Research library
Original and synthesis-led papers that develop a question, theory, model, or framework through traceable evidence and explicit reasoning.
Publication standard
A substantive paper must make its proposition, evidence, reasoning, scope, and limitations visible, and be substantial enough for another person or agent to test, cite, or reuse.
What stays in Writing: Essays, commentary, briefings, guides, playbooks, event notes, news reactions, and shortened companions remain available in Writing, even when they are well sourced.
Start here when agents and people need shared terms for requests, commitments, evidence and handoffs, not just more conversation.
A research paper proposing agentic language as a common operating layer for humans and agents: shared business terms, Agent Moves, Meaning Blocks, receipts, judgement, human-care signals, and pattern promotion.
Use this to distinguish a decision people have tested and can support from agreement produced by pressure or silence.
A research paper proposing consensus as a disciplined process of conviction, evidence, listening, challenge, adaptation, and commitment, then translating that human governance model into agentic systems.
Explore a connected operating model for agent roles, memory, judgement and handoffs, with authority kept explicit.
A research paper proposing Woodlands Agentic Theory as a practical theology and operating model for how agentic workers coordinate, hand off, judge, remember, and work safely inside companies.
Consider what people need to understand and challenge AI-mediated information, and why education matters beyond learning to prompt.
A research paper mapping where education systems are failing to teach citizens how to comprehend information, judge evidence, and act responsibly in an AI-mediated public sphere.
Use this when designing how an agent notices an exception, routes attention and requests review without treating signals as feelings.
A research paper proposing triggers as a practical signal language for long-running agents, helping systems route attention, constrain action, create reviewable memory, and learn from exceptions without hoarding noise.
Separate evidence, human impact and warning signals from the authority to decide, so an agent's judgement can be inspected.
A research paper setting out Head / Heart / Gut / Spine as a practical judgement grammar for long-running agents, separating evidence, human impact, anomaly sensing, authority, and purpose.
Read this before connecting more memory: it asks which source is authoritative, what is stale and what context an agent may use.
A research paper proposing Woodlands as a practical model for connected memory across native systems, source authority, boundaries, ageing, calibrated judgement, and agentic context.
This is the deep version for teams designing long-lived agentic employees and needing shared language across crews, memory, intent, tools, and governance.
A white paper exploring how the architecture of agentic employees – crews, flows, intent, memory, and style – reflects the core functions of human cognition. Drawing on neuroscience and AI research, it offers a shared vocabulary for building adaptive, persistent, and trustworthy agentic systems.
Read this if you are thinking about always-on agents and need a clearer split between exploration, integration, and action.
A practitioner-led proposal separating exploration, integration and action in continuously operating agentic systems.
This one is for agent memory design: how surprise, shame, curiosity, and distrust can become signals for what an agent should remember.
As agentic artificial intelligence systems transition from episodic task execution to continuous operation, the design of memory becomes a critical and under-examined challenge. Prevailing approaches treat memory as an accumulation problem, prioritising exhaus
Privacy choice
Cookieless Matomo analytics help me understand which public pages are useful. They are on by default unless you turn them off, and your choice never affects access to the site.