systems i've architected, built, or led, one line each.
event-driven orchestration for real-time, cross-channel customer journeys
multi-tenant graph + time-series platform for shared business outcomes
cerner, sms mainframe, hl7, and revenue cycle integrations; patient self-registration system
ai assurance platform, evidence pipeline, signed attestations
research on the security of ai systems and the protocols agents will run on. published in the open — ietf drafts, specs, and working code.
draft-miller-ztip
Verifiable delegation chains, intent-scoped authorization, and behavioral claims for multi-agent systems — so a token issued for one intent can't be spent on another. Composes with OAuth, GNAP, and ZTNP.
draft-miller-ztnp
Session-scoped trust negotiation for software security posture: challenge for a signed posture assertion, evaluate it against a public framework, issue a short-lived, channel-bound permit.
agent-trust-protocols/agent-trust-protocols
A family of open, cryptographically verifiable protocols for trust negotiation, delegation, and authorization in agentic AI systems. Hosts ZTIP, ZTNP, reference implementations, and test vectors.
zivisai/zat
Signed, machine-readable compliance attestations with outcome-level claims, Merkle-committed evidence, selective disclosure, and post-quantum signatures.
zivisai/maul
A deliberately vulnerable AI application for red-team training and security research. Covers RAG pipelines, embedding attacks, agent-tool misuse, and SSE hijacking.
essays and pattern libraries — written for practitioners, kept current as the field shifts.
Revisiting the 2018 primer through the lens of agentic AI — what still holds, what's changed, and how event-driven patterns shape the systems agents will run on.
zivis.ai/patterns
An opinionated, security-first pattern library for AI systems — agents, retrieval, prompting, memory, and emerging approaches, each with threat analysis.
@jakemillerindy
Long-form essays on architecture, ai security, and the engineering reality behind agentic systems.
film and generative media work under pink stack studio. same systems thinking, different medium.
video unavailable here — watch it on pinkstackstudio.com →
63.93 seconds · 1280 × 720 · streamed from pinkstackstudio.com
pink stack studio
A 64-second film prototype and an open breakdown of how it was made: references, hinge frames, generated bridges, continuity rules, edit, and sound.
how the work runs, written down so it can be held against the output.
strategy, architecture, and implementation are one job. set the direction, design the system, and write the code that proves it holds.
every claim built on working code, repeatable labs, and traces you can replay. no hand-waving, no academic distance from the system.
ietf drafts, open specs, repos, and demos — where the community can read, break, and extend the work. findings belong to the field.
show the failure mode before the fix. build the threat before the defense. the point is not to reassure — it is to be correct about what is broken.
technology leader and architect who still ships. 20+ years building software and the teams behind it, now focused on ai security and agent systems.
Jake Miller is a technology leader, software architect, and hands-on engineer. He has run engineering organizations, served as CTO and CEO, and designed platforms used by global brands, and he still writes production code. His current focus is how AI systems fail in real-world environments — across LLM applications, RAG pipelines, agents, tools, MCP architectures, APIs, workflows, and the infrastructure they depend on.
His work explores the gap between AI security theory and production reality: what breaks, how it breaks, whether it is exploitable, and what evidence is needed to prove a fix actually holds. He's especially interested in agentic systems, human-in-the-loop validation, continuous testing, prompt and workflow attack surfaces, and the emerging security boundaries between models, tools, memory, and data.
Jake has spent more than two decades building software across startup, enterprise, and private-equity-backed environments. He joined ExactTarget as a software engineer on Journey Builder and, through the Salesforce acquisition, grew into Director of Software Engineering for Marketing Cloud, leading a 25-person organization across three product teams. He later co-founded Metaimpact as CTO, where he built MetaCX, and founded The Engineered Innovation Group as CEO.
Today, Jake builds and studies AI security systems through hands-on experimentation, field research, simulations, and platform work. The goal: help builders and defenders move beyond AI anxiety toward durable confidence — understanding what can break, how attackers may exploit it, and how teams can close the loop in real systems.
open inbox. i respond within 24 hours.
technology leadership, architecture & engineering roles.
advisory & consulting.
research collaborations & co-authorship.
executive briefings & board sessions.
press & analyst inquiries.