Foxbox Digital is an award-winning engineering-focused product development agency.

Inside the Box Foxbox Digital Blog

Versapay: Digital Payments Mobile Strategy

AI has moved from novelty to necessity in software engineering. Learn about how Foxbox is using tools like Claude Code and Cursor to accelerate development, maintain code accountability, and deliver greater value to our clients.  

Evolving with intention in the age of AI-amplified engineering 

A year ago, most engineering teams were still treating AI like a novelty. Something to explore on the side, not something you’d bet the business on. Most agencies were still keeping AI tools at an arm’s length, including Foxbox. 

video not  long ago  about “vibe coding”

 and generally concluded that it yielded surprisingly quality results, but was still most applicable to proof of concepts or easily automated tasks.


When updated models of tools like Claude Opus, Gemini and Cursor were released earlier this year, the agency world reached a threshold. I firmly believe we’re now on the other side of it.


So we’re adapting.  This article outlines what we’re doing now, what we’re learning in real time, and how we’re choosing to move forward as a company. It’s not a set of final answers. It’s a snapshot of how we think, how we build, and how we’re staying grounded while everything around us moves quickly.


Dependency upgrades, typically long and arduous processes, can now be completed in a fraction of the time. Which helps eliminate typical bottlenecks to innovation and new feature development.


We’re using Claude Code as a pair programmer working alongside our engineers to build new features. We lead the tool, breaking down the problem for Claude as if we were to write it ourselves. Claude writes the first pass of the code. Then we edit, review, and commit. Look out for security and performance issues. Collaborate with the tool to write unit tests. Claude Code opens pull requests and automates the arduous pull request description writing. 

Here’s the key thing: our engineers are accountable and responsible for every line of code shipped. The tool helps, but we’re accountable.

, we instruct Claude Code on exactly what we want it to look like by providing screenshots of Figma or example code. It does a very good job. Then we use our expertise to fine tune and get the UI just right.


We’re using tools like Claude Code and Cursor to 

. Instead of manually writing failing tests and debugging step by step, we feed the bug into the AI, which helps generate a test case, suggest a fix, and even write the pull request. This automates much of the traditional TDD workflow and helps us resolve issues faster and with more confidence.
These aren’t shortcuts. 

They’re scaffolding that helps our engineers move faster without cutting corners.
Of course, we don’t just hit “accept” on AI output and ship it. Human oversight is built into every step. In many ways, these tools haven’t made software easier to build, they’ve made it more possible to build exceptional software in far less time.

We’ve seen the critiques. That AI-assisted code erodes discipline. That it nudges teams toward shipping faster instead of thinking deeper. That it risks turning engineers into editors. And some of those concerns are valid.
But the solution isn’t to slow down out of fear. It’s to build systems of accountability and lean into the process. 

We’re not handing off thinking to machines. We’re extending our own capacity to think with quicker clarity and greater context. When we automate a test suite or use AI to surface a cleaner refactor, it’s not because we’re lazy. It’s because we want our engineers focused on what only humans can do: make tradeoffs, understand users and build systems that adapt . 


I’m proud that I have a development and engineering team full of people that take tremendous pride in their craft. As an engineer who had to work hard to let go of writing code, I understand the defensive instinct or hesitation lots of engineers are feeling right now. 

The craft of software engineering isn’t about elegant code for its own sake. It’s about solving real problems through thoughtful systems. Great engineering bridges the gap between what a product does and what people actually need. The best solutions are often invisible—seamless, intuitive, and built with care. 

It’s about solving problems. Bridging gaps between product and user. It’s invisible architecture and elegant functionality, using the most advanced tools at our disposal to build things that impact people’s lives. It’s about the insight, creativity and attention to detail that makes a product so seamless and intuitive that it 

That’s the craft. Engineers that learn to be less precious about their code will be the first to remaster it.


We’re choosing to ride the wave of change: document as we go, evolve with intention, and stay focused on maximizing value to our clients. That tracks with what we’re seeing. The developers on our team aren’t just getting more done. 

They’re spending more of their time doing higher-value work.
So what does it mean when all engineers become leads? What blind spots might future engineers have if they never actually learn the basics of programming? 

Nobody knows exactly what’s next. That’s the point.
We’re not trying to predict the endpoint. We’re designing for the middle. For the messy, fast-changing space where smart humans and fast machines solve problems together. 

If we’ve learned anything over the past year, it’s that you can’t wait for certainty to take action.
So that’s what we’re doing. We’re not claiming to have it all figured out. But we’re moving fast, thinking deeply, and having the conversation out loud along the way.

Foxbox in the AI Era

Recap of our 7/10/25 event in Chicago exploring AI-amplified development. From shifting engineering mindsets to emerging workflows with Claude Code, here’s what stood out.

Event Recap | AI-Amplified Development | Foxbox Digital

Thanks to everyone who joined us in Chicago for an open conversation about AI-amplified development and its role in our industry. These discussions are only becoming more important as the ground beneath software development keeps shifting. 

Looking forward to keeping the momentum going and seeing where it all leads next. 

Below is a recap of what stood out to us.


It’s clear a major cultural shift is underway: developers are learning to let go of treating code as precious. Instead of clinging to large codebases, the focus is moving toward the 

There’s a growing willingness to start over—to explore a partially working solution, then reframe or rebuild it with fresh context.

The long-term mindset: adapt and evolve with tools, but rely on your own ability to learn. Our friend Dustin Anderson had perhaps the quote of the day: 

“The model to stick with long-term is yourself.”

2. Prompting, Specificity, and Workflow Success 

AI tools like Claude Code is highly dependent on specificity and context. The better the prompt and problem framing, the better the results.

One group discussed using workflow tools (like NAM?) to compartmentalize steps and tune processes, improving outcomes from LLMs.

The importance of structure and breaking work into discrete, contextual pieces came up repeatedly.

There was discussion about potential intergenerational divides in how AI tools are adopted:

Older professionals may bring depth and experience but less familiarity with modern AI tools.

Younger folks may experiment more, but questions remain: Will they still need to learn to code? When does AI replace or augment that skill?

This led to a broader theme: When do we rely on expertise, structure, and process vs AI-driven agility?

One historical analogy was made to Visual Basic: non-programmers could build real apps—useful, if limited. We’re now facing the same blurred lines with AI.

4. Tool Fragmentation and Future-Proofing

Attendees raised concerns about tool fragmentation and uncertainty. It’s hard to say what will be around in 5 years.

Standards that scale from startup to enterprise

Balancing morale vs velocity is another leadership challenge—how to move fast while keeping teams grounded and motivated.

Claude Code impressed many and is being used creatively:


One attendee described using Cursor to write user stories, then Claude to build features.
Another mentioned Claude auto-generating commit history and invoices.

—where an AI agent orchestrates tooling.

One example involved crypto platforms using APIs like CoinGecko:
A new MCP server  was added to the agent interface, removing the need to directly interface with complex APIs. “That was a game changer." 

6. Trust, Quality, and System Reliability

Across industries, especially in healthcare and enterprise, the central challenge is 

One line summed it up: “It will always boil down to reliability and trust.”
Developers and engineers have to be accountable for code generated by AI.


How to scale processes across teams with different work styles

Some teams are exploring LLM-on-LLM supervision: using one large language model to monitor or verify the output of another.

For example: one LLM generates code, another flags issues or corrects it. This concept echoes the need for checks and balances, potentially reducing hallucinations and increasing reliability.


Tools like Claude Code’s code reviewer or Gemini code assist can be helpful for first pass reviews.


At what point does a product or idea need to transition from low-code or AI-built prototypes into a more “real” language or 

 around AI-assisted development before it scales too far without oversight?

Will non-developers continue to build increasingly complex tools—

From rethinking long-held engineering mindsets to experimenting with emerging tools like Claude Code, it’s clear the way we build is changing fast. These conversations are rooted in curiosity, healthy skepticism, and real-world application, and they’re essential as we navigate what comes next. 

Stay tuned for future gatherings as we continue to explore, question, and shape the future of AI-amplified development together.

AI Amplified Development: Beyond Vibe Coding - Event Recap

The power of predictability, helping healthcare leaders get more out of AI, and a worthwhile visit to Atlanta.

Foxbox Founder's Update - Spring 2025 | Foxbox Digital

As we navigate 2025, one thing is clear: stability and predictability have never been more valuable. In a world of economic uncertainty, companies that focus on consistent, proactive product maintenance are reaping the rewards.

Product Maintenance: A Strategic Advantage

We’ve always believed that product maintenance is more than just fixing bugs—it’s about ensuring reliability, improving performance, and keeping products aligned with evolving customer needs. Our clients are proving that a 

leads to higher user engagement, fewer costly disruptions, and a foundation for future innovation.

One of our healthcare clients recently revamped their product maintenance approach, shifting from a reactive model to a proactive one. The result? Faster feature releases, fewer production issues, and better provider adoption rates. It’s a reminder that 

 isn’t just about survival—it’s a competitive edge.

We’ve been weaving AI into nearly every aspect of our business, from how we build and maintain products to how we 

help our clients leverage AI responsibly.

Healthcare organizations, in particular, are looking for guidance on AI integration. Our team is helping clients navigate AI with confidence—whether that’s through predictive analytics, automation, or patient-facing AI solutions. It’s not just about innovation, it’s about creating practical, compliant, and ethical AI applications that drive real impact.

Healthcare: Engaging Providers & Patients

Healthcare remains a core focus at Foxbox, and we’re seeing a growing demand for better digital experiences for both providers and patients. Our team is tackling these challenges head-on, from reimagining provider workflows to building consumer-grade patient experiences.

One thing we’re particularly excited about is how  

 are enabling organizations to modernize their systems without being locked into a monolithic EHR vendor. Additionally, our 

 are helping healthcare clients explore how AI can enhance their operations, from administrative automation to personalized patient engagement.

I was lucky to spend some quality time with Elliott Torres and Brett Ryan in Atlanta. Special thanks to Bala Balakrishnan and Vio Balanoiu for helping carve us out some space to make the most of it. I worked closely with Bala, Vio, and of course Elliott at Anthem building 

. Always great to collaborate together the old fashioned way.

Speaking of reasonable things to do - we took a home-made airplane for a test drive. Thankfully it was built by a friend whose engineering brain I trust implicitly. Thanks 

As we look ahead, we’re doubling down on building products that are not just innovative, but also scalable, maintainable, and future-proof. If you’re curious to explore more of what that looks like for your business, let’s talk.

Founder's Update - Spring 2025

"Sometimes, the best compliment is being 'out-of-sight, out-of-mind.' At Foxbox, we’ve learned that true success isn’t just about high-visibility projects—it’s also about seamless, reliable execution that keeps our clients’ teams moving forward without friction."

Product maintenance, the power of predictability and the advantage of going unnoticed

I want projects with high visibility as much as the next guy.

But as Foxbox has evolved, I’ve come to equally embrace the other side of that equation.

“Honestly, you guys are completely out-of-sight, out-of-mind.”

It was a routine quarterly review with the VP of Engineering of an ongoing product maintenance client. Unlike the iconically devastating line from Don Draper in Mad Men, it was intended as a compliment. And it was received as one.

When the goal is predictability, routine problem-solving, and the ability to keep our clients’ engineering teams pointed in the right direction, off-the-radar is not a bad place to be.

service at Foxbox is designed to provide. We step in to handle the ongoing upkeep, bug fixes, and iterative improvements that keep digital products running smoothly—so our clients don’t have to think about it. No firefighting. No disruptions. Just dependable, proactive maintenance that keeps their teams focused on innovation rather than troubleshooting.

High-profile launches are exciting, but sustained success depends on what happens after the initial release. Without a solid maintenance strategy, even the best-built products degrade over time. Technical debt creeps in, performance lags, security vulnerabilities emerge. 

That’s where we come in—ensuring the 

long-term stability and scalability of the products our clients rely on

So when a client tells us we’re “out-of-sight, out-of-mind,” we take it as proof that we’re doing our job right. Because in product maintenance, the best work is often the work that goes unnoticed.

Want to keep your product running at peak performance without the headaches? 

The value in staying "off-the-radar"

A quick primer on the pros and cons of building a custom AI model, using off-the-shelf LLMs, or a hybrid approach. 

Custom LLM vs Off-the-Shelf: Navigating AI Platform Decisions

Deciding between a custom AI model, an off-the-shelf solution, or a hybrid approach? Each has trade-offs in cost, control, and scalability. Here’s how to choose the best option for your business needs and goals.

Building a proprietary LLM from the ground up.

 Full Control Over Capabilities & Optimization

Can be trained specifically on domain-specific data to outperform generic models.

Tailored fine-tuning for superior accuracy, relevance, and compliance.

Sensitive data remains within the company’s control.

Easier to meet stringent industry regulations (e.g., HIPAA, GDPR, SOC 2).

Proprietary AI can become a strategic moat.

Potential licensing or monetization opportunities.

Requires extensive compute resources, skilled talent, and infrastructure.

Training and inference costs can be significantly higher than off-the-shelf solutions.

Developing a high-quality model can take months or even years.

Requires iterative fine-tuning and evaluation.

Needs continual updates to remain relevant and competitive.

Risks of model drift, bias, and security vulnerabilities.

2. Off-the-Shelf LLMs (ChatGPT, Gemini, Claude, etc.)

Using pre-built AI models via APIs or cloud services.

No need to invest in expensive infrastructure.

Pay-as-you-go pricing with predictable costs.

Access to cutting-edge AI without having to train it.

Providers continuously update and improve their models.

Fine-tuning options are often restricted.

May not perform as well on niche or proprietary tasks.

Customer data is sent to third-party servers (potential compliance risks).

Control over data retention and security is limited.

Dependence on external providers for model updates and pricing.

Sudden changes in API costs or terms can impact business continuity.

Combining off-the-shelf models with proprietary data and fine-tuning.

Leverages pre-trained models while allowing customization.

Can fine-tune smaller, domain-specific models for performance gains.

Avoids the heavy lift of training from scratch.

Fine-tuning or using Retrieval-Augmented Generation (RAG) enhances domain relevance.

Sensitive operations can be handled in-house while still benefiting from cloud AI.

Hybrid deployment options (e.g., using an API for general queries but a local model for sensitive data).

Requires some ML/AI expertise for fine-tuning.

Ongoing model maintenance still needed, though less than fully custom models.

Requires careful orchestration between different AI components.

May need additional infrastructure to manage hybrid workflows.

Decision Framework: Which Approach is Best?

Want to explore more about building a tailored  LLM & AI strategy  for your business?   

Get in touch

The modular approach for healthcare providers who have outgrown their EHR.

The Case for Headless EHRs | Foxbox Digital | Healthcare 

For healthcare providers who have outgrown their existing EHR, a new solution is emerging: 

Unlike traditional EHRs, which often bring high implementation costs, complex workflows, poor interoperability and extensive training requirements for clinicians, Headless EHRs provide an API-based infrastructure that can help clinical organizations finally close the gap between their ideal clinical workflows and the back-end operations that make patient-focused care possible.


While counterintuitive at first, Headless EHRs can help close that gap by actually decoupling the back-end infrastructure from the front end-interface, creating a modular design that delivers the flexibility, interoperability and efficiency that many mid-size providers  are lacking from the solutions they can currently afford. 


So for leaders looking for the best way to evolve how they manage patient data and clinical workflows, here’s our abbreviated case for going “headless,”  what to expect from leading platforms, and why the Headless EHR could be the modular approach midsize healthcare providers have been searching for.

Headless EHRs enable real-time data synchronization between different care teams. This promotes efficient communication and faster decision-making, leading to reduced wait times and more responsive care. As the system can adapt to user needs, patients can benefit from updates and new features more quickly, improving their overall satisfaction.


 - Flexible API - Out-of-the-box, Healthie’s API is designed to make it easy to go live quickly, with options for partial or full white-label custom branded solutions for easy flexibility that scales along with your practice.

The API-first approach enables the integration of patient-centric tools such as personalized patient portals, telehealth solutions, and AI-driven virtual assistants. By offering a user-friendly interface that can be easily customized, providers can ensure patients have smoother access to scheduling, medical histories, and care plans.


 - Future-Ready Architecture: In addition to HIPAA and SOC2 compliance out of the box, anything built on Medplum inherits FHIR API access and which can be extended to partners, maximizing interoperability between care providers. 


Cost control is obviously a major consideration in EHR selection, particularly for midsized providers. The modular nature of headless EHRs means leaders can select only the components they need, minimizing upfront investments. The cloud-based infrastructure common to headless EHRs enables better scalability, and more manageable upgrades, as providers can roll out new features incrementally rather than undertaking costly system overhauls.

- Unified patient experiences:   Because it’s directly integrated with their other service offerings, Oystehr’s API can support insurance validation, claims submissions, diagnostic test processing, telemed calls and SMS chat, all from one system.

Like any new technology investment, the EHR 2.0 that’s right for your organization will only be as effective as it is properly thought through from the beginning. For leaders curious about what to do next, here’s where we would start:


 about the solutions that are right for your unique circumstances.

At Foxbox, we're actively working with providers of all shapes and sizes to make the transition to “headless" as efficient, painless and future-focused as possible.      

If you’d like to learn more about what we can help unlock within your organization, we’d 