Get Good at Agents
📰 Interconnects
Adapting to work with AI agents requires a shift in approach, scoping, and management to maximize their potential
Action Steps
- Re-evaluate current work habits and approaches to identify areas where AI agents can be leveraged
- Learn to design systems and workflows that integrate AI agents
- Focus on high-level tasks and let AI agents handle sub-components and implementation details
- Cultivate a mindset that allows for more open-ended and ambitious task assignments to AI agents
Who Needs to Know This
Engineers, researchers, and product managers can benefit from understanding how to effectively work with AI agents to enhance their workflow and productivity
Key Insight
💡 The key to getting good at agents is to change how we scope, manage, and approach our work to maximize their potential
Share This
💡 AI agents are changing the game - learn to work with them to boost productivity!
Key Takeaways
Adapting to work with AI agents requires a shift in approach, scoping, and management to maximize their potential
Full Article
Published Time: 2026-01-21T17:05:15+00:00
# Get Good at Agents - by Nathan Lambert - Interconnects AI
[](https://www.interconnects.ai/)
# [](https://www.interconnects.ai/)
Subscribe Sign in
Discover more from Interconnects AI
The cutting edge of AI, from inside the frontier AI labs, minus the hype. The border between high-level and technical thinking. Read by leading engineers, researchers, and investors.
Over 63,000 subscribers
Subscribe
By subscribing, you agree Substack's [Terms of Use](https://substack.com/tos), and acknowledge its [Information Collection Notice](https://substack.com/ccpa#personal-data-collected) and [Privacy Policy](https://substack.com/privacy).
Already have an account? [Sign in](https://www.interconnects.ai/p/get-good-at-agents)
# Get Good at Agents
### The tools are getting so powerful that we need to change how we scope, manage, and approach our work.
[Nathan Lambert](https://substack.com/@natolambert)
Jan 21, 2026
218
14
48
Share
Article voiceover
0:00
-5:05
Audio playback is not supported on your browser. Please upgrade.
Two weeks ago, I wrote a [review](https://www.interconnects.ai/p/claude-code-hits-different) of how Claude Code is taking the AI world by storm, saying that “software engineering is going to look very different by the end of 2026." That article captured the power of Claude as a tool and a product, and I still stand by it, but it undersold the changes that are coming in _how_ we use these products in careers that interface with software.
The more personal angle was how “I’d rather do my work if it fits the Claude form factor, and soon I’ll modify my approaches so that Claude will be able to help.” Since writing that, I’m stuck with a growing sense that taking my approach to work from the last few years and applying it to working with agents is fundamentally wrong. Today’s habits in the era of agents would limit the uplift I get by micromanaging them too much, tiring myself out, and setting the agents on too small of tasks. What would be better is more open ended, more ambitious, more asynchronous.
I don’t yet know what to prescribe myself, but I know the direction to go, and I know that searching is my job. It seems like the direction will involve working less, spending more time cultivating peace, so the brain can do its best directing — let the agents do most of the hard work.
Since trying Claude Code with Opus 4.5, my work life has shifted closer to trying to adapt to a new way of working with agents. This new style of work feels like a larger shift than the era of learning to work with chat-based AI assistants. ChatGPT let me instantly get relevant information or a potential solution to the problems I was already working on. Claude Code has me considering _what should I work on_ now that I know I can have AI independently solve or implement many sub-components.
Every engineer needs to learn how to design systems. Every researcher needs to learn how to run a lab. Agents push the humans up the org chart.
[Share](https://www.interconnects.ai/p/get-good-at-agents?utm_source=substack&utm_medium=email&utm_content=share&action=share)
I feel like I have an advantage by being earl
# Get Good at Agents - by Nathan Lambert - Interconnects AI
[](https://www.interconnects.ai/)
# [](https://www.interconnects.ai/)
Subscribe Sign in
Discover more from Interconnects AI
The cutting edge of AI, from inside the frontier AI labs, minus the hype. The border between high-level and technical thinking. Read by leading engineers, researchers, and investors.
Over 63,000 subscribers
Subscribe
By subscribing, you agree Substack's [Terms of Use](https://substack.com/tos), and acknowledge its [Information Collection Notice](https://substack.com/ccpa#personal-data-collected) and [Privacy Policy](https://substack.com/privacy).
Already have an account? [Sign in](https://www.interconnects.ai/p/get-good-at-agents)
# Get Good at Agents
### The tools are getting so powerful that we need to change how we scope, manage, and approach our work.
[Nathan Lambert](https://substack.com/@natolambert)
Jan 21, 2026
218
14
48
Share
Article voiceover
0:00
-5:05
Audio playback is not supported on your browser. Please upgrade.
Two weeks ago, I wrote a [review](https://www.interconnects.ai/p/claude-code-hits-different) of how Claude Code is taking the AI world by storm, saying that “software engineering is going to look very different by the end of 2026." That article captured the power of Claude as a tool and a product, and I still stand by it, but it undersold the changes that are coming in _how_ we use these products in careers that interface with software.
The more personal angle was how “I’d rather do my work if it fits the Claude form factor, and soon I’ll modify my approaches so that Claude will be able to help.” Since writing that, I’m stuck with a growing sense that taking my approach to work from the last few years and applying it to working with agents is fundamentally wrong. Today’s habits in the era of agents would limit the uplift I get by micromanaging them too much, tiring myself out, and setting the agents on too small of tasks. What would be better is more open ended, more ambitious, more asynchronous.
I don’t yet know what to prescribe myself, but I know the direction to go, and I know that searching is my job. It seems like the direction will involve working less, spending more time cultivating peace, so the brain can do its best directing — let the agents do most of the hard work.
Since trying Claude Code with Opus 4.5, my work life has shifted closer to trying to adapt to a new way of working with agents. This new style of work feels like a larger shift than the era of learning to work with chat-based AI assistants. ChatGPT let me instantly get relevant information or a potential solution to the problems I was already working on. Claude Code has me considering _what should I work on_ now that I know I can have AI independently solve or implement many sub-components.
Every engineer needs to learn how to design systems. Every researcher needs to learn how to run a lab. Agents push the humans up the org chart.
[Share](https://www.interconnects.ai/p/get-good-at-agents?utm_source=substack&utm_medium=email&utm_content=share&action=share)
I feel like I have an advantage by being earl
DeepCamp AI