This is the third in a series of blog posts about How to build with GenAI- From strategy to implementation. In this series, we will explore the following questions:
- Is GenAI the right strategy for your product roadmap?
- Should you build or buy your GenAI model?
- How do you navigate the complexity of data to deliver clear results?
- Should you take a Human-in-the-loop approach?
- How do you manage costs while developing with GenAI?
***
Choosing the right AI approach is just the beginning. Once you’ve decided whether to build, buy, or fine-tune, the next step is applying it effectively to solve real-world problems.
For Yotascale, that meant tackling one of the biggest challenges in cloud cost management: complexity. Helping users sift through mountains of data, identify patterns, and make informed decisions isn’t easy—but it’s where Gen AI shines.
As Jeff Harris, our Director of Strategy and Operations, puts it: “It’s not about removing complexity altogether—that’s often impossible. It’s about helping users navigate it in ways that feel simple, intuitive, and empowering.”
Here’s how we’ve approached using Gen AI to turn complexity into clarity—and what we’ve learned along the way.
Meeting Users Where They Are
Complexity in cloud cost management is a given, but users shouldn’t have to feel overwhelmed by it. At Yotascale, we use Gen AI to simplify workflows by anticipating what users need and making their interactions with data more seamless.
For example, when users want to understand cost drivers, they often face a maze of filters, tags, and attributes. Instead of asking them to navigate that maze manually, we use Gen AI to let them ask natural questions like, “Which business units are driving costs this quarter?” The AI then translates that query into an API call, retrieves the data, and delivers a clear, actionable response.
As Jeff explains: “By reducing the number of clicks and decisions users have to make, we’re not just saving time—we’re helping them feel confident they’re getting the answers they need.”
Adding Context for Smarter Responses
One of the keys to making Gen AI work is injecting the right context at the right time. Without it, even the best models can struggle to deliver accurate results.
Jeff Harris, our Director of Strategy and Operations, shares: “When we first started, the AI didn’t understand the specific context of our users’ data. It couldn’t tie their questions back to cloud computing or the custom business tags they’d entered into Yotascale. We had to figure out how to provide that context dynamically.”
To solve this, we designed a system that feeds relevant organizational data—like business units, team structures, and cloud-specific tags—into the AI’s prompts. This ensures every response is tailored to the user’s unique environment.
The result? Smarter, more relevant answers that make it easier for users to tackle complex problems.
Iterating Toward Better Solutions
Simplifying complexity isn’t a one-and-done process. It requires continuous iteration, guided by real user feedback.
As Jeff explains: “Our initial AI implementation was focused on one use case—answering cost-related questions. Once we saw how users were interacting with it, we started identifying new opportunities, like creating custom filters or flagging anomalies automatically.”
By starting small and iterating based on user needs, we’ve been able to expand Gen AI’s capabilities in ways that deliver real value.
Key Takeaways
If you’re using Gen AI to tackle complex workflows, here are a few lessons we’ve learned:
- Inject Context Dynamically: Provide the AI with the data it needs to deliver smarter, more tailored responses.
- Focus on Pain Points: Start by addressing specific user challenges, then expand your use cases over time.
- Embrace Iteration: Every interaction is an opportunity to improve—listen to your users and refine accordingly.
Looking Ahead
Simplifying complexity is just one piece of the puzzle. In our next post, we’ll explore the importance of keeping humans in the loop—how combining AI efficiency with human judgment creates smarter, more trustworthy solutions.
