Angie Jones
VP Engineering, AI Tools & Enablement
New Orleans, Louisiana, United States
Actions
Angie Jones is the VP Engineering, AI Tools & Enablement at Block, Inc. An award-winning educator and international keynote speaker, Angie shares her expertise with audiences at software companies and conferences around the globe.
As a Master Inventor, Angie is celebrated for her innovative and creative thinking, which has led to over 25 patented inventions in fields such as metaverses, collaboration software, social networking, smarter planet technologies, and software development processes.
Area of Expertise
Topics
Vibe Coding with Goose: Building Apps with AI Agents and MCP
So you want to be a vibe coder, huh? Well, let's put your skills to the test.
Your mission, should you choose to accept it, is to build not one, not two, but TEN apps in just a few hours!
Sounds impossible? Not when you've got AI Agent Goose by your side.
In this high energy, hands-on workshop, you'll be dropped into a series of fast paced coding challenges. Each task calls for creativity, speed, and a little help from AI. Armed with Goose and a curated lineup of MCP servers, you'll generate apps at the speed of vibes.
No fluff. No filler. Just real dev work assisted by a powerful open source AI agent that knows how to get things done.
Up for the challenge? See you there!
This message will self-destruct in 3… 2… 1… 🧨
MCP Mashups: How AI Agents are Reviving the Programmable Web
Remember the Mashup Era where developers mixed and matched APIs from different vendors to create new services?
This was such an exciting time for developers. APIs like Google Maps, Twitter, and Flickr gave developers access to data they could use to create interactive user experiences that were simply delightful. However, the excitement eventually fizzled as developers realized they had to maintain these applications which were often just fun side projects.
Now, 20 years later, that excitement and curiosity has returned with the introduction of AI Agents. With the MCP (Model Context Protocol) open standard, developers can integrate data and functionality from multiple services without the burden of maintaining full systems. By connecting AI agents to various APIs, resources, and data sources, we get quick modern-day mashups.
In this talk, we’ll explore how AI Agents are bringing fun and creativity back to software development and giving new life to the “programmable web”.
Don’t Confuse the Bots: A Layered MCP Design for Large APIs
AI agents are here, and they're hungry for context. But if you just throw your massive API at them with hundreds of endpoints, inconsistent patterns, and cryptic parameters, the agent will stumble, burn tokens, and make mistakes.
We ran into this problem as we designed the Square MCP server. With a very intentional approach, we managed to cover 30 APIs and 200 endpoints… with just three tools.
In this talk, I'll show you the layered design pattern we used to keep our tools structured, how we avoided "tool bloat" while still covering a large API surface, and how we baked in safety, auditability, and recovery from the start.
If your API feels too big or messy for agents to handle, this session will show you how to build a lightweight, agent-friendly MCP server without rewriting your APIs.
The Accidental AI Revolution: How an Engineering Tool Won Over the Entire Company
AI adoption usually starts in engineering, but what happens when it proves so useful that the entire company wants in? That’s exactly what happened with Goose, our autonomous AI agent. Initially built as an internal developer tool, Goose helped our engineers become 20% more efficient, streamlining workflows and automating tedious tasks. But what we didn’t expect was non-engineering teams across the company using it too, finding creative ways to boost their own productivity.
As adoption spread organically, leadership took notice. Seeing the measurable impact, we pushed to expand Goose as a company-wide initiative.
In this talk, I’ll share the journey of how an AI tool went from an engineering experiment to a business-wide enabler, the roadblocks we hit along the way, and the strategies we used to turn skeptics into superusers.
Whether you’re introducing AI at a small scale or looking to drive enterprise-wide adoption, this session will give you a playbook for making AI indispensable across your organization.
Air Fryers, Automation, and AI
What do air fryers, automation, and AI have in common? More than you might think!
New technologies like AI and intelligent agents aren’t here to replace tools like automation tools. They’re here to work alongside them, expanding what’s possible in automation.
In this talk, we’ll uncover how the automation tools that we know and love remain a critical component for browser automation, even as we integrate AI to tackle increasingly complex workflows.
Whether you’re an automation engineer, a technology enthusiast, or just someone who loves air fryers (like me!), this talk will leave you hungry for what’s next in automation!
Codename Goose: An Open Source Local AI Agent Built on MCP
AI coding assistants are evolving fast, but most are limited to generating code. Codename Goose, an open source AI agent, takes it further by actually running commands, fixing code, and interacting with your development environment like a true assistant.
Unlike cloud-based AI tools that rely on proprietary APIs, Goose runs locally on your machine and allows you to use the LLM of your choice, giving you full control over its actions and integrations. It’s built on the Model Context Protocol (MCP), an open standard that connects Goose to 1,700+ extensions giving it the ability to fetch data, interact with your databases, IDEs, GitHub repos, Google apps, and much much more.
In this session, we’ll explore:
* How Goose turns LLMs into actionable agents, capable of more than just code suggestions.
* How Goose is infinitely extensible, letting you integrate it with any LLM and any API.
* Real-world use cases.
Goose is local-first, developer-first, and open source. Come see it in action and learn how to build, extend, and customize your own workflows.
From Experiment to Enterprise: How Block Operationalized MCP at Scale
At Block, we've moved beyond experimentation to implement MCP across our entire organization, integrating it into everyday workflows. And not just within engineering. Teams across the company, from legal to marketing, now utilize MCP to automate their work.
This talk will explore our journey from initial adoption to company-wide deployment, highlighting how we've leveraged MCP to build Goose, an open source MCP client, and how it's been configured to connect with an array of MCP servers while meeting our security and compliance requirements.
Attendees will gain insights into practical strategies for deploying MCP in enterprise environments, including server curation, access control, and user adoption.
Beyond Code Generation: Getting Real Work Done with AI Agents
AI tools can write code now. Cool. But what about everything else? Triaging issues, writing tests, opening PRs, updating docs. That's the stuff we should be delegating to AI.
In this talk, I'll show you what happens when agents step out of the IDE and actually start doing work. No flashy prompts. Just practical, repeatable workflows where agents take real action across environments and tools, and even collaborate with other agents and models to get complex tasks done faster.
If you're using AI to help you write code, great. Now let it help you ship.
Angie Jones
VP Engineering, AI Tools & Enablement
New Orleans, Louisiana, United States
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top