AI Engineer · Video summary
Agentic Engineering: Working With AI, Not Just Using It — Brendan O'Leary
Shift from using AI tools to collaborating with AI agents by mastering context management and adopting a research-plan-implement workflow for higher leverage.
Watch on YouTube ↗Key takeaways
- 💡The paradigm shift is from using AI as a tool to working with AI as a collaborator, akin to a junior developer who is fast and knowledgeable but lacks judgment and business context.01:50
- 🚀Treat AI agents as enthusiastic but naive junior developers; delegate tasks while retaining judgment and providing clear, specific context.03:14
- 🎯Context engineering is crucial for AI agents; more context doesn't always mean better results and can even degrade performance beyond 50% context window utilization.04:37
- 🔍Bad context, such as mixing unrelated tasks or using outdated information, can poison the agent's output and lead to incorrect or irrelevant results.06:00
- 🚀Managing context involves persisting information outside the window, being selective about what's included, and summarizing/compressing context as tasks evolve.07:16
- 🔧Actively manage AI context by persisting key information externally, being highly selective about what is fed into the agent, and summarizing/compressing context periodically.07:16
Chapters
- 0:00🎯 Introduction to Agentic Engineering
- 1:16🎯 The Evolution of AI Tools in Coding
- 2:30🎯 Working with AI as a Collaborator
- 4:29🎯 Managing Context in AI Collaboration
- 7:12🎯 Strategies for Context Management
- 11:38🎯 The Research, Plan, Implement Loop
- 13:50🎯 The Ask Mode for Research
- 15:30🎯 Creating and Reviewing Plans
- 16:14🎯 Executing Changes with a Clear Plan
- 17:24🎯 The Value of Human Thinking
- 17:44🎯 Configuring and Optimizing Agents
- 19:38🎯 Tools for Workflow and Documentation
- 21:21🎯 Tools for Contextual Workflow
- 21:42🎯 Configuring and Customizing Agents
- 22:51🎯 Multi-Tool MCP and External APIs
- 25:44🎯 Review and Iteration Process
- 26:37🎯 Conclusion and Final Tips
The digest
High Level Overview
This exploration of agentic engineering highlights the essential shift from merely using AI as a tool to actively working with AI as a collaborative partner in software development. Brendan O'Leary emphasizes that while most engineers use AI methods like autocomplete, few deeply understand or optimize the interplay between human judgment and machine-generated output. This video is crucial for engineers, managers, and technical leaders seeking to harness AI’s full potential for productivity and quality by adopting new workflows and mental models informed by AI’s evolving capabilities.
Keep reading in The Digest
The full 5-minute article, 11 more sections, and every new episode from AI Engineer and the creators you follow.
- Understanding the Paradigm Shift in AI Engineering
- From Tools to Collaborators (0:00–3:10)
- Agentic Engineering Defined: Working With AI (3:10–4:20)
- Tactical Approach: Context Engineering (4:20–8:50)
- The Art and Science of Context Management
- Best Practices for Managing Context
- Core Workflow: Research → Plan → Implement Loop (11:40–17:15)
- Agent Configuration and Customization (17:20–22:10)
- Integrations and Tools Beyond the IDE (22:10–24:45)
- Practical Implications & Takeaways
- Action-Oriented Summary
More from AI Engineer
Training an LLM from Scratch, Locally — Angelos Perivolaropoulos, ElevenLabs
In this hands-on workshop, Angelos Perivolaropoulos from ElevenLabs guides participants through the process of training an LLM from scratch using basic libraries like Torch, emphasizing the importance of tokenization and model architecture in building effective language models.
Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase
In this workshop, AI Engineer Pedro Rodrigues discusses how to enhance agent performance at Supabase using skills—structured workflows that improve agent interaction and efficiency. He shares insights on creating, testing, and implementing these skills, highlighting their significance in the development of agent-friendly applications.
Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick
In this workshop, AI Engineer Chris Parsons introduces Ralph Loops, a method for building simple AI workflows that enhance productivity by iteratively refining tasks, using real coding examples like a Pomodoro timer. Participants learn to implement these loops practically, emphasizing the importance of context and feedback in AI-assisted coding.
Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked
In this video, Peter Werry from Unblocked discusses the importance of a context engine for AI agents, emphasizing how it optimizes task execution by providing relevant context and reducing cognitive load for users. He debunks common myths surrounding context engines and illustrates their effectiveness in enhancing productivity and understanding within organizations.
Context Is the New Code — Patrick Debois, Tessl
In this talk, Patrick Debois presents the concept that context is the new code, emphasizing the importance of creating, testing, and distributing context in the software development lifecycle, particularly when using AI coding agents. He advocates for a systematic approach to context development that involves generating reusable prompts, evaluating their effectiveness, and leveraging feedback to improve overall coding practices.
Mastering AI Pricing: Flexible & Agile Monetization — Mayank Pant, Stripe
In this video, Mayank Pant from Stripe discusses the challenges and strategies of AI pricing, emphasizing the need for hybrid pricing models that adapt rapidly to changing features and customer needs, allowing companies to maintain competitive margins while fostering customer trust and engagement.