James Ross

I run a multi-agent workspace in production every day and publish what I measure on it: what the agents cost, how much of their work gets sent back, and which controls hold up. The architecture is open source and the essays are below.

Now
Founder of Vector.
Open source
agent-workspace-architecture, a reference architecture of eighteen patterns drawn from the workspace I run, with six more public repos around it.
Book
Agent-First: Rebuilding the Organisation One Governed Loop at a Time. Second draft complete.
Research
PhD candidate, James Cook University, researching trustworthy shared memory for collaborative AI agents.

Latest writing

More writing

  1. 16 Nov 20264mDigest #4: three teardowns, a new Action and six experimentsdigest
  2. 27 Sep 20263mDigest #3: a teardown of GPT-RAG and two correctionsdigest
  3. 06 Sep 20264mStop asking the AI to be careful. Make carefulness a config file.essay
  4. 06 Sep 20262mDigest #2: three teardowns and a learn trackdigest
  5. 30 Aug 20263mYour agent bill is mostly context, not outputessay
  6. 30 Aug 20263mYour agents are about to start working unattendedessay

All 13 pieces →

Projects

A grid scoring eight agent systems against eighteen patterns as present, partial, absent or not assessed.

open source · teardowns

Eight teardowns, eighteen patterns

I read other people's agent systems against the same eighteen patterns and publish what I find, including the corrections when I get one wrong. No pattern is present in all eight.

Tools

Instruments from the working system, all free. Everything runs in your browser, and your agents can call the same instruments over MCP at jamesross.ai/mcp.

About

I came to agents through data engineering, building production data platforms. That meant cloud data warehouses, ETL pipelines and the analytics executives decide on. Then I went deep on agent systems. I built a full multi-agent workspace from the ground up, and built and deployed an AI-driven SaaS end to end.

I bring an engineer's production discipline to it (version control, testing, provenance, rollback, observability), in a field that is still mostly demos. Separately, I'm a PhD candidate researching how autonomous agents share and govern memory.

Doctorate
Doctoral research, James Cook University, from 2026. Trustworthy shared memory for collaborative AI agents.
Masters
Master of Data Science, James Cook University.
Diploma
Graduate Diploma in Research Methods, James Cook University.
Contact
james@vectorai.au, or GitHub and LinkedIn. New essays go out by email on Substack.