My profile picture

Senior Solutions Architect — Digital Platforms & AI Systems

I help insurers ship Guidewire transformations end-to-end: ClaimCenter/PolicyCenter delivery, integration architecture, and modern digital experiences with Jutro. I also write and build side projects in ML and production-grade AI agents.
Core insurance platform systems and integration layer diagram.
Digital portals architecture with cloud infrastructure and CI/CD pipeline.
Foundational machine learning visuals: decision boundary, sigmoid curve, contour plot.
Unrolled sequence model diagram showing memory gating and fading gradients.
Reinforcement learning training instability dashboard with reward, entropy, KL spikes.
Trading agent loop from order book features to policy execution and feedback.
Modern web architecture stack from browser and edge to APIs, services, and data.
Operability visuals: CI/CD pipeline, distributed tracing, and transactional outbox pattern.
Agent platform architecture with tool gateway, policy gates, evals in CI, and observability.
Core insurance platform systems and integration layer diagram.
Digital portals architecture with cloud infrastructure and CI/CD pipeline.
Foundational machine learning visuals: decision boundary, sigmoid curve, contour plot.
Unrolled sequence model diagram showing memory gating and fading gradients.
Reinforcement learning training instability dashboard with reward, entropy, KL spikes.
Trading agent loop from order book features to policy execution and feedback.
Modern web architecture stack from browser and edge to APIs, services, and data.
Operability visuals: CI/CD pipeline, distributed tracing, and transactional outbox pattern.
Agent platform architecture with tool gateway, policy gates, evals in CI, and observability.
Core insurance platform systems and integration layer diagram.
Digital portals architecture with cloud infrastructure and CI/CD pipeline.
Foundational machine learning visuals: decision boundary, sigmoid curve, contour plot.
Unrolled sequence model diagram showing memory gating and fading gradients.
Reinforcement learning training instability dashboard with reward, entropy, KL spikes.
Trading agent loop from order book features to policy execution and feedback.
Modern web architecture stack from browser and edge to APIs, services, and data.
Operability visuals: CI/CD pipeline, distributed tracing, and transactional outbox pattern.
Agent platform architecture with tool gateway, policy gates, evals in CI, and observability.
Core insurance platform systems and integration layer diagram.
Digital portals architecture with cloud infrastructure and CI/CD pipeline.
Foundational machine learning visuals: decision boundary, sigmoid curve, contour plot.
Unrolled sequence model diagram showing memory gating and fading gradients.
Reinforcement learning training instability dashboard with reward, entropy, KL spikes.
Trading agent loop from order book features to policy execution and feedback.
Modern web architecture stack from browser and edge to APIs, services, and data.
Operability visuals: CI/CD pipeline, distributed tracing, and transactional outbox pattern.
Agent platform architecture with tool gateway, policy gates, evals in CI, and observability.

About Me

I’m a senior solutions architect and consultant focused on insurance platforms and digital delivery. My day-to-day work spans core-system transformations, integration architecture, cloud delivery patterns, and governance that keeps large programs shippable. Alongside consulting, I run long-form technical writing and side research in ML and agentic systems—especially how to make agents operable in production (evals, tool safety, observability, and compliance-by-design).

Work Experience

2021 - Present

Senior Architect at
Alchemy

2012 - 2021

Senior Consultant at
Guidewire

2010 - 2011

Consultant at
Novabase

Writing & Research

Short essays and long-form series on operable AI agents, evaluation, governance, and production reliability

Agentic AI Is Becoming a Cybersecurity Problem

Once agents can take actions, they become non-human identities with privileges — and that turns “AI productivity” into “security surface.” This post explains the new threat model, why “kill switches” are really identity and execution controls, and the architecture patterns that make agentic systems operable.

OpenClaw: A Viral Agent, a Skills Ecosystem, and the Supply-Chain Reality Check

OpenClaw went from “personal AI assistant” to “security headline” in weeks. This post explains what OpenClaw actually is (agent runtime + gateway + skills), why skills are a software supply chain, and the architecture patterns that make a self-hosted agent survivable.

Prism and the Architecture of Artifact-Native AI for Science

Prism is a LaTeX-native, AI-first workspace for scientific writing. Under the hood, it’s a new pattern: the model is embedded in the artifact, not bolted onto the side. This post explains the architecture, the contracts that keep it honest, and what “artifact-native AI” changes for reliability and governance.
Axel brought clarity to a complex platform and integration landscape. He translated ambiguity into an execution plan with clear contracts, ownership boundaries, and delivery guardrails. The team shipped with fewer surprises and a calmer release cadence.
Program Lead (anonymized)

Program Lead (anonymized)

Program Lead, Insurance Platform Transformation

Axel consistently reduced delivery friction across teams. He made architectural decisions actionable, aligned stakeholders quickly, and improved reliability through pragmatic release and operational discipline.
Delivery Manager (anonymized)

Delivery Manager (anonymized)

Delivery Manager, Enterprise Program

Axel operates as a force multiplier. He can go from system-level architecture to hands-on delivery support, and he leaves teams with reusable patterns—not just diagrams.
Engineering Lead (anonymized)

Engineering Lead (anonymized)

Engineering Lead, Digital & Integrations

Frequently Asked Questions

Answers to common questions about my process and services.
Axel Domingues - 2026