How to Use AI to Become a More Effective Engineering Leader

How to Use AI to Become a More Effective Engineering Leader

An adapted chapter from my book “The Multiplier Mindset”, published by O’Reilly.

Gregor Ojstersek

Oct 20

This newsletter is sponsored by Atono.

AI is definitely making engineers ship faster than ever. But AI-generated specs keep coming back with questions. And the problem is the missing product context, understanding in detail, how the product should actually work.

In this recorded webinar from Product School’s AI Builder Week, Doug, CPO at Atono, shows how important giving AI real product context is.

In the webinar, you’ll learn:

• Why your AI keeps guessing and how product context fixes it

• How to ground AI in your actual product decisions and architecture

• When your spec is actually ready to hand off to engineering

Get the recording

Thanks to Atono for sponsoring this newsletter. Let’s get back to today’s thought!

Intro

A lot of engineering professionals may think that writing (generating) code is the best use case for AI. But some of the biggest opportunities are actually outside of coding. Preferably, even before the coding starts.

And especially as an engineering leader, the more you grow in your career, the more of your impact comes from making better decisions, communicating effectively, helping others grow, and removing bottlenecks.

And AI can help you with all of these things.

In this article, I’ll share 5 practical ways you can use AI beyond coding to become a more effective engineer and engineering leader, with examples you can start applying right away.

Let’s start!

My book “The Multiplier Mindset” has just became a Bestseller! 🥳 🎉

This article is an adapted version of one of the chapters of my book called “The Multiplier Mindset”, published by O’Reilly.

I announced the e-book (Kindle) version and pre-orders on Friday, last week, and the book is already a #1 New Release and Bestseller on Amazon in 3 categories 🤯

And the print version of the book hasn’t even been released yet, it will be on October 31st!

I am overwhelmed by the interest and how many copies have already been sold and pre-ordered, thank you SO much! 🙏

Learn more about the book

Communicate More Effectively

A lot of engineering is about communicating and aligning with others: colleagues, stakeholders, the PM, and your manager. You can use AI to perform the following communication tasks by writing prompts like the ones in the examples.

Drafting design documents

You may know about the blank page syndrome, and the gist is that it’s always easier to start with something already, instead of staring at an empty Google docs, Notion, or any other page.

And if you and your team have been discussing about a certain feature, it’s much easier to feed the context of the conversation to AI and create the design document that way, instead of starting from scratch!

You can use this prompt:

Turn these notes into a design document. 
Include the problem,proposed solution, alternatives considered, trade-offs, risks, 
and open questions. 
Create diagrams where appropriate.

Improving technical specs

What I like to say: What seems clear to you may not be clear to others. AI can help you find your blind spots, edge cases that you are missing, or any incorrect or missing assumptions. Always remember the following:

The most expensive change is the one you realize you need after the code has already been written (generated).

You can use this prompt:

Review this spec for anything that is unclear, ambiguous, or missing. 
Pay particular attention to assumptions and edge cases.

Summarizing long documents

The more you grow in your career, the more projects you’ll be involved in, and it’s impossible to understand (or go over) every single detail, so you need ways to make your life easier. And using AI to summarize longer documents is a great way to do it.

You can use this prompt:

Summarize this document for an engineering leader. 
Give me the key decisions, risks, open questions, and anything that requires my attention.

Preparing for important meetings

Whether you’re preparing for an architecture discussion meeting or getting buy-in from the stakeholders on a new initiative, AI can help you gather your thoughts, provide discussion points, questions, and overall key points to cover.

You can use this prompt:

Based on this context, help me prepare for the meeting. 
Identify the key points I should cover, questions I should ask, decisions we need to make,
and potential areas of disagreement.

Adapting your communications for nontechnical audiences

Adjusting your communication based on who the target audience is crucial and can be the difference between successfully getting buy-in on a new project or not.

I always suggest “reading the room”, which means understanding what motivations and problems the stakeholders are dealing with, and focusing on explaining things in a way that would resonate with them.

You can use this prompt:

Rewrite this explanation for a product and business audience. 
Remove unnecessary technical details but keep the impact, tradeoffs, and risks clear.

These are some examples of how you can use AI to communicate more effectively.

The important part is that AI helps you communicate your own thinking; it shouldn’t do the thinking for you. You still need to decide what matters, what you want to communicate, and whether the final message accurately represents your view.

Find Relevant Internal Information Quickly

A lot of engineering work involves simply finding information. Manually searching Slack, Jira, GitHub, and Notion (or whatever your organization uses) can take a long time.

I’ve seen different companies address this issue by having a shared knowledge repository that brings together information from various sources. This repository normally lives on GitHub or GitLab, and it’s version-controlled.

This doesn’t necessarily mean you need to copy everything into one place. You can also connect your existing tools and continuously index through the sources of these tools.

The goal is to give AI one place to search across your organization’s knowledge, so that you don’t have to open five different search tools. Once you have all the knowledge in one place, you can use prompts like these to get the information you need:

Why did we decide to use PostgreSQL for this service? Find the relevant
discussions, design documents, and pull requests, and summarize the
reasoning.

What did we decide about the authentication migration in last month's
meetings, and who owns the follow-up actions?

Having a shared knowledge repository is very useful in situations like these, as such information often gets scattered across different tools and nobody really knows how to find it when they need it.

Using AI to search a shared repository can save a lot of time, especially if you are part of a larger organization where many different things can happen at the same time and it’s impossible to be on top of everything.

Here are (quoted) words from Anton Zaides, who is an Engineering Manager at Honeybook, on such a repo being extremely useful to him:

Meeting transcripts automatically sync into the repo. The repo connects to Slack and can summarize discussions. There are markdown files organized by topic that automatically sync to Notion as we work on them. The repo becomes a living, queryable record of the project, not just our decisions but our thinking.

When I want to get up to speed on a specific part of the project, I just talk to Claude. I can ask what specific people think about a given decision, and I’ll get an accurate answer grounded in the Slack threads and meeting transcripts.

Instead of scheduling 10 conversations to understand where 10 people stand, I can ask one tool to figure it out for me in minutes.

Coach and Lead Your Team

AI can help you be a better coach and mentor to your team, but make sure that you use it in the right way.

It shouldn’t replace your judgment, which means that you still need to understand your people, build trust, and make the final decisions yourself. Let’s go through some examples next.

AI can act as a thinking partner when you’re dealing with challenging situations. You can use it to role-play difficult conversations, explore different approaches to giving feedback, or brainstorm ways to help overcome certain challenges that your people are facing.

The more you grow in your career, the more you need to focus on making everyone around you better, and that takes a lot of preparation. AI can help you prepare for one-on-one meetings by generating discussion points and action items, reviewing promotion packets, and even help you prepare for performance reviews.

But at the same time, its really important to understand that AI should help you become a better leader, not replace your judgment.

Additionally, be very careful about using AI note-taking tools during one-on-ones. In most cases, I recommend avoiding recording or transcribing these conversations altogether.

One-on-ones should feel like a safe, private space where people can open up about wins, struggles, concerns and frustrations.

Even if you ask for permission, a direct report may not feel fully comfortable saying no to their manager. Knowing that everything is being transcribed can also make people a LOT less willing to share what they really think.

A safer approach to write down your own notes and use AI to help organize or summarize them without creating a full transcript of what was said.

Make Better, More Data-Driven Decisions

During my recent visit to the OpenAI offices in San Francisco, I talked to engineers and engineering leaders. I asked them, “What do your dashboards look like, and what tools are you using?”

Interestingly, they said that while they do use some external tools, they mostly use their internal data agent to help everyone in the company make data-driven decisions.

Anyone inside OpenAI can ask data-related questions and get the insights they need to make data-driven decisions.

They don’t need to go to the data engineers and ask them to generate another dashboard; they can simply ask the data agent.

Some use cases include the following:

• Reviewing metrics

• Identifying bottlenecks and specific issues

• Analyzing user behavior

• Creating dashboards

• Evaluating trade-offs

That's a really great use case to help everyone inside the company make better, data-driven decisions (including yourself).

Automate Repetitive Work

Try to automate anything that doesn’t require human judgment. Every hour you save on repetitive work is an hour you can invest in higher-leverage activities, like mentoring your team or solving problems.

For example, many companies automate part of incident reporting, with AI collecting information about incidents from alerts, logs, Slack discussions, deployment histories, and recent commits.

This would take an engineer hours to gather. An AI agent does a good job (in my experience) of reconstructing timelines, summarizing what happened, and identifying possible root causes, as long as it’s given access to all the relevant data.

The engineer can then review the agent’s draft, make adjustments, determine the root cause, evaluate the team’s response, and possibly decide on specific changes to the system and processes.

This is just one example. Other highly valuable tasks you can automate include the following:

• Turning incident report action items into Jira/Linear tasks

• Setting up automatic proposed updates of your libraries in your repositories (after you have implemented any relevant changes to the code)

• Setting up reminder emails, alerts, or Slack notifications for specific purposes

• Running code formatting, linting, and other routine checks

• Automating any manual filling out of forms

• Updating tickets with progress from commits and pull requests

• Making recurring status updates from completed work

• Keeping documentation or changelogs updated after releases

• Collecting information from several systems and putting it into a standard report

There are many more ways AI can help you automate repetitive work, and you just need to investigate and determine where such work creates bottlenecks so you can find better solutions.

Last words

Let’s end this article with the following:

Always keep in mind that AI is like any other tool, it’s just more powerful. It can help you generate ideas, code, or give feedback, but you’re still responsible for deciding what’s correct and what really matters.

LLMs and overall tooling for AI will keep getting better, but the goal will always stay the same. To create more value for your team, your organization, and the customers.

You got this!

Liked this article? Make sure to 💙 click the like button.

Feedback or addition? Make sure to 💬 comment.

Know someone that would find this helpful? Make sure to 🔁 share this post.

Whenever you are ready, here is how I can help you further

• Interested in sponsoring this newsletter? Check the sponsorship options here.

• Check out my book “The Multiplier Mindset” coming out later this year, here.

• Take a look at the cool swag in the Engineering Leadership Store here.

• Want to work with me? You can see all the options here.

Get in touch

You can find me on LinkedIn, X, YouTube, Bluesky, Instagram or Threads.

If you wish to make a request on particular topic you would like to read, you can send me an email to [email protected].

This newsletter is funded by paid subscriptions from readers like yourself.

If you aren’t already, consider becoming a paid subscriber to receive the full experience!

Check the benefits of the paid plan

You are more than welcome to find whatever interests you here and try it out in your particular case. Let me know how it went! Topics are normally about all things engineering related, leadership, management, developing scalable products, building teams etc.

© 2026 Gregor Ojstersek
548 Market Street PMB 72296, San Francisco, CA 94104