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