active
Multi-Agent Orchestration
I test how agents divide work, share memory, and recover when a handoff fails. Coordination is the system, not the glue.
Independent researcher · Agentic systems · Cybersecurity
I build multi-agent AI systems,
then I try to break them:
coordination,
security,
and control.
exAgentica is my personal agentic AI lab.
I build experiments and write about what I learn. After three decades in Internet infrastructure, I keep coming back to the same questions: what can fail, how far can it spread, and who can stop it?
Read the Field Notes01 / The field notebook
Field Notes
What I’m learning about agents, security, and the infrastructure underneath.
When You Can't Pull the Plug
Dependency is the takeover.
The Orchestration Wars: We Are in the Docker Swarm Era
Who wins, how, and what the Kubernetes of agent systems actually looks like.
Trust No Agent
Zero Trust for machines, and why the machine identity crisis is the defining AI security problem of our era.
02 / Experiments
Active lab work
The questions I’m spending time on. Active work and research notes.
active
Agentic Coding
I use coding agents to write and review software. I look for the point where a passing test hides a decision that still needs human review.
active
Local LLM Deployment
I run models locally with Ollama and LM Studio, testing which tasks can stay on my hardware and what I give up in speed and capability.
notes
Swarm Architectures
I study what happens when agents disagree: how they reach a decision, detect circular work, and know when to stop.
active
AI-Driven Security
I study agents on both sides of a security boundary. Tool permissions, untrusted context, and response authority are part of the same problem.
notes
Post-Quantum & Zero Trust
I examine machine identity and cryptographic dependencies. Which permissions should an agent inherit, and which should it have to earn?
What I’m working with
- Claude Code
- Codex
- Grok Bot
- Cursor
- Antigravity
- Ollama
- LM Studio
- TypeScript
- Python
- Cloudflare Workers
- Astro
- LangGraph
- CrewAI
- MCP
- Docker
- Git
- Linux
I approach multi-agent AI as a distributed systems problem. Tools, memory, and permissions make each agent part of something larger. A local mistake can become a system failure.
I co-founded one of the first ISPs in Texas, helped launch OpenStack and the Open Compute Project at Rackspace, and served as Field CTO at Cloudflare. That experience shapes what I test here.
Full bio at johnengates.com04 / Contact
Let’s compare notes.
If you’re building agent systems or working through AI and cyber decisions on a board, I’d be interested in a conversation.