How to use AI agents at work

🧠 Knowledge Series #60: Practical AI agents you can build and use at work. Apply for jobs, conduct market research, draft speaker notes for presentations and more.

🔒The Knowledge Series is available for paid subscribers. Get full ongoing access to 60+ explainers and tutorials to grow your technical knowledge at work. New guides added every month.

---

Hi product people 👋,

At last week’s CIO Summit hosted by the Wall Street Journal, 61% of attendees said that they’re currently experimenting with AI Agents - but 21% said that they’re not using them at all.

Given that this summit was attended by some of the world’s leading technologists - including the CTO of OpenAI - it’s hardly surprising that the majority of folks said that they’re currently experimenting with their use. But the fact that nearly a quarter of them admitted that they aren’t using them at all tells us that there’s plenty of healthy scepticism relating to their use at work.

In this Knowledge Series, we’re not going to spend too much time debating whether AI agents will become the disruptive force some are predicting. Instead, we’re going to look at some of the practical ways you can use AI agents at work right now for product related tasks like conducting market research, analysing your competitors' tech stack, finding your next job and more.

Coming up, how to use AI agents at work for these practical use cases:

1. Understand your competitor’s tech stacks

2. Find and apply for new jobs and update your resume

3. Draft speaker notes for an upcoming presentation

4. Conduct market research and analysis

5. Assign work to AI agent developers

---

The Knowledge Series

We previously touched upon some of the technical approaches to building AI agents that product teams can choose. As a quick recap, the three most common ways AI agents are built include:

1. Use an existing framework

2. Building from scratch

3. Using no code or SaaS solutions

In this Knowledge Series, we’re going to focus on the third option which involves using no code and SaaS products. These will include products like Gumloop, Zapier, Microsoft Copilot and others.

Let’s take a look at the first AI agent use case: creating a competitor tech stack report.

Create a competitor tech stack report

If you’ve not heard of Gumloop before, they’re a new startup that recently raised over $17 million in funding to power their workplace automation platform. The product works a little bit like Zapier with AI powers and at the heart of their value proposition is the ability to create AI agents that can perform a series of different tasks.

You can sign up for a free account which includes a bunch of free credits to experiment with and in this example we’re going to use Gumloop to create an AI agent that creates a competitor tech stack report.

How this AI agent works

This agent includes a series of workflow automation steps that allow us to create a fully completed competitor tech stack report. The agent’s steps include scraping the web for information, passing it through to Builtwith for analysis and using LLMs like Claude and ChatGPT to analyse tech stacks and output the results.

Here’s a video of it in action:

In this example, I’ve asked it to visit the linear.app website and provide me with a report of their tech stack. It takes a little while but you can see that the end result is a fully fledged competitor analysis report that includes things like:

1. Programming languages

2. Javascript libraries and frameworks

3. Mobile optimization information

4. Payment providers

5. CDNs

This agent is then saved into my dashboard in Gumroad and can be scheduled to run on whatever cadence I decide. I’m also able to link this to a spreadsheet of all of my competitors and ask the agent to run the same report across multiple different products.

2. Find and apply for new jobs, keep track of your work to add to your resume

Finding a job can feel like a job in itself. With layoffs impacting many folks in tech, so much more of our time is now spent on the job application and preparation process.

And if there’s one use case that AI agents are especially good at, it’s the repetitive procedural tasks that are associated with job searches.

In this example, we’ll create an agent that can not only help us find job vacancies at companies we want to work for - but also keep track of our achievements at work so that our resume is always up to date with our most recent workplace achievements.