Franklin Okpako
Building and evaluating infrastructure for reliable autonomous AI systems.
My work connects production systems and distributed architecture to AI inference, trustworthy agent infrastructure and usable business workflows. At BlockOps I build model infrastructure; through Agent Rails I investigate the controls around agents; with businesses I am testing how those components can become useful systems.
Built on
About the researcher
- 01Production systems
- 02Distributed and platform architecture
- 03AI inference infrastructure
- 04Trustworthy agent infrastructure
- 05Applied AI systems for businesses
I began in systems engineering and moved through networking, cloud engineering, DevOps, security, platform engineering and infrastructure architecture. My focus increasingly became designing observable, fault-tolerant, self-healing systems that reduce unnecessary operational intervention and give teams safe, self-service platforms to build on.
At Exodus, from February 2022 to August 2026, I designed and operated production Kubernetes and distributed infrastructure across five EKS clusters supporting wallet and blockchain systems at global scale. That work included GitOps architecture, networking, stateful workloads, observability and incident response, and turning recurring failures into automation and more resilient system design.
Today, my applied work at BlockOps focuses on AI infrastructure: model serving, GPU-backed workloads, isolation, observability and simplifying deployment across cloud and privately managed environments. I am going deeper into inference and serving internals so that design decisions follow from how the components actually work.
Alongside that work, I build Agent Rails, an open-source effort exploring authorization, memory, observability, delegated authority, orchestration and evaluation for autonomous AI systems. Agent Guard is the flagship: a concrete place to examine policy, identity, human approval, audit and execution boundaries together.
I am also working with businesses to understand how these components can become usable AI tools. The SME Agent Template supports two different workflow shapes; workflow validation with businesses and development toward an MVP are in progress, not completed real-world validation.
Read the full research visionAgent Rails: questions with running code.
Agent Rails is the umbrella for my work on authorization, memory, observability and orchestration. Agent Guard leads the research, bringing policy, identity, approval, audit and isolation into one inspectable boundary.
From infrastructure to usable systems.
Understand the infrastructure, build the controls, compose them into workflows, then test whether people can use them.
BlockOps
Teams need a usable path from choosing a model to operating it on cloud or privately managed GPU infrastructure.
Current applied AI-infrastructure work, informed by deeper study of inference runtimes and serving internals.
Read the design and current limits →SME Agent Template
Control primitives matter only if they can be composed into systems that organizations can understand and operate.
Applied systems work composing Agent Rails controls into a business-facing template; workflow validation is in progress.
Read the design and current limits →Recent articles.
Notes from the workbench.
August 2026: Building memory isn't enough
The harder problem is deciding what should be remembered, and what should be allowed to fade.
July 2026: Uncertainty is information, not a bug
The most interesting failures are not when an agent is wrong, but when it is uncertain and acts anyway.
Agent Rails, organized by research problem.
The repositories are components of one research effort. Agent Guard is the flagship; the other components investigate the memory, evidence and coordination it needs around it.
Authorization / control
Who may act, with what authority, and where is it enforced?
Memory
What should an agent retain, revise or discard when sources disagree?
Observability / evidence
What happened, what was claimed, and what can the record establish?
Orchestration
How do these boundaries hold across a complete workflow?
A decade of production systems, as evidence for the research.
At Exodus, I operated five EKS clusters and built distributed infrastructure and self-service delivery platforms. At BlockOps, I now apply that experience to model serving and deployment infrastructure. The recurring goal is observable, fault-tolerant systems that reduce unnecessary intervention.
AWS · Kubernetes · Linux · Cilium · Terraform · ArgoCD · Cloudflare · reliability · security
Hands-on help with agentic AI infrastructure.
Architecture review, security baselines, and implementation support for teams building autonomous systems.
Talk to an engineer, not a sales bot.
Tell us about your stack and what you're trying to automate. We'll reply within one business day with a concrete next step — pilot, architecture review, or a quick async answer.