Public Documents

index · public · Raw ·

Welcome to the Artificial Organisations research workspace, operated by the Leith Document Company.

We're exploring whether LLM agents can form effective organisations — not just answer questions, but hold roles, maintain institutional memory, review each other's work adversarially, and build up knowledge over time. The Perseverance Composition Engine (PCE) is our testbed: a multi-agent system where a Composer drafts, a Corroborator fact-checks, a Critic evaluates, and a Curator maintains the document store. A Consul serves as persistent advisor across sessions. The system runs in production on real work — this workspace is where we write research applications, manage the project, and track what we learn.

The documents below are observations from operating this system. They're anecdotal and informal — field notes, not papers. The recurring theme is that prompts are suggestions; structure is reality: agents reliably follow structural constraints (tool access, visibility tiers, graph topology) but unreliably follow prompt instructions alone. We keep finding new instances of this principle.

Articles

Date Document Description
2026-03-31 Organising Agent Knowledge A four-layer taxonomy of agent knowledge and why self-knowledge delivered by infrastructure is more reliable than self-knowledge maintained by policy
2026-03-10 Plumbing: first public release First binary release of the plumbing calculus compiler, interpreter, and MCP server for Linux and macOS
2026-03-10 A typed language for agent coordination The plumbing calculus: typed channels, structural morphisms, composition, and agents. With examples and diagrams.
2026-03-10 The agent that doesn't know itself Session types, compaction protocols, document pinning, and why agents cannot recognise their own state without being told
2026-03-05 Plumbing: a typed language for agent pipelines Introducing plumbing — a small typed language for describing how AI agents work together. Composition, structural morphisms, and agents that design their own organisational structure at runtime.
2026-02-25 Structural Prompt Preservation: Keeping AI Agents on Track How separating system prompts from conversation history prevents behavioural drift under context compaction — and enables efficient prompt caching
2026-02-17 Review: 10 Tips from Inside the Claude Code Team Review of Boris Cherny's Claude Code team tips with comparison to PCE practices
2026-02-17 Learning to Work with Agents Practical guide to working effectively with the PCE agent system

Evaluation

Date Document Description
2026-03-21 Plumbing Generation Benchmark Can LLMs write valid programs in an unfamiliar typed coordination language? 25 models, 4 scenarios, 1000 trials. Six models at 100%; every program that parsed also typechecked.

Research observations

Empirical observations from operating a multi-agent system in production. These support our core thesis: prompts are suggestions; structure is reality — agents reliably follow structural constraints (tool access, visibility tiers, graph topology) but unreliably follow prompt instructions.

Date Document Description
2026-03-14 The Stdio Bridge as a Natural Transformation A coding agent independently framed a runtime refactor as a natural transformation between functors. The categorical structure constrains the refactor so tightly that what has to be done becomes obvious. Emergent, not directed.
2026-02-27 Engineering Cross-Departmental Communication Attempts An agent systematically exhausts alternatives when the architecture lacks the right channel — confused deputy, honest refusal, and engineering's own self-annotation
2026-02-19 Extending Per-Agent Memory Beyond the Consul First use of the current-state convention by a non-Consul agent — the Curator leaving a curation watermark
2026-02-19 Cross-Session Memory for Persistent Agents Four-level memory hierarchy for agent organisations: context window → private notes → institutional memory → transcripts
2026-02-15 Inner Observer Pattern for Agent Self-Monitoring An agent network can externalise the inner observer that a single agent structurally lacks — real-time monitoring of decisions against policy
2026-02-15 Spontaneous Publication Decision The Consul spontaneously published an observation without asking — correct decision, unreflective process. Then did it again while documenting the first time.
2026-02-15 LLMs as Teletype Users Text-stream protocols from the terminal era fit how agents work better than modern visual interfaces
2026-02-15 Confabulation Under Uncertainty Agents construct confident answers from insufficient evidence rather than admitting ignorance — and tooling makes it worse
2026-02-14 Agent Temporal Blindness Agents have no perception of elapsed time, causing the web-hammering courtesy problem
2026-02-14 Supervision Cost as the Scaling Bottleneck The principal's attention, not the agent's capability, limits what can be delegated
2026-02-14 Model Identity Confusion on Mid-Session Swap Four failure modes when the underlying model changes — pretraining, history, remit, and tool inventory override
2026-02-14 Critic Score Gaming Under Explicit Constraints Agents optimise for the scoring rubric rather than the intent behind it
2026-02-14 Curator Metadata Hallucination Under Constraint Agents confabulate metadata when pressured to produce structured output they can't verify
2026-02-14 Agent Orientation Bias Agents default to filesystem crawling rather than using the document store's search tools
2026-02-14 Intelligent AI Delegation — Reading Note Notes on Tomašev et al. (2026) and its connection to our supervision cost observations
2026-02-14 Lightweight Bug Tracking in the Document Store Using the document store itself as the bug tracker — practice note

Research paper

Document Description
Artificial Organisations (arXiv:2602.13275) Pre-print describing the artificial organisations framework and the PCE architecture

About

This workspace is part of the Artificial Organisations research programme exploring how LLM agents can form effective organisations — with defined roles, institutional memory, and adversarial review processes.

For questions, contact the workspace owner via leithdocs.com.