aggregate intellect

Cohort 1

Cohort 2409

Cohort-2501

Cohort-2505

Cohort-2507

2510

2601

2603

This document serves as a guide for developing your agentic product. It is designed to help you systematically define your product's goals, requirements, and implementation strategy. By working through each section, you will refine your product idea, identify potential challenges, and develop a comprehensive plan for building and deploying your solution.

Agents Playbook v2506

This document serves as a guide for developing your agentic product. It is designed to help you systematically define your product's goals, requirements, and implementation strategy. By working through each section, you will refine your product idea, identify potential challenges, and develop a comprehensive plan for building and deploying your solution.

Agents Playbook v2504

Are you interested in building LLM Agent Products, but unsure where to begin, or if you have the necessary background knowledge? We have curated this learning path using 70+ hours of (mostly) free resources that you can use to:<ol><li>Get started on your journey of building LLM Agent Products</li><li>Prepare to get the most of this course or similar ones, and</li><li>Evaluate areas where there's a gap in your knowledge</li></ol> After entering your email, you will be directed to a Miro Board. Contact maven@ai.science if you have any issues with this resource.

LLM AGENTS - Learning Path

This isn't just another course. You'll walk away with tangible assets that advance your career and concrete skills that set you apart.

Founder at Aggregate Intellect

Amir Feizpour, PhD

10+ years in AI and Product Development

AI Agents for Pragmatic Builders - Claude Code, LangGraph, n8n

Photonics Researcher

Product Manager

Software Developer

Game Developer

Director, Risk Models & Data Science

Manager, Data Scientist

Dev Lead

Researcher

founder of my company

Note 1: Join my next <a target="_blank" rel="noopener noreferrer nofollow" href="https://calendly.com/amirfzpr/agents-office-hour">Agents Office Hour</a> and ask about this bootcamp.Note 2: If you are interested in a mentorship version of this bootcamp, reach out to <a target="_blank" rel="noopener noreferrer nofollow" href="https://mailto:bootcamp@ai.science">bootcamp@ai.science</a> 🟢 WHAT DOES SELF-DIRECTED MEAN?It means that you consume the material we curated, build, and demo every 2 weeks while tapping into our help with any issues you face asynchronously via Slack. To make this as smooth as possible, we have set up all our coaching material and resources for common issues as Claude Code skills that will be available to you 24/7 as you learn and build. Sprint demos will be live and interactive.🟢 WHAT WILL I BE ABLE TO BUILD?You’ll build a functional application powered by LLM agents for a use case of your choice. Along the way, you'll learn to design agentic systems, and integrate required tools. By the end of the program, you'll have a working application ready to showcase in a public demo.▶️ <a target="_blank" rel="noopener noreferrer nofollow" href="https://tinyurl.com/llm-agent-demos">Playlist of previous public demos</a> 🟢 WHAT SHOULD I EXPECT TO HAPPEN DURING?Think about it like this: This is a 3-sprint product development + 1 week of prep for the public demo.🖌️ SPRINT 1 - DESIGN (wk 1 &amp; 2)🔨 SPRINT 2 - DEVELOP (wk 3 &amp; 4)🚢 SPRINT 3 - DEPLOY (wk 5 &amp; 6)🎭 PUBLIC DEMO (wk 7)

Self-directed Program to Help You Build an Agent-based MVP

How to identify opportunities for building AI agents

A Complete AI Agent Application

Real-World AI Agent Skills

Systematic Agent Development Process

Recommended but not required: eg. Claude Code

Coding co-pilots

No-code App Building

Recommended but not required: eg. LangGraph

Python Coding

Biz or Tech Entrepreneurs - You want to build an agentic MVP to test the feasibility of your startup idea.

Hands-on Product or Operations Managers - You want to build an agentic MVP to explore a new feature in your existing product / process

Developers, Data Engineers, Data Scientists - You want to build an agentic MVP to demonstrate your skills for career progression purposes.

Build Agentic Apps Using Claude Code & Bootcamp Info Session

Amir Feizpour

Founder @ Aggregate Intellect

Assess if agentic approach is appropriate for your use case.

Design agentic workflow for your use case.

Implement your agentic workflow using Claude

Leave with some workflow files you can immediately use

Learn more about our 7-week program to help you build

Building AI Agents: Bootcamp 2601 Public Demo

What agentic systems can be built in 7 weeks

Skills necessary to build agentic systems

Tool stack involved in building agentic systems

How our 7-week program helps you build an agentic system

How you can go from a vague idea to a working MVP

Claude Skills - A Mental Model for Builders

Mohsin Iqbal

Sr. MLE @ Alethia AI

A conceptual breakdown of skills beyond surface-level documentation.

What Agent Skills Really Are

How skills are discovered, loaded, expanded into prompts, scoped, and executed.

The Skill Lifecycle

How Claude integrates skills into its reasoning process and decision-making.

Reasoning and Behavior Shaping

Frameworks that make complex agent systems easier to reason about and debug.

Mental Models for Agent Design

Agentic Long Loop Workflows That Solve Real Problems

Kris Hansen

Founding Engineer @ Erebor Bank

What distinguishes workflows that persist and adapt over many steps from simple one-shot agent tasks.

Understanding Long Loop Workflows

How to structure complex tasks into reusable, version-controlled pipelines using human-readable definitions.

Declarative Workflow Design

Techniques for managing loops, conditions, and agent-driven decisions that adapt as context changes.

Iteration, Branching & Decision Logic

Patterns for orchestrating multiple agents—each with unique skills—to collaborate on large problems.

Multi-Agent Coordination

The Killer App of AI Is Context

J Nicholas Tolson

Founder @ Razzo AI

Understand the four-layer framework (Company, Department, Project/Client, Role) and what belongs in each.

What a Context Profile Is

Why improving inputs isn’t about writing smarter prompts—but about supplying richer context.

From Prompt Engineering to Context Engineering

How to deploy a lightweight version immediately using project-based knowledge files.

Simple Implementation for SMBs

Considerations for governance, maintenance, and scaling context systems across teams.

Building Context Infrastructure

AI + Quantum: What’s Actually Happening?

Kris Kaczmarek

Investor at QDNL

How quantum computing and agentic AI are overlapping and what that means in the near term

Hybrid AI–Quantum Architectures

Where quantum and AI might offer advantages to each other

Use Cases and Constraints

The gap between research progress and deployable systems—and what to watch over the next 3–5 years.

Commercial Reality Check

Explain Like I’m a Designer; Design Principles for Agents

Ruth Birman

Advisor @ Open North

How clearly articulated aesthetic and structural constraints improve agent performance.

Design as Constraint

Why describing intent via design language (style, hierarchy, motion) produces stronger outputs than generic instructions

From Prompting to Art Direction

Techniques for guiding agents toward a consistent visual identity rather than fragmented components.

Style Specificity and Cohesion

Understanding the limits of current models in transitions, motion, and nuanced creative execution

Where Agents Struggle

How to incorporate AI into a professional design-to-development pipeline without sacrificing control or quality.

aggregate intellect

aggregate intellect

Courses

Lightning Lessons

Resources

Reviews