# Colin Kolano on building an AI agent system

URL: https://start.joinautopilot.com/journal/colin-kolano-interview
Updated: 2026-11-16

Colin Kolano is a small business owner who got into agentic AI out of necessity. Colin's business could not afford full marketing or accounting staff, so Colin built an AI agent system to read local news for leads and draft outreach instead.

[Open it in the Autopilot app.](https://link.joinautopilot.com/eXKr?c=colin-kolano-interview&af_sub1=intro) https://link.joinautopilot.com/eXKr?c=colin-kolano-interview&af_sub1=intro

Kolano's interest in AI agents began with the practical demands of a small business. In the interview, he describes building a system to read local news and draft replies, then using that experience to explore the computing infrastructure behind AI agents, including memory, bandwidth and photonics.

That system became the starting point for Colin's investing. An agent Colin built reads hundreds of news articles a day looking for the infrastructure behind the AI buildout, memory, photonics, bandwidth, and Colin does further research before deciding what goes into the Portfolio. Colin also publishes a Portfolio built around autonomous warfare, watching drones change how militaries spend money.

Colin publishes Agentic AI Backbone, Autonomous Warfare and Intentionally Lucky on Autopilot. We talked about small business, building an agent system from scratch, and what a retail investor can do that an institution can't.

This interview comes from the transcript of our conversation with Colin Kolano in June 2026. It has been edited and condensed.

### Who are you, and how did you get into investing?

Early on I've been investing since I was 14 years old, so I was just a kid who wanted a Lamborghini and was looking through YouTube and wanted to find the best ways to make money. Obviously, in high school, I was not the best trader. I was looking at how to day trade and pick penny stocks, and I was pretty terrible at it. It really took a long time to figure out that I just needed to trust good companies and really trust myself and figure out where the world's headed. I stopped looking at technicals completely.

### What's your background, and how did it lead to your first Portfolio?

What got me to the Agentic AI Backbone Portfolio was I work in small business, so we don't have enough money to do full marketing or full accounting. I went down that rabbit hole and did things that I never thought were possible. They would have cost tens of thousands of dollars, and we simply couldn't afford it. So I was looking to invest in agent AI really becoming a big thing and expanding to other businesses. That's what got me to that portfolio.

### What problem did you build your first agent system to solve?

My biggest problem was we just couldn't scale with the appropriate marketing we had. We had marketing interns that were doing a good job, but we couldn't really pay a full time person to do our marketing. We have a lot of local business, so what that really entails is reading through the local newspapers, looking for new projects in our areas, and we just simply couldn't pay for people to do that. So I created an agent system to read the articles for me, draft replies, and reach out to the people that we need to. And that has saved us a lot of time and money.

### What convinced you that agentic AI was undervalued?

That's exactly how I discovered that agent AI was super undervalued. I think the average user is really just typing into a chat bot, and they're not setting up these 24/7 autonomous systems that are really doing the bulk of the work. What was undervalued for my investment so far was the average user was looking at what is the best model and who was going to have the best success and the best large language model. What they were missing is all of the stuff that is built and the structure behind that. Photonics is a good example. Memory is a good example. Bandwidth is a really good example of the things that I've been investing in for these agents to run 24/7, not just the occasional message to the large language model.

### How do you actually use the agent system day to day?

I built a system of agent AI that is running 24/7. It is reading around 600 to 800 news articles a day, figuring out what the actual bottlenecks are for the infrastructure, and it is giving a conviction score and ranking the technicals, and giving me that initial base of information. And then what I do is I do deep research on what it provides me, and then I put that into my portfolios.

### What can a retail investor do that an institution can't?

A retail investor can do whatever they want. They can use whatever technology they want. They can research whatever they want without any limitation. The average company is completely restricted by their IT departments shutting down certain connectors, and their security team is not letting them really evolve to get into the AI space the way that the retail investor can.

### Has the system gotten something wrong, and what did you learn?

AMD was the biggest thing that we missed. We have risk tolerances for the portfolio, and it purposefully left out AMD because we were too concentrated in the chip sector. Although it passed every single other technical factor, with flying colors, we left it out from a risk perspective. We are constantly going to tweak this portfolio and learn that we don't want to miss these big growth opportunities.

### What would it take a retail investor to do this on their own?

A retail investor would have to spend a lot of time figuring out how to set up these agent systems. It took me many, many weeks to figure out how to get to at least a starting point. If somebody hasn't done this before, it's going to take months of learning and months of fine tuning.

### What should retail investors watch out for when they get information online?

You can't get all of your information online. You can't trust too many people. There are really good creators out there that will tell you a lot, but you really have to make sure that you're looking at the right ones, and you need to be very diligent about who you're getting your information from. Everybody's throwing darts at the wall. Everybody sees the company go up and wants to hop on the wave. But that's not the right way to do things.

> "You need to be very diligent about who you're getting your information from."

## Follow Colin Kolano's Portfolios on Autopilot

[Colin Kolano publishes Agentic AI Backbone, Autonomous Warfare and Intentionally Lucky on Autopilot, an investing app that lets you follow Portfolios from investors, AI models, and public filings in your own brokerage account.](https://link.joinautopilot.com/eXKr?c=colin-kolano-interview&af_sub1=body) Visit [Colin Kolano's Pilot page](https://start.joinautopilot.com/strategies/pilots/colin-kolano-4215). https://link.joinautopilot.com/eXKr?c=colin-kolano-interview&af_sub1=body

Following a Portfolio on Autopilot works like this:

- You follow in the brokerage account you already have, and the money stays there.
- On Premium Tier, when the Portfolio changes, Autopilot Advisers sends the orders to your broker; on Basic Tier you get an alert.
- Review the Portfolio's method, holdings and any available performance record before following it. New Portfolios show return figures after 30 days.
- The Pilot sets the subscription price, there's a 0.00% AUM fee, and you allocate at least $500.

You're never trading at the same moment as Colin, and your account won't match the Portfolio exactly.

[Open it in the Autopilot app.](https://link.joinautopilot.com/eXKr?c=colin-kolano-interview&af_sub1=end) https://link.joinautopilot.com/eXKr?c=colin-kolano-interview&af_sub1=end

"Autopilot" refers to Autopilot Holdings Corp and Autopilot Advisers, LLC, an SEC-registered investment adviser. Agentic AI Backbone, Autonomous Warfare and Intentionally Lucky are managed by Colin Kolano, an independent Third-Party Pilot unaffiliated with Autopilot. Autopilot doesn't manage, validate, or guarantee this Pilot's portfolio. This interview reflects Colin's own views as of June 2026, edited and condensed, and isn't a recommendation to buy or sell any security or to follow any Portfolio. Individual stocks shown are illustrative and not a recommendation. Where a Pilot uses an AI tool in their own stock-selection process, that tool does not advise clients, select investments for clients, or place trades. Investing carries risk-including possible loss of principal-and past performance is not indicative of future results. Figures current as of 10/09/26. View our Customer Relationship Summary and other important info at [joinautopilot.com/disclaimer](https://joinautopilot.com/disclaimer).

## Portfolios and pilots mentioned in this article:
Colin Kolano: https://start.joinautopilot.com/strategies/pilots/colin-kolano-4215
3 public portfolios.
Agentic AI Backbone (Colin Kolano): https://start.joinautopilot.com/strategies/agentic-ai-backbone-995938
Returns as of November 16, 2026. Month -7.2%, 3 months -13.2%, YTD n/a, 1 year n/a, Since start +20.3%.
Autonomous Warfare (Colin Kolano): https://start.joinautopilot.com/strategies/autonomous-warfare-1011398
Returns as of November 16, 2026. Month -8.9%, 3 months -32.0%, YTD n/a, 1 year n/a, Since start -34.6%.

The performance data presented reflects the aggregated results of actual client portfolios managed by the Registered Investment Adviser (RIA), based on the trading activity in the securities contained in the relevant portfolio over the specified period. If fewer than 10 clients are invested in the portfolio, the data represents the aggregate performance of all clients following this strategy. Performance figures are shown net of advisory fees, calculated using the applicable subscription fee and an assumed $50,000 account size. Because subscription fees are flat rather than asset-based, accounts smaller than $50,000 would experience a higher effective fee percentage and lower net performance, while larger accounts would experience a lower effective fee percentage. Actual investor outcomes can vary due to factors like brokerage support for fractional shares, account size, trade timing, fees, and taxes, and past performance should not be interpreted as a guarantee of future results or typical of all portfolios.
