Public Event
In Person
AI Tinkerers:
How It’s Made: Architecting Planning-Based AI Systems ft. AI21 Maestro
May
19

This technical session provides a deep dive into the engineering principles and design decisions behind building a planning-based AI platform. Using AI21’s Maestro as a case study, we’ll explore the practical considerations in creating an enterprise-grade AI system that transcends traditional token prediction models.
Key topics include:
- Implementing decision-theoretic planning with Monte Carlo Tree Search (MCTS)
- Engineering explicit cost and success probability models for each action
- Building verification systems that combine deterministic procedures with LLM-based heuristics
- Creating “anytime” execution frameworks that provide baseline outputs while optimizing for improvements
- Designing for parallelism and human-in-the-loop interactions
- Defining a robust plan description language (subset of Python) for action sequences
This session walks through the architectural decisions required to build AI systems that provide enterprise-grade reliability while leveraging the full capabilities of modern language models.
Who is this for?
This workshop is designed for active AI builders, engineers, and entrepreneurs. If you’re actively tinkering with LLMs and generative AI and agents and want to take your skills to the next level, this is the perfect event for you.
Our gatherings are not suitable for those looking to enter the field, individuals seeking to market their services like SaaS sales, consulting or recruiting, angel investors aiming to connect with prospective founders, or professionals looking for early stage clients, etc.
Specifically, this event is perfect for:
- Professional developers and engineers
- AI practitioners
- Technical leaders
- Emphasis on working professionals (not students)
What is AI Tinkerers?
AI Tinkerers is a meetup designed exclusively for practitioners who possess technical, machine learning, and entrepreneurial backgrounds and are actively building and working with foundation models, such as large language models (LLMs) and generative AI. If you’re deeply passionate about creating LLM-enabled applications, have hands-on experience in building such systems, and are eager to connect with like-minded individuals who share your level of commitment, then this group is the perfect fit for you. With AI Tinkerers meetups taking place in multiple cities, we cater to a dedicated community of practitioners.