Work · selected systems

Selected work.

Each case pairs the claim with architecture, decisions, guarantees and a sanitized artefact from the real system.

01 · Lead case

One working memory, many agents

ProductionInternal system

Claude, Codex and ChatGPT read the same work history instead of starting from zero.

Read the case
Working memory · authority and boundariessanitized policy diagram
  1. identity and permanent boundaries
  2. confirmed profile and preferences
  3. current confirmed decisions and open work
  4. original project documents
  5. the working-memory graph · history, not orders
Working memory

History and context, never orders.

Agents may query it; they may not refresh it or use it to skip approval.

Read-only for agents
02 · Gate case

AI Control Tower: delegation behind a gate

In developmentMCP server

Premium agents keep the reasoning. Bulk work goes to cheaper models, only after an exact approval.

Read the case
03
Productionn8n workflows

Search monitoring that diagnoses before it alerts

n8n collects, an AI step diagnoses, a human decides.

04
ProductionAudit suite

Evidence-first agentic audits

Agents audit a site end to end without writing a single byte to it.

05
ProductionScheduled routine

An evidence-gated research digest

Collection runs without a model. Writing runs with one. Evidence rules decide what gets in.

06
In developmentWeb app

A daily-focus app

Capture a reminder in one gesture. See the day as an editorial page.