The
Multiverse
School

8-Week Course

Production Agent Engineering

10.28.24 - 12.16.24 8 weeks live & online, 10.5 hours in class

Mastering Intelligent Language Models

with Liz Howard

Tell me when the next one is scheduled

This run has finished. Leave your email and we will tell you when the next one opens.

We'll email you to confirm, then when the next one is scheduled, plus up to two reminders. Unsubscribe any time.

What You'll Learn

In this advanced course, participants will explore the cutting-edge of agent and tool engineering within the context of Large Language Models. From writing effective system prompts to designing autonomous agents capable of evolving their own functionality, this class covers the comprehensive skills required to innovate in the field of AI and machine learning. Participants will learn how to harness open-source tools, manage vector stores economically, and create complex agent architectures for collaborative and secretive tasks.

  • Write effective system prompts for regularized outputs or tool use
  • Design and implement agents capable of using, creating, and managing tools
  • Develop agents with autonomous action capabilities, including scheduling and event-triggered responses
  • Utilize open-source tool hubs designed for Large Language Models
  • Manage and economically host large vector stores
  • Construct self-improving agents that can evolve their prompts
  • Create and manage swarms of agents collaborating on complex goals
  • Design meta-swarms and information hierarchies for advanced agent collaboration and secrecy
  • Evaluate and create benchmarks for LLM performance analysis

Course Schedule

4Weeks
10.5Classroom Hours
Week 1

Tool Users

Monday, October 28 at 2:00 PM - 3:30 PM PDT

Focuses on writing effective system prompts for regularized output or tool use and creating agents who can utilize tools efficiently.

1.5h
Week 1

Automate Agent Creation

Wednesday, October 30 at 2:00 PM - 3:30 PM PDT

Covers creating benchmarks for LLM performance evaluation, and writing agents capable of creating tools and other agents.

1.5h
Week 2

Tool-Using Agents with RAG

Monday, November 04 at 2:00 PM - 3:30 PM PST

Explores the use of open-source tools designed for LLMs, managing knowledge in vector stores, and hosting vector stores economically.

1.5h
Week 2

Common Agent Patterns

Wednesday, November 06 at 2:00 PM - 3:30 PM PST

Delves into writing agents that can take autonomous actions based on schedules or event triggers.

1.5h
Week 7

Self-Improving Agents

Monday, December 09 at 2:00 PM - 3:30 PM PST

Focuses on creating self-improving agents, using critical theory, and applying expert strategies for prompt optimization.

1.5h
Week 7

Swarms and Swarm Architecture

Wednesday, December 11 at 2:00 PM - 3:30 PM PST

Teaches about creating swarms of agents for collaboration on complex goals and constructing effective agent architectures.

1.5h
Week 8

MetaSwarms

Monday, December 16 at 2:00 PM - 3:30 PM PST

Covers constructing meta-swarms with information mediators and creating an information hierarchy among agents for enhanced secrecy and collaboration.

1.5h

All times shown in Pacific Time

Who Is This Course For

Students with foundational knowledge in Prompt Engineering and Agent Engineering, looking to specialize in advanced agent and tool creation and management.

Who this is for & what you'll need

Pro engineering

Built for working engineers.

A few installs

You'll install a couple of tools, we'll help you in class.

Where This Class Leads

What you leave able to do

  • reconcile agents from different toolchains into one run
  • select among agent architectures
  • synthesise a memory hierarchy for an agent
  • synthesise a retrieval over relationships not just similarity
  • synthesise a self extending agent behind a review gate
  • synthesise an accountability regime for an unattended agent
  • originate an operating model for managed agent teams

How you show it. A written operating model in use by at least two people, with a recorded instance of it catching a failure that the previous arrangement missed.

It sits on one path

The AI Builder10 of 12 after Advanced Retrieval Augmented Generation · before Agentic SDLC

About 24 hours of practice sit behind this one. See what your hours buy.

Join the Course

Pay what you can - accessible learning for all

The minimum is $70, it keeps out spam. Need a larger discount? Apply for a scholarship. We offer 100% scholarships, no one is turned away for lack of funds.

Suggested $140 pay what you can

Suggested price • Pay what you can

    Pay What You Can

    Secure payment via Stripe

    Suggested $200 pay what you can

    Suggested price • Pay what you can

      Pay What You Can

      Secure payment via Stripe

      Instructor

      Liz Howard

      Liz Howard

      Future Infinitive☸️ (Liz Howard) Founder & Professor, The Multiverse School Computer Science · AI · Cybersecurity Formerly faculty, Cal State Monterey Bay Co-founder, Hipcamp Previously built Hackbright Academy, Girl Develop It, Galvanize, Enki

      GitHub LinkedIn Website

      Frequently Asked Questions

      How are classes delivered?

      All classes are live and online via video call. Sessions are recorded so you can review them later if you miss one.

      What does "pay what you can" mean?

      We show a suggested price. The minimum is $70, which keeps out spam. If that's out of reach, apply for a scholarship, we offer 100% scholarships and no one is turned away for lack of funds.

      Do I need prior experience?

      Pro engineering. Built for working engineers.

      What do I get when I enroll?

      Live sessions with the instructor, access to course curriculum materials, community access via our Matrix chat server, and recordings of all sessions.

      Want to schedule this course for your team?

      Contact us: [email protected]