AI Engineer · Senior / Staff

Agents users touch, agents that write code, and the platforms that run them.

I have ridden the whole arc of AI-assisted engineering, from smart line completions in an editor to agentic coding to frameworks that operate fleets of coding agents, and I have been putting agents in production the entire time.

Shipped, funded, and running

Agent work with users, revenue stakes, and receipts.

In product
agents users touch, at Cloaked

I built autonomous LangChain agents that change passwords, log in, and manage email on users’ behalf. They became a core fundraising narrative and powered an AI onboarding experience that measurably boosted adoption and retention.

In the repo
agents that write code

At Block Party I designed and built the framework behind the company’s internal AI coding bots. On my own time I run Fountain, a multi-tenant control plane for sandboxed coding agents that was largely built by the agents it orchestrates. Fountain ships under BinaryBourbon, the GitHub identity my agent fleet works under. I set the roadmap, review the work, and operate the system.

$400K
pre-seed for an agent-native SaaS

I cofounded Ravi, where AI agents manage their own accounts, secrets, and 2FA. It raised a $400K pre-seed from South Park Commons and grew to hundreds of users, with the instrumented v1’s real usage data carrying the pitch.

Protocol
MCP and A2A in the wild

I am a member of the MCP Hosting Working Group, publish MCP servers, and contributed to the Dart MCP SDK. This site practices what I pitch. ai.jakegaylor.com serves an A2A agent card and an MCP server, so your screening agent can interview me directly.

My first 90 days on your AI roadmap

1 · Find the agent-shaped work

Most orgs have workflows an agent could own today and features an agent can’t carry yet. I sort one from the other before writing code.

2 · Ship a small agent, instrumented

An embarrassingly small v1 in front of real users with tracking from day one, the same way Ravi won its funding.

3 · Build the guardrails as a platform

Sandboxing, review gates, and observability, so scaling from one agent to a fleet is an operations problem instead of a leap of faith.

“Jake is a force for good unlike any other. He migrated our infra to a cheaper and more scalable system, crafted a CI pipeline that accelerated deploys by 30x, and taught the whole company how to make data-driven decisions by building an entire product analytics stack. And that was just his first 6 months.”

Aaron Biller, Director of Platform Engineering, Cloaked

Sound like the role you’re hiring for?

The resume has the full 15-year history. Or skip straight to a conversation.

Or browse my projects & ventures. Screening with an AI assistant? Point it at ai.jakegaylor.com.