Skip to content
View alexherrero's full-sized avatar

Highlights

  • Pro

Block or report alexherrero

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
alexherrero/README.md

Alex Herrero

Software Engineering Manager | Building great things.

"From a kid who got in trouble for taking things apart, to a Software Engineer and Engineering Manager at Google, I have always loved figuring out how things work and how to make great things."

I lead engineering teams and build software that ties together product features, production-scale, artificial intelligence and security. I believe tech should be intuitive and easy, which usually means it should be simpler. I am great at seeing and understanding complex systems and seeing how to make them simpler and more intuitive. I see artificial intelligence as an opportunity to remove systemic friction, boilerplate drudgery, and cognitive overhead so that technology becomes an extension of human creativity.


🧠 Things I care about

  • Usability over Complexity: My background in systems infrastructure taught me that the most resilient systems are the ones that are easiest to use. Good security doesn't rely on artificial friction, and asking someone to approve rarely makes things safer; security comes from engineering automated, intelligent boundaries that automatically self-correct, and guide users to do what is safe naturally and intuitively, making doing the safer thing easy.
  • Unlocking Creativity: Syntax boilerplate and environment configuration is boring. By removing repetitive engineering, we make room for human creativity—allowing engineers to spend more time creating. Engineering can be art and it should be fun!
  • Making systems more 'experienced': I am interested in self-reinforced, automated learning systems that remember and can gain experience. I want agents to become more than that 'junior engineer' they can be today. I want them to remember that last pair programming session they were in with you and to be better the next time you work on a project. That requires persistent memory that works more like we do, and makes it possible to have a truly useful assistant. When I think about what natural assistants are like, I imagine the kind of interactions you see in the movies, where you can just talk with your agent and it can manage your projects, files and your digital knowledge naturally. That makes engineering less about the code and brings out the best creativity in us all.

🛠️ Some of my recent projects

I've been working on projects that integrate with AGENTS.md-aware environments, Claude Code, and Antigravity in particular. I want these to work more seamlessly with me every day.

Think of Agent M as the structural backend harness you wished you had—part Star Trek Computer, part J.A.R.V.I.S.-level contextual autonomy, engineered to manage your projects, memory, persistent knowledge and complex projects seamlessly across any modern agent surface, gaining experience and self-improving as it goes.

Inspired by the iconic, hyper-compact firearm from Men in Black, Crickets is a tactical suite of agent primitives and targeted tools engineered to punch far above their weight. As the execution engine behind Agent M, it can be deployed as a unified pairing or standalone for maximum operational impact from a minimal footprint.

Finance often treats Artificial intelligence as something to be careful with, after all, they have successfully used it's precursor ML, for years. I am interested in pushing the boundaries of how AI can change trading and make it more accessible to every day tech enthusiasts. My testbed for this ideas is Sherwood, a self-hosted, automated trading engine capable of tracking the markets and crypto at the speed of AI. I want to see how some smart AI use can help a user make consistent returns that aren't 'get rich quick' but that are better than market and safer than the average trade. It combines an isolated predictive-planning subsystem with a mandatory human-in-the-loop gatekeeper for execution safety. v2 currently in active design.

A per-machine bootstrap script enforcing deterministic, opinionated, and highly portable development environment conventions. This is how I tie together my tools so I can make great things.


💼 What I'm good at

[ LEADERSHIP ]     Growing and making Teams more efficient / Cross-Functional Strategy / Mentorship and Career Growth
[ PRODUCT ]        User facing features / Capabilities that make them useful / Simpler, more intuitive products
[ PLATFORMS ]      Cross Platform Software and Management / Cryptography / Security and Threat Intelligence
[ INFRASTRUCTURE ] Google Cloud Platform (GCP) / Zero-Trust Boundaries / Automated CI/CD / Safe, frequent rollouts
[ LANGUAGES ]      API / Golang / C++ / PowerShell / SQL / gRPC

📬 How to Find me

Pinned Loading

  1. sherwood sherwood Public

    A simple trading bot concept with a UI and support for Robinhood

    Go 1

  2. agentm agentm Public

    Think of Agent M as the structural backend harness you wished you had—part Star Trek Computer, part J.A.R.V.I.S.-level contextual autonomy, engineered to manage your projects, memory, persistent kn…

    Python 2 1

  3. crickets crickets Public

    Inspired by the iconic, hyper-compact firearm from Men in Black, Crickets is a tactical suite of agent primitives and targeted tools engineered to punch far above their weight. As the execution eng…

    Python 1

  4. google/certtostore google/certtostore Public

    Hardware Backed Keys and Certificate Store Management on Windows

    Go 109 33