Courtesy of Brandon Pedersen
- GoTo engineer Brandon Pedersen says people should never blindly trust AI-generated work.
- Pedersen suggests that you ask AI for its sources, follow the links, and check its reasoning.
- He follows this two-second rule: If you can do it quickly yourself, skip the AI assistance.
This as-told-to essay is based on a conversation with Brandon Pedersen, a 41-year-old senior principal engineer at GoTo, based in the Salt Lake City area. The following has been edited for length and clarity.
As a senior principal engineer at GoTo, where I started working in 2013, I'm the technical lead of an AI enablement team responsible for maintaining AI platforms, creating new tools that help people do their jobs, and providing training and consulting support across the company.
On any given day, I could be helping train a team to write better AI prompts or automating parts of their workflow through an AI skill or a custom-built application. We also collect use cases from people across the company who want to automate tasks. We evaluate what will have the biggest impact on the business and decide what's worth automating and how we can help enable teams to build their own applications.
I also look at the architecture and systems involved in what we build across other teams. Since I've been at GoTo for a while, I'm able to work across departments, such as marketing and sales, to connect the pieces.
Here are some of my tips for deciding when to use AI, based on my experiences.
1. Don't trust AI blindly
From the beginning, whether it was generating a single line of code or a simple function, I've always reviewed AI's output because there were a few mistakes here and there. I think those mistakes have decreased in the smaller use cases, but they still show up in larger ones.
Compared to three years ago, when I started working heavily on AI, I trust that our AI tools, including Claude Code and GitHub Copilot, can get meaningful work done for me, allowing me to build larger-scale solutions, create bigger presentations and web pages, and help with entire applications. My confidence in AI's ability to handle larger tasks has greatly improved.
2. Be precise with your prompts
When I look at an AI output, I assume there's probably something in it that could be improved, clarified, or corrected. That doesn't mean it isn't useful; it means I approach it with a critical mindset.
I've always viewed AI through the lens of an experienced engineer, having spent a lot of time reviewing code and pull requests, and catching changes others might miss.
I've found this same attention to detail useful when evaluating AI's outputs. I saw what these tools produced, the mistakes they could make, and how small changes in a prompt's wording can completely change the output. Once I understood that, I became more intentional about when to use AI, how to use it, and how much trust to place in its responses.
3. Do the mission-critical work yourself
I was tasked with building our internal AI governance policy. At first, I thought we could use one of the publicly available industry standards, ask AI to collect the information, and generate a solid draft policy for us, but I chose not to do that. I knew this policy would be shared internally, that there would be critical reviewers of the document, and that I would need to explain and defend every word of it.
When you ask AI to generate documents like that, it can produce something that looks pretty good on the surface, but once you start to analyze it more closely, you realize that it doesn't always make sense in the day-to-day reality of how your business operates.
In this case, I decided to write the policy myself and use AI to help with things like diagrams and supporting artifacts that made the concepts easier for people to understand, rather than the actual policy language.
4. Know when to delegate — use the two-second rule
There are certain things I see people try to automate that would take them two seconds to do themselves. I would not use AI for personal communication with others. We don't want to become a proxy for an AI model. If someone asks you a question, they could ask AI themselves, but they're looking for your input and don't want to feel like they're talking to a machine.
I also would not use it to make judgment calls about people — not just because of legal risks, but because AI doesn't share our values or have the full context.
You don't need to automate everything in your work. There are plenty of things you could automate with AI, but you end up wasting time and resources fighting with the tool, waiting for it to respond, and working through the process when you could've just done it faster yourself.
5. Validate and verify factual claims
I've also learned that sometimes you need to push back on AI rather than accept its final answer. One of the best examples of that came from a training our finance group shared more broadly across the organization. The advice was simple: when AI gives you an answer, ask it for the sources of its information, follow the links, and check the logic.
I recommend doing this mostly for questions you're worried about, especially for unfamiliar subjects, because you don't know what you don't know. Even just having the mindset of being suspicious of the output, not assuming it's smarter than you, and not being blinded by the impressiveness of the response is good because then you won't miss if it starts leading you astray.
Even if you're not completely sure it's wrong, it helps to challenge it and say, "I don't think that's right, show me your sources." Sometimes it will catch itself and correct its own answer. If you want to be more intentional with AI starting now, that's a very practical first step.
6. Start experimenting today
Once people actually start using AI, they get excited. In 30 or 40 minutes, they can sometimes solve a problem they've been stuck on just by using straightforward language to describe what they want done. That makes people feel empowered to make changes themselves, maintain what they've built, and then share those ideas with others.
As we look to the future, AI will advance in capability, speed, and intelligence, and it will likely make fewer mistakes, but it will remain our job to bring our own judgment, critique, and values to get the most from it.
Read the original article on Business Insider