini API (native YouTube URL support)
Can we use the Gemini API (already configured in `davidamitchell/Latest-developments-`) to
extract full transcripts from YouTube videos without being blocked by YouTube's IP restrictions?
Exploit versus explore Artificial Intelligence (AI) investment classification
How should organisations distinguish between exploitation and exploration AI investments in practice, and what diagnostic criteria and portfolio tools enable that distinction to be applied at budget a…
Sources of research: what to monitor and how
What are the best sources for AI/ML research, and what is the right monitoring strategy for each — RSS, YouTube channels, arXiv, newsletters, GitHub?
Research output types
What are the possible output types from a research item, and how should each type be handled, stored, and acted upon?
Local index vs reference
For each type of research content, should we store a local copy / index, or just maintain a reference (URL, citation)? What are the right trade-offs between storage cost, offline access, durability, a…
Research agenda curation
How should the research backlog be maintained and prioritised to ensure balanced coverage of important domains, detect over-concentration in one area (research drift), and surface high-value gaps — ra…
Knowledge retention: mechanisms for ensuring completed research is recalled and…
What mechanisms ensure that knowledge from completed research items is retained, recalled when contextually relevant, and applied to decisions — rather than being archived indefinitely with no re-enga…
Knowledge Representation for Agent Context
What techniques — latent semantic extraction, knowledge graphs, concept maps, hierarchical document compression, and layered abstraction — most effectively represent and compress large knowledge corpo…
Knowledge linking: building a connected research corpus via explicit…
What is the minimum viable approach to making the `Research/completed/` corpus a connected knowledge network — where items explicitly reference related items, contradictions and confirmations are surf…
YouTube transcript fetcher for research
Can we port the YouTube transcript fetcher from `davidamitchell/Latest-developments-` to this repo and adapt it for research use (bulk fetch, save transcripts, not just email digest)?
Transaction Cost Economics
What are the foundational concepts of transaction cost economics (Coase → Williamson → North → Ostrom), and how might the analytical framework map onto software engineering organisation, AI agent desi…
Agent Memory Management and Context Injection
What is the current state of agent memory management systems — beyond RAG — and which approaches best address the real constraints of latency, knowledge freshness, scoping, governance, quality, and di…
GitHub wiki for research content
What is the best approach for publishing completed research items from `Research/completed/` into the GitHub wiki, and what tooling is needed to keep it current and readable?
Simple process for adding a research item
What is the minimum-friction workflow for adding a new research item so that good ideas get captured before they are lost?
Keeping research backlog separate from repo improvement backlog
What is the cleanest way to separate two distinct types of work — *what to research* vs *how to improve this repo* — so that neither overwhelms the other and each can be prioritised independently?
Information synthesis
What is the best way to synthesise information from multiple sources in a manner that is minimally lossy — preserving the most signal while compressing volume — drawing on information theory, entropy,…
Indexing and tracking method for research content
What is the best method for indexing and tracking research content (transcripts, papers, notes) given the constraints of a git-based, local-first repo?