How Thinqpoint built real AI systems without the fluff

About

Thinqpoint

Thinqpoint is a healthcare analytics startup focused on delivering solutions that help safety net organizations maximize their impact serving underserved communities. Their AI-driven platform unlocks expert insights for federally qualified health centers, critical access hospitals, and community-based organizations, enabling them to improve decision-making and elevate service delivery.

We spoke with Bogdan Rau, Founder and CEO, about his journey taking Thinqpoint from an experiment with AI to a full agentic system capable of orchestrating complex, context-aware healthcare analytics.

Challenge

When raw API calls hit a wall

Thinqpoint is on a mission to democratize access to advanced intelligence for community health clinics, critical access hospitals, and organizations serving underserved populations. Founder Bogdan Rau, an epidemiologist by training, saw AI as a tremendous opportunity to close long-standing analytics gaps in community health.

He built a data visualization platform and tested whether AI could interpret thematic maps—a core need for community health analysis. His early experiments were promising, but they also exposed hard limitations. A single map interpretation took roughly 30 seconds, and each additional step in the analysis added more complexity. 

Without a framework, even simple AI-powered functionality required significant effort. Each new feature meant stitching together custom code, managing context by hand, and rethinking how analysis steps fit together. Progress was possible, but slow and fragile.

As Bogdan explained: "We built the first feature using Node.js, no framework, and a Gemini endpoint. There was a lot of heartache to just get it to run because there weren't any of the utilities you get with a framework."

Bogdan quickly realized he wasn’t just looking for faster API calls. He needed something fundamentally different. 

“We weren’t looking for API endpoints. We were looking for a way to orchestrate the work. It’s not just about what context you put in, but also when. We needed a framework that let us insert domain expertise at the right moments across a complex workflow. We wouldn't have been able to do that with any of the tools we evaluated back then, and the last thing I would have wanted to do is build that from scratch.”

As a first-time founder with a data science background (rather than a traditional software engineering background), Bogdan needed a solution that was powerful yet approachable, one that would let him move quickly, test ideas, and build toward a production-ready platform without requiring months of infrastructure work.

Decision

Picking pragmatism over flashy features

As Thinqpoint evolved beyond early prototypes, Bogdan evaluated several API approaches and supporting tools, including established frameworks such as LangChain and the OpenAI Agents SDK. While some offered flexibility, they also introduced significant complexity and boilerplate. Others required committing to a single model vendor. Bogdan was left with a growing sense that he would be spending more time managing infrastructure and vendor dependencies than improving the product.

He needed to narrow the field, and the first filter was clear: no vendor lock-in and no forced commitments.

Vendor lock-in was the first thing to rule out. Thinqpoint needed to remain model-agnostic as the AI ecosystem continued to evolve.

"Early on we had to make a decision: can we afford to choose a platform that locks us into one vendor? The answer was quickly no. And if not that, then what do you choose out of the sea of frameworks that are just now coming up?"

But flexibility without pragmatism still fell short. The platform had to enable real, production-ready work without unnecessary complexity.

In that search, Agno emerged as a very strong candidate.

Agno checked every box. The documentation was clear, the community was active, and there was no vendor lock-in. Most importantly, the framework focused on the fundamentals required to build real systems, rather than flashy features that fell apart in practice. It was simple to get started, pragmatic by design, and flexible enough to support more complex workflows over time.

"Agno became a really good candidate because it had the main things I was looking for: simple implementation, a community to help onboard, and pragmatism—not the fluffy language and cool features that sound great on paper but break down when you try to implement them.”

What sealed the decision was speed to validation. Within about a day, Bogdan was able to test Thinqpoint's core hypothesis: whether inserting domain-specific knowledge at strategic points in a workflow could meaningfully improve analytical accuracy. It wasn’t a finished product, but it was proof that the idea worked and that there was a clear path from experiment to production.

Conversations with the Agno team reinforced the choice. Rather than simply fielding usage questions, the team engaged in thoughtful discussions about how to solve real-world problems, offering architectural guidance and even incorporating Thinqpoint’s feature requests into their roadmap.

For Bogdan, Agno wasn’t just a framework. It was a foundation that let him focus on what mattered most: building a system that delivers fast, trustworthy insights for organizations working on the front lines of community health.

Solution

Orchestrating context, not just calling endpoints

To move beyond brittle prototypes and build a system capable of real analytical work, Bogdan adopted Agno as the foundation for Thinqpoint’s AI platform. The goal wasn’t to add a chatbot, but to orchestrate complex, multi-step analysis in a way that was fast to iterate, reliable in production, and sustainable for a nimble team.

Thinqpoint’s platform runs on Azure, using a combination of serverless functions and containerized services. It integrates both structured data, such as demographic tables and community health metrics, and unstructured content, including documents, reports, and thematic maps, all managed through a custom-built content management system.

Agno is deployed as a containerized service and plays two primary roles. On the backend, it orchestrates the end-to-end data analysis workflow, drawing from both structured and unstructured sources and handling tasks ranging from data validation and quality checks to the generation of analytical artifacts. On the frontend, Agno exposes the APIs that power the user-facing application. When a user submits a question or requests an analysis, Agno coordinates the underlying processes and returns results in a clear, actionable format.

By grounding Thinqpoint on Agno, Bogdan shifted effort away from infrastructure management and toward delivering real analytical value. Agno provided a pragmatic framework that enabled faster iteration, confident production deployments, and a platform designed to scale in both complexity and ambition.

Here are the highlights:

Rapid experimentation and validation

Agno's simplicity allowed Bogdan to move from idea to working prototype fast—critical for fast iterations of new concepts.

"With Agno, we can start an idea at the beginning of the week and have it into production by the end of the week with evals in place."

That speed wasn't just about shipping. It was about learning. "A lot of the features we ended up implementing started with 'I wonder if this would work," Bogdan says. “And that very quickly turns into, 'OK, how do we integrate it into our workflows?'"

This fast feedback loop allowed Thinqpoint to validate ideas early, discard what didn’t work, and double down on what did, without committing to months of engineering effort upfront.

Orchestration over endpoints

Rather than relying on one-off model calls, Agno enabled Thinqpoint to orchestrate entire analytical workflows. This included managing context, sequencing reasoning steps, validating data quality, and generating usable artifacts for end users.

As Bogdan described it:

“We needed more than one-off model calls that pass data in and get answers out. We needed a framework for orchestrating context. Not just what information the model sees, but when it sees it. Agno gave us the ability to strategically introduce the right pieces of information at the right moments across our workflows, so now we’re able to find the right timing when a piece of information is useful to the model to actually make a correct interpretation.”

This orchestration-first approach produced results that were more reliable, more explainable, and better aligned with real analytical work than simple prompt-and-response interactions.

Built-in tools for testing and debugging

AgentOS became a critical part of Thinqpoint’s development process. The chat-based interface allowed Bogdan to test agent behavior, refine guardrails, and evaluate tone, accuracy, and workflow logic without deploying changes to a full development environment.

"AgentOS is kind of the instant proof of concept. It’s been invaluable.”

This setup gave him confidence that new features were production-ready before they ever reached end users.

“By the time I deploy something to development, I don't need to worry about it. We've already figured it out in AgentOS."

Concepts that map to real work

For a data scientist building an agentic system, Agno's design felt intuitive. The framework mirrored how Bogdan already thought about orchestrating analytical workflows.

"The core concepts make sense—not just from a software development perspective, but from how you orchestrate work as an individual or as a leader. There's a natural mapping between what we do day-to-day as humans and what you can do in Agno."

A true partnership, not just a vendor

What Bogdan expected was documentation and a few answered questions. What he got was collaborative problem-solving. He said, "The answers weren't just 'here's how to use this feature.' They were 'have you thought about using this?' or 'we can't do that now—let's add it to the roadmap.' That was fairly unique in my experience."

"I don't think another platform or another team would have gotten me this far."

Continuous improvement, built in

As Thinqpoint's platform matured, Bogdan noticed that improvements weren't always coming from his own code. Updates to Agno's core platform, including how agents process instructions, how context is passed between agents, and how workflows are structured, were quietly improving Thinqpoint's performance without requiring changes on his end.

"It's not just improvement in code, but improvement in the way language is used to drive a workflow. That's led to faster answers and changes in how agents reply. Some of that doesn't come from us—it comes from improvements in the core platform itself."

The Agno team isn't in maintenance mode, they’re actively thinking about what agent builders will need tomorrow. Agno’s investment in product means Thinqpoint improves at the pace of AI: every time Agno ships an improvement, Thinqpoint gets better too.

Results

Speed, reliability, and room to grow

By building on Agno, Thinqpoint accelerated development, reduced friction, and unlocked deeper analytical capabilities.

The impact showed up across several dimensions:

Faster time to insight

Early experiments with raw API calls took 30 seconds just to interpret a single map. Now, Thinqpoint handles multi-step queries—understanding organizational context, pulling relevant data, running analysis, and generating recommendations—in under a minute.

"Had I used the old system, you can imagine—30 seconds over 30 seconds over 30 seconds. We'd be in the many-minutes range. Now with Agno, we do it in under a minute."

Compared to manual analysis, users can reach actionable answers in a fraction of the time, often more than ten times faster than traditional approaches.

"We measured what it would take for someone to manually get the data, think about what it means, and arrive at an answer. It's always above tenfold. At least 10 times as long as going into our platform and asking the question."

More reliable, context-aware outputs

As Bogdan explained, the real value comes from moving beyond raw data and into interpretation: “Somebody will come to our platform and say, ‘My organization serves these zip codes, and I’m trying to figure out where I should do more outreach for food insecurity.’ There’s a lot built into that question.”

The goal is not to simply return answers faster, but to provide recommendations that reflect real-world constraints, organizational context, and lived experience in community health. Building on Agno has made that possible, giving the platform the ability to reason across complexity rather than just summarize it.

Instead of simply returning data, the Thinqpoint platform can generate recommendations informed by organizational context, population characteristics, and domain-specific knowledge.

Scalable productivity without added headcount

Without a large engineering team, Bogdan needed a framework that amplified his own capacity. Agno reduced the need for custom glue code, repetitive infrastructure work, and manual testing, allowing Thinqpoint to scale capability without scaling complexity.

 "Some of the other platforms that I kind of tried out... just made it seem like I was at the bottom of a mountain. And to get to the other side was going to be some major lift. Getting this far, this quick would not have been possible without Agno."

Confidence to build toward more ambitious use cases

Perhaps most importantly, Agno gave Thinqpoint a foundation it could build on with confidence. With orchestration, evaluation, and iteration baked in, Bogdan is now expanding toward more advanced workflows, including end-to-end research projects and multimodal interfaces.

For Bogdan, Agno wasn’t just a tool to ship faster. It was the framework that made it possible to turn an ambitious vision into a production-ready platform.

"Agno for me wasn't just Agno. It was the framework itself and it came with the community. It came with subject matter expertise that I didn't necessarily have. Over time, Agno has become more than just the components we use. With agents in place, it’s really the glue that holds our platform together.”

Industry perspectives

On asking better questions and trusting the community

How Bogdan thinks about AI

For Bogdan, AI's value isn't in the technology itself. It's in solving real problems. As a technologist, he's seen how easy it is to get distracted by what's possible and lose sight of what actually matters.

“I always try to step back and ask, ‘What problem are we actually trying to solve?’ A lot of the time, the problem you think you’re solving isn’t the real one. Without that effort to understand things at their core, there’s a real risk of building things that don’t matter. And especially now, with AI making software development so much easier, it’s more important than ever to be sure you’re solving the right problem, so you don’t end up spending months building the wrong thing.”

He's especially wary of the current moment, where AI has made it trivially easy to build something, but not necessarily something useful.

"Anybody can get a front-end interface in under a day now. That makes it even more important to make sure you're solving for the right problem, so you don't end up spending months on things that don't ever get used."

That conviction, that solving the right problem matters more than shipping more software, is something he saw reflected in the Agno team from day one.

“Early on, I was impressed by a conversation I had with Ashpreet. I remember thinking, why is this guy reaching out to me? He's a startup founder, he's busy. But it quickly became clear that it reflected how the whole team works—focused on understanding the problem we were trying to solve, not just selling us another framework.”

“Since adopting Agno, I haven't really looked at other frameworks. Seeing how the team thinks gives me trust that we're not working with just a vendor. We're working with someone that thinks critically about the problems they're trying to solve for their customers."

Bogdan believes that lived experience is the key to extracting real value from AI. Understanding a problem deeply is what allows you to frame it correctly for a model. He said, "If you look at LinkedIn now, everybody's a thought leader, and everything looks the same. You immediately recognize when something was generated by someone who probably hasn't even read it. The more you see of that, the less you care."

For Thinqpoint, AI isn't a shortcut. It's a way to scale expertise.

Bogdan's advice for anyone getting started

For anyone evaluating agentic frameworks, Bogdan's advice is simple: just start.

"Once you land your first few lines of code and understand how Agno functions and how there's common sense built in—just start. Agno isn't going to be right for everybody. But the sooner you try, the sooner you realize where the value is."

He also encourages builders to lean on the community rather than going it alone. Too often, he's seen people (including himself) waste time going down dead ends when a quick question would have surfaced a better path.

"I've gone down rabbit holes that don't lead anywhere, and had I just asked a question, I would have gotten a much better solution much quicker. Get involved in the community. Exploit the collective mind of everybody using Agno. There are a lot of folks willing to share their expertise."

Looking forward

What’s next for Thinqpoint

With a strong AI foundation in place, Thinqpoint is now focused on expanding their offerings. The focus is shifting from answering individual questions to powering full-scale research and strategic planning workflows. He said, “What excites me the most is our ability to now build on these foundations. For example, our new needs assessment capability delivers end-to-end, complex analyses about the health and health-related social needs of communities. What started out as a chat interface that answers ad-hoc questions is now an advanced intelligence platform that delivers complex insights in minutes.

In 2026, I want us to deliver more end-to-end, complex research & development capabilities for our users. Needs assessments is the first of many examples we hope to ship this year.

Instead of relying on users to know exactly what to ask, future iterations of the platform will help determine which questions matter in the first place, run the necessary analyses, and deliver outputs that are usable for real-world decision-making.

As Bogdan explained, “Somebody might come in and say, ‘I need to better understand the communities that I have.’ There isn’t one question built in there. There are hundreds of questions.”

Thinqpoint is also exploring ways to meet users where they already work, whether that's integrating with messaging platforms or experimenting with multimodal interfaces like voice and video.

At the same time, Bogdan is preparing the platform for deeper use of sensitive data, including PHI and PII, as Thinqpoint expands into more advanced healthcare use cases. The architectural decisions made today are intentionally designed to support that future without requiring major rework.

Security was a key factor in choosing Agno from the start. With Agno, security and privacy are built into the architecture. The user data stays fully within Thinqpoint’s environment. So, Thinqpoint has the foundation to handle PHI and PII when the time comes. That wouldn't be possible with a framework that routes data through external systems. Bogdan explained: "The choices we're making now in terms of the platform we use and how we implement it are going to be critical when we start onboarding PHI, PII, or other types of sensitive information."

Ultimately, Bogdan and Thinqpoint are building an AI system that doesn't just respond to questions but actively supports understanding, strategy, and action for organizations on the front lines of community health. It's exactly what democratizing access to advanced intelligence looks like in practice.