Grokking the Agentic Loop 26 Workshop: Difference between revisions

From HOPE Wiki
No edit summary
Kwame (talk | contribs)
mNo edit summary
 
Line 7: Line 7:
== Day / Time / Location ==
== Day / Time / Location ==


Day 2, Saturday, 15-August-2026, 2:00pm - 3:30pm<br>
Day 2: Saturday, August 15, 2026<br>
Workshop A (Sutton Place, third floor)
2:00pm - 3:30pm<br>
Workshop A (Sutton Place, third floor)<br>


== Full Description ==
== Full Description ==


[optional: put your longer description here]
As agentic AI becomes more prevalent, understanding the underlying control logic is essential for hackers looking to build, secure, or critique these systems. We’ll be covering:<br>
* The Basic Loop: Understanding the reason, act, observe cycle.
* Function Calling: How LLMs interact with external tools.
* Iterative Logic: Designing the control flow that powers autonomous behavior.


== Registration -- NOT required ==  
== Registration -- NOT required ==  


<span style="color:orange">'''NOTE:  You do NOT need to register to take this workshop<br>-- please show up early to ensure a seat at the WORKSHOP A room (in Sutton Place, on the third floor).'''<br>
<span style="color:orange">'''You do not need to register to take this workshop.'''</span><br>
Please just show up early to ensure a seat in the Workshop A room, at Sutton Place on the third floor.


== Presenter(s) ==
== Presenters ==


Kwame Wright<br>
[http://linkedin.com/in/kwamewright Kwame Wright] is a software engineer working in the autonomous vehicle space, where he integrates AI to boost productivity and improve the customer experience. He holds a Ph.D. in Electrical Engineering from the University of Southern California. Outside of his core work, Kwame is fascinated by the intersection of math, physics, and art, frequently exploring topics in 3D computer graphics like rendering and path tracing.
Jarone Wright


== Materials ==
[http://linkedin.com/in/jaronecreate Jarone Wright] is an educational technologist and computer scientist working in higher education. He holds a Master’s degree from the Interactive Telecommunications Program (ITP) at the NYU Tisch School of the Arts. Outside of his academic work, Jarone focuses on creative and tangible technology, with personal interests that include physical computing, interactive music, and kiln glass.
 
Any materials needed to participate in this workshop will be available at-cost.<br>
Observers are welcome at no cost.<br>
'''To do the hands-on portion for this workshop:<br>
'''Materials Cost: none'''<br>


== Required Software / What to bring ==
== Required Software / What to bring ==


[example: Bring laptop, if you can, with Arduino software installed.]
Bring a laptop with a Python development environment, and a Google account for using the Gemini API.


== Links ==
== Links ==


[put helpful links here]
[http://aistudio.google.com Google AI Studio]

Latest revision as of 06:00, 5 August 2026

Grokking the Agentic Loop: From Chatbots to Autonomous Agents workshop

Abstract

Many people interact with large language models (LLMs) through simple, linear chat interfaces. However, AI unlocks its true potential when these models are placed inside an agentic loop - a cycle of reasoning, acting, and observing. In this hands-on workshop, you will demystify AI agents by building a basic agentic loop from scratch using Python and the Gemini API. Participants will learn how to move beyond static prompts to create systems that can use tools, evaluate their own outputs, and iterate toward a goal. This workshop is designed to turn the magic of AI agents into a clear, hackable process.

Day / Time / Location

Day 2: Saturday, August 15, 2026
2:00pm - 3:30pm
Workshop A (Sutton Place, third floor)

Full Description

As agentic AI becomes more prevalent, understanding the underlying control logic is essential for hackers looking to build, secure, or critique these systems. We’ll be covering:

  • The Basic Loop: Understanding the reason, act, observe cycle.
  • Function Calling: How LLMs interact with external tools.
  • Iterative Logic: Designing the control flow that powers autonomous behavior.

Registration -- NOT required

You do not need to register to take this workshop.
Please just show up early to ensure a seat in the Workshop A room, at Sutton Place on the third floor.

Presenters

Kwame Wright is a software engineer working in the autonomous vehicle space, where he integrates AI to boost productivity and improve the customer experience. He holds a Ph.D. in Electrical Engineering from the University of Southern California. Outside of his core work, Kwame is fascinated by the intersection of math, physics, and art, frequently exploring topics in 3D computer graphics like rendering and path tracing.

Jarone Wright is an educational technologist and computer scientist working in higher education. He holds a Master’s degree from the Interactive Telecommunications Program (ITP) at the NYU Tisch School of the Arts. Outside of his academic work, Jarone focuses on creative and tangible technology, with personal interests that include physical computing, interactive music, and kiln glass.

Required Software / What to bring

Bring a laptop with a Python development environment, and a Google account for using the Gemini API.

Links

Google AI Studio