FOUNDER, ANTHUS
Ryan Porter
Technology leader and architectural innovator with a proven history of developing and operating mission-critical, high-availability systems that deliver business value. Focused on delivering exciting AI applications through serverless cloud architectures.
01 / Experience
Where I’ve worked
January 2024 – Present
Anthus AI Solutions
Our team has been working together for over a decade, and we have been working on AI solutions for years now. The Anthus name is the only new thing, as we fully focus on the intersection of software solutions and artificial intelligence.
August 2021 – January 2024
Tao Group Hospitality
Formerly with Hakkasan Group, Angel Management Group, and Venue Driver in an evolving role with the same venture.
- Pioneering technical strategy: developed and operated a critical ticketing system evolving since 2007 into a comprehensive platform for reservation, guest list, and artist booking management.
- Seamless transition and growth: managed the system’s transition through corporate acquisitions, maintaining high availability while processing as much as $64 million in revenue per year with no major incidents.
- DevOps and agile leadership: championed a DevOps culture of rapid iteration and continuous improvement, aligned closely with business needs.
- Longevity and adaptation: adapted the platform from early monolithic structures to a modern serverless distributed architecture, passing AWS Well-Architected audits by multinational corporations.
February 2014 – August 2021
Hakkasan Group
Formerly with Angel Management Group, and Venue Driver in an evolving role with the same venture.
- Scalable system leadership: continued advancement of a high-revenue ticketing system on scalable, fault-tolerant AWS infrastructure, embodying the Well-Architected Framework.
- Data integration initiative: initiated and delivered an enterprise data warehouse integrating diverse data systems to support analytics, Salesforce CRM, Marketo and Salesforce Marketing Cloud.
October 2013 – February 2014
Angel Management Group
Formerly with Venue Driver in an evolving role with the same venture. Continuation and expansion of the existing role at Angel Management Group, which created Venue Driver as a spin-off.
2007 – October 2013
Venue Driver
Startup technology foundation: built and managed all technology infrastructure for a hospitality-focused technology startup, evolving the company into a major event ticketing provider.
Leadership and technical training: directed software development, web operations, technical hiring, and training programs, laying the foundation for the eventual acquisition and growth.
2002 – 2005
CoolJunkie, LLC
A joint venture with Nick McCabe to develop a nightlife production and media company in Miami Beach. The CoolJunkie.com website and its interactive forums were a pillar of the Miami Beach nightlife scene for years, before social media. The company also produced events like the BBC Radio One Miami party during the Winter Music Conference, and events from artists like Pete Tong and Cedric Gervais.
1997 – Present
Endymion Corporation
A small software product company started after graduating, built around a web mail application popular in the early days of the web, in the days of WebTV and AOL. Developed, licensed and supported a PERL-based web mail application used by thousands of users, and a Java-based enterprise web mail product.
02 / Education
Where I studied
1992 – 1997
University of Florida
Worked as an undergraduate research assistant for Dr. Gerhard X. Ritter and Dr. Mark S. Schmalz on their work in computer vision using the Image Algebra framework, with funding from the US Department of Defense. One project’s goal was the automated detection of land mines using multi-spectral imagery, an early predecessor of today’s visual segmentation models, built on 2D convolution algorithms without modern visual AI. The main job was C++ development.
A related computer vision project aimed at detecting water mines by removing distortion in images from the surface of the ocean.
Also worked on research by Dr. Panos Livadas on automated code analysis and refactoring tools that foreshadowed LLM-based coding tools like GitHub Copilot, and as an undergraduate teaching assistant for a class based on the classic Lisp textbook, The Structure and Interpretation of Computer Programs.
03 / Portfolio
Systems and projects
DataParade
DataParade is a privacy and security product built on a semantic knowledge graph, with a custom ontology and taxonomy that ties into the OCSF standard. Anthus is working with DataParade to develop it. It belongs to the new class of tooling that lets people see what AI agents are doing across a project once they've stepped back from writing the code themselves. • Semantic knowledge graph as the system of record for what happened, to what, and by whom • Custom ontology and taxonomy mapped to the Open Cybersecurity Schema Framework • Built for the operator who has delegated the work and still has to answer for it Visit dataparade.io.
B0rd
B0rd is a standalone LED-matrix desk display built by Anthus Microelectronics, a spinoff venture rooted in Anthus's ubiquitous use of AI agents and the constant all-day need to monitor their progress and steer them. It puts glanceable information — launch countdowns, agent status, notifications, an idle clock — on the wall or desk without a screen you have to sit in front of. • Handbuilt microelectronics with a custom handbuilt (AI-assisted) OS • Standalone appliance: setup over Wi‑Fi, no app store, no phone required • Glanceable cues for long-running agent sessions — walk away from the desk and still know • In sync by design: matching units stay in step with no pairing or hub Visit b0rd.info or the Etsy shop.
Speaker Role Classifier
A real-world example of how the agentic programming paradigm enables rapid solution development. We faced a problem where ambiguity in speaker role names could have made a traditional programmatic solution complex and time-consuming. By giving an AI agent the right tools, we delivered a working solution quickly and moved on—demonstrating how agent-based programming enables much greater agility and speed. View the project on GitHub.
Classification with Confidence
A practical exploration of LLM fine-tuning for text classification. By fine-tuning GPT-4o-mini, we significantly improved classification accuracy and alignment to specific business requirements. The project demonstrates a production-ready approach to model alignment with confidence scoring that determines when human review is needed—a practical application of human-in-the-loop principles that balances automation with expert oversight. View the project on GitHub.
SQLBot: Your AI Database Analyst
SQLBot is a new kind of interface for your database. Instead of writing SQL queries yourself, you delegate high-level analytical tasks to an AI agent. It reasons through your request, executing a chain of queries and analyzing the results until it arrives at a complete answer—all while keeping your data safe with built-in safeguards. View the project on GitHub.
- Pass
- Miss
Each call is one document and gets one scored row. We have scored calls this way across hundreds of scorecards and millions of calls.
Call Criteria
Call Criteria scored call-center QA with custom fine-tuned LLM classifiers run by an outside service. It worked, but the vendor was too expensive and too slow to scale to every new scorecard, and they wanted control. We built them an in-house classifier lab on Primus in their own AWS account and operated it for years: hundreds of scorecards, millions of calls, the cheapest model that clears each bar, and reviewers whose corrections became policy.
Primus
Primus is our MLOps platform. We built it as the core infrastructure for the classifier lab we built for Call Criteria, and it has managed the full lifecycle of classifiers and AI agents at production scale for years: • Hundreds of scorecards, millions of interactions scored • Reviewers correct verdicts and say why; the explanation becomes policy • Training, evaluation, deployment, and monitoring on the record, version by version • Any model as a backend: hosted LLMs, fine-tuned LLMs, small ML classifiers, and decision models like Jev Visit primus.anth.us for the product.
- Event
- Function
- Delivered
Ticketing, VIP tables and guest lists on serverless, event-driven infrastructure, wired into loyalty, ServiceNow and a data warehouse.
Venue Driver
A nightclub management system that has been the backbone of Las Vegas hospitality operations since 2007, processing over a quarter of a billion dollars in total revenue: • Processed as much as $64 million in revenue a year • Began as an on-premises solution for reservations and guest lists, tailored for Las Vegas nightlife • Underwent successful cloud transformation to AWS, enhancing scalability and reliability • Transitioned to serverless architecture, dramatically reducing operational costs while improving performance • Adapted continuously to support new business models and regulatory requirements • Integrated with other systems, creating a comprehensive hospitality management ecosystem Venue Driver's longevity, financial impact, and successful technological evolution demonstrate our ability to create and maintain mission-critical solutions that grow with our clients' needs, from on-premises to cloud to serverless architectures.
04 / Integrations
What we connect to
PRESS START
Bring us the problem.
Even if you can’t yet say what you need. Working that out is part of the first month, and it’s often the most useful part.