Recent Updates

Million Dollar Surprise

•

04/03/2025

They’re going to put me out of business

“They’re going to put me out of business. They want over a million dollars. I don’t have a million dollars”, his voice cracked over the phone.

“Who?” I thought to myself. The Russian mafia?

Years ago, I used to write software and mathematical routines for online sports betting platforms. One of our systems would get hit like clockwork—always right before the Super Bowl. Russian mafia. They’d call and say, “Pay us, or we’ll take your site offline.” And they could. They’d DDoS us into the ground. Usually, we paid—because when the alternative is a crash during the biggest betting day of the year, you don’t mess around.

“I’m going to have to sell the building. This will ruin me. They’re clawing back everything”. He continued.

This wasn’t the Russian mafia – it was worse: it was Medicare.

I stepped into my client’s office, mind racing, trying to piece together what the hell was happening. Been working with this guy for years—never a hiccup. He ran a solid operation, serving patients who genuinely needed it. Never once saw anything sketchy. I collected the information, calmed him down, and reminded him we have everything documented.

The Audit Trap

Here’s what they don’t tell you about Medicare audits: they’re not really audits. They’re retroactive death sentences wrapped in paperwork.

Medicare doesn’t review all your claims. They hand a slice—maybe 150 claims—to a third-party contractor whose job is to claw back money. If the contractor thinks the documentation for 75% of the sample isn’t strong enough, they extrapolate. Meaning: they assume everything is invalid. Every claim. Every patient. Every dime.

In this case? That would have been millions.

The services had already been provided. The work had already been done. The bills had been paid. There was no fraud—just missing or misunderstood documentation. But the government doesn’t care. If the audit sticks, the clinic folds.

And here’s the punchline: they hadn’t even made that much money. Anyone who’s actually worked in medical billing knows Medicare reimbursement isn’t exactly a goldmine. It’s barely sustainable on a good day.

Preparedness Pays Off

Most of the time when someone calls us after an audit notice, we can’t do much.

But this clinic had something most don’t: they’d been using FairPath since day one.

I told them to take a breath. I was already in the system. FairPath wasn’t built just to run billing workflows—it was built to defend them. And now it was time to prove why that mattered.

While Medicare reviewed their 150-claim sample, I didn’t just pull documentation for those 150. I started stitching together a much larger picture. Clinician notes, EMR data, claim history, call records, messages—we gathered evidence across every system they used. Not just the obvious fields, but the buried ones. Not just structured entries, but the soft signals and contextual breadcrumbs that show real care was delivered.

Then I loaded everything into SemDB, our semantic database. This gave us a unified structure for connecting all that disparate information: patient encounters, communications, documentation trails, claim metadata—stitched together into a coherent, queryable layer. That orchestration allowed us to go beyond responding to the audit—we could investigate it.

I used their own 150-claim sample as a model and extrapolated across the patient base, proactively surfacing any patterns that might have triggered concern. I won’t go into the specifics of what we found, but I can say this: the goal wasn’t just to push back on Medicare. The goal was to make sure every patient had truly received the care they were promised—and that the record showed it.

What we delivered to the auditors wasn’t a pile of PDFs. It was a comprehensive, structured, cross-referenced case file—something that normally takes a hospital system a full compliance team to produce. But this wasn’t a hospital. It was a medium-sized clinic with no compliance department, and we gave them the tools to stand toe-to-toe with a federal audit.

We didn’t argue. We presented. And what we presented made it clear: the care was there, the documentation was there, and the clinic had done its job.

They didn’t take a dime.

Why I Built FairPath

Because I’ve seen too many clinics blindsided by clawbacks they couldn’t fight—not because they did anything wrong, but because they didn’t have the documentation the system demands.

Medicare audits don’t make headlines, but they end practices. Small and mid-sized clinics don’t have compliance teams, regulatory lawyers, or forensic analysts. They have overworked staff, a limited budget, and a calendar full of patients. The audit process wasn’t designed for them. It was built to claw money back, favor complexity, and punish anything that doesn’t look perfect on paper.

FairPath exists to flip that script.

It’s not just billing software. It’s infrastructure for proof. It doesn’t just help you run a practice—it helps you protect it. It logs, structures, and defends your work in real time, across multiple systems, without asking your team to become compliance experts. In an audit, it doesn’t just hand over files. It presents a case.

It’s AI—but not the kind that guesses. It’s explainable, deterministic, and rooted in reality. It builds your defense as you operate, without slowing you down.

Since launching FairPath, we’ve helped our clients prevent over $8.6 million in Medicare clawbacks. That’s not theory. That’s battle-tested.

Audit-proofing isn’t something you bolt on at the last second. It’s something you build into the workflow. That’s what FairPath does.

So if you’re tired of waiting for the letter… if you want to know what we captured, how we logged it, and how we’ve helped practices survive what others couldn’t.

You don’t need to be scared of the audit.

But you do need to be ready.

Give us a call.

Unlocking AI: A Practical Guide for IT Companies Ready to Make the Leap

Justin Brochetti

•

12/22/2024

Introduction: The AI Revolution is Here—Are You Ready?

Artificial intelligence isn’t just a buzzword anymore—it’s a transformative force reshaping industries worldwide. Yet for many IT companies, the question isn’t whether to adopt AI but how. If you're scratching your head wondering where to start, you're not alone. For businesses looking to incorporate AI while safeguarding data and staying ahead of the competition, there’s a way forward—and it doesn’t have to be overwhelming.At Intelligence Factory, we specialize in helping companies like yours confidently integrate AI into their operations. Whether it’s addressing data security concerns or keeping your proprietary information safe from open-source data pools, we can guide you step-by-step into this new era.

Step 1: Understand the Business Case for AI

The first step to adopting AI is identifying your “why.” AI isn’t one-size-fits-all—it’s about solving specific business problems.

‍Ask yourself:

What tasks consume your team’s time that could be automated?
Are you missing opportunities due to slow data processing?
How could AI enhance your customer interactions or product offerings?

From automating customer service with voice agents to streamlining internal workflows, AI solutions must align with your strategic goals.

Step 2: Address the Elephant in the Room—Data Security

One of the biggest barriers to AI adoption is fear over data privacy. Many IT companies hesitate, worried that using AI tools might expose their proprietary information to external threats or open-source ecosystems.

‍Here’s the good news: Our AI solutions prioritize security from the ground up. We ensure all your data stays private, compliant, and within your control. Using technologies like Buffaly, which integrates seamlessly into existing systems, we provide AI capabilities without compromising your sensitive information.

‍Key takeaway: AI doesn’t have to mean giving up control over your data.

Step 3: Start Small, Scale Fast

Rather than trying to overhaul your entire business with AI, start with a pilot project.

For example:

Automate your lead management process.
Implement an AI-driven customer service agent.
Use AI tools for faster and more accurate data retrieval.

These “quick wins” build confidence and demonstrate ROI, allowing you to scale your AI efforts strategically over time.

Step 4: Partner with Experts (Like Us)

You don’t have to figure this out alone. AI adoption is complex, and the right partner can make all the difference. At Intelligence Factory, we offer:

Customized AI solutions designed for your unique business needs.
Data security expertise to keep your information protected.
Hands-on support to integrate AI seamlessly into your existing operations.

Why Now is the Time to Act

The AI market is evolving rapidly, and those who wait risk falling behind. Early adopters are already seeing gains in productivity, customer satisfaction, and bottom-line growth. Your competitors aren’t waiting—so why should you?

Closing: Let’s Build Your AI Roadmap Together

At Intelligence Factory, we’ve helped IT companies transform uncertainty into opportunity. Whether you’re concerned about data privacy, unsure where to start, or just need a trusted partner, we’re here to help.

Let’s connect to explore how AI can work for your business. Reach out today to schedule a consultation and take the first step toward your AI-powered future.

Agentic RAG: Separating Hype from Reality

Matt Furnari

•

12/18/2024

Agentic AI is rapidly gaining traction as a transformative technology with the potential to revolutionize how we interact with and utilize artificial intelligence. Unlike traditional AI systems that passively respond to commands, agentic AI systems operate autonomously, making decisions and taking actions to achieve specific goals. This shift from passive to proactive AI has sparked considerable excitement and debate, with proponents touting its potential to automate complex tasks, optimize workflows, and enhance decision-making across various industries.

This report delves into the world of agentic AI, exploring its relationship with Retrieval Augmented Generation (RAG), examining the latest approaches, and analyzing its potential benefits and shortcomings. We'll also provide a comprehensive overview of companies and products offering agentic AI solutions, separating marketing hype from factual capabilities.

What is Agentic AI?

Agentic AI refers to advanced AI systems that can operate independently, much like a human employee. These systems go beyond simply responding to commands; they can understand context, set goals, and adapt their actions based on changing circumstances. Agentic AI systems are designed to pursue and achieve complex objectives with minimal human supervision. They can analyze situations, formulate strategies, and execute actions to achieve specific goals, all with minimal human intervention.

One of the key characteristics of agentic AI is its ability to dynamically adjust its execution strategy based on environmental changes and outcome assessment. This adaptability sets it apart from other forms of AI, such as Robotic Process Automation (RPA) or some generative AI systems, which typically follow pre-defined rules or rely on static models.

Agentic AI systems are not merely chatbots that provide responses based on single interactions. Instead, they use sophisticated reasoning and iterative planning to solve complex, multi-step problems. This allows them to handle more intricate tasks and workflows, understanding the bigger picture and breaking it down into smaller steps to achieve the desired outcome.

The potential benefits of agentic AI are significant. It can revolutionize customer interactions by providing personalized and responsive experiences at scale and speed. By leveraging sophisticated models, AI agents can infer customer intent, predict needs, and offer tailored solutions, all while operating 24/7 to ensure consistent and efficient support.

Furthermore, agentic AI systems can enhance human performance, productivity, and engagement rather than replacing human employees. By seamlessly integrating with existing systems and processes, agentic AI systems can form a powerful partnership with workforces, augmenting human capabilities and allowing employees to focus on higher-value tasks.

Agentic AI and Retrieval Augmented Generation (RAG)

Retrieval Augmented Generation (RAG) is a technique that enhances large language models (LLMs) by retrieving relevant information from external knowledge sources. This process allows LLMs to provide more accurate, contextually relevant, and grounded responses.

Agentic AI takes RAG a step further by incorporating AI agents into the RAG pipeline. These agents orchestrate the retrieval process, analyze data, refine responses iteratively, and adjust based on real-time feedback. This approach is particularly powerful in complex settings where dynamic data and multi-step reasoning are necessary.

Agentic RAG systems can continuously learn from their environment, refining their understanding with each data retrieval. This means that subsequent queries will likely yield better, more accurate results.

One of the key insights about agentic RAG is that it enables AI to act as a proactive partner, making real-time decisions independently. This marks a significant shift from passive to proactive AI, where systems can anticipate needs and offer solutions without explicit human intervention.

Core features of Agentic RAG include:

Intelligent Agents: Employs autonomous agents that analyze, reformulate queries, and refine responses as needed.
Multi-Step Reasoning: Capable of handling complex queries by dynamically adjusting responses.
Dynamic Workflow Adaptation: Leverages agents to adapt workflows based on context.
Tool Integration: Integrates tools like APIs, databases, and external functions to enhance capabilities.

Latest Approaches in Agentic AI

Self-Improving Agentic AI

Self-improvement, where an agent autonomously improves its own functioning, has intrigued the AI community for several decades. There are two main categories of self-improvement in agentic AI:

Narrow self-improvement: The agent improves its performance within a fixed operating environment or goal. For example, an LLM-based agent might monitor its performance and autonomously launch a fine-tuning loop to retrain its LLM on a new dataset when it detects performance deviations.
Broad self-improvement: The agent improves its performance across different environments or goals. This involves modifying its own architecture, learning algorithms, or reward functions.

One approach to self-improvement is reflection, a prompting technique where a language model analyzes and critiques its previous actions to identify areas for improvement. This process can also incorporate external data, such as insights from tool interactions, to provide a more informed and thorough reflection.

Self-improvement in agentic AI allows systems to continuously learn and adapt without constant human intervention. This is a key advantage of agentic AI, as it enables systems to become more effective and efficient over time without requiring ongoing manual updates or adjustments.

Another important aspect of self-improvement is the use of feedback loops. Agentic AI can use feedback loops where it actively seeks out new data to refine its models or decision-making.

Knowledge Representation in Agentic AI

Agentic AI and Vector Databases

Vector databases play a crucial role in agentic AI, particularly in RAG applications. They store vector embeddings of data, enabling efficient similarity search and retrieval of relevant information. In an agentic RAG system, an AI agent can evaluate a query's context and autonomously decide which vector database to query.
‍
Vector databases also enable agents to learn and adapt by storing and organizing vast amounts of information. This allows agents to become more versatile, understanding, and capable of handling complex tasks.
‍
Agentic RAG systems that utilize vector databases can incorporate various tools to enhance their capabilities, such as:

Querying a vector database: This is the most common tool, allowing the agent to retrieve relevant documents based on the query.
Query expansion: This tool improves the query by adding synonyms, correcting typos, or generating new queries based on the original one.
Extracting filters: This allows for narrowing down the results based on specific parameters.

Agentic AI and Graph Databases

Graph databases are useful for representing and analyzing complex relationships and networks in agentic AI systems. They can be used to store knowledge graphs, which provide a structured representation of knowledge that complements the capabilities of LLMs.

AI agents utilize memory and knowledge graphs for context and reasoning. This allows them to understand the relationships between different pieces of information and make more informed decisions.

Agentic AI and Ontologies

Ontologies provide a structured representation of knowledge that helps AI agents understand and reason about the world. They allow different AI systems to share and understand the same ideas and goals, making it easier for them to work together. Ontologies can also be updated as new information comes in or things change, helping AI agents stay adaptable and flexible.

The applications of ontologies in AI extend beyond simple knowledge representation. In healthcare, ontologies are helping AI systems understand the complex relationships between symptoms, diseases, and treatments, potentially revolutionizing diagnosis and patient care. In financial systems, ontologies enable AI to navigate the intricate web of global markets, regulations, and economic indicators, providing insights that can shape investment strategies.

Companies and Products Offering Agentic AI

Several companies are developing and offering agentic AI solutions, with a focus on agentic RAG. Here's an overview of some key players:

Company / Product

Aproach

Technology

Claimed Capabilities

Shortcomings

SemDB / Intelligence Factory

SemDB is focused on providing safe, explainable and controlled Agentic AI

Uses a hybrid Vector / Ontology backend to store “what” and “how”.

Ability to incrementally improve over time and learn new capabilities directly from data.

Lack of integration with open source platforms.

SuperAGI

Open-source platform for building and managing autonomous AI agents. SuperAGI is focused on developing Large Agentic Models (LAMs) to power these agents.

Large Agentic Models (LAMs), multi-hop sequential reasoning capabilities.

Concurrent agent execution, extensive tool integration, robust memory and context management.

Limited accessibility for non-technical users, potential for marketing hype exceeding actual capabilities.

Cognigy

AI agents designed for enterprise contact centers. Cognigy's AI agents use cognitive reasoning to evaluate user intent and contextual clues.

Conversational AI engine combined with LLMs.

Cognitive reasoning, hyper-personalization, real-time decision-making.

Potential for frustration for non-technical users when encountering problems, limited flexibility in some cases.

Theta EdgeCloud

Offers Agentic AI as a service with a focus on RAG chatbots, allowing businesses to access cutting-edge AI capabilities without significant investment in infrastructure.

High-performance cloud-based GPUs, integration with Google Cloud.

Continuous knowledge base updates, accurate and personalized interactions.

Concerns about safety and reliability, potential for malicious actors to exploit vulnerabilities.

NVIDIA

Focuses on providing the infrastructure and tools for agentic AI development, enabling developers to build and run AI agents locally.

NVIDIA RTX AI PCs, NVIDIA NeMo microservices, NVIDIA Blueprints.

Enhanced productivity, autonomous problem-solving, real-time decision-making.

Challenges with staying ahead of the competition, potential for security issues.

Weaviate

Open-source vector database and AI platform for building and scaling AI applications. Weaviate aims to provide a flexible and scalable embedding service for AI development, addressing common limitations of other embedding services.

Hybrid search, RAG, generative feedback loops.

Building trustworthy generative AI applications, maintaining control over data.

Potential for overhyping capabilities, limited robustness in some cases.

LangChain

Framework for building LLM-powered applications with a focus on agentic AI. LangChain views agent adoption as a spectrum of capabilities, acknowledging that different levels of autonomy exist.

ReAct architecture, multi-agent orchestrators, LangGraph framework.

Managing multi-step tasks, automating repetitive tasks, task routing and collaboration.

Brittleness of agent patterns, difficulty in debugging, lack of maintenance options.

Evaluating Agentic AI Systems

While companies often make bold claims about their agentic AI capabilities, it's essential to look beyond marketing materials and seek independent evaluations to gain a more objective understanding of their strengths and weaknesses.

For example, an independent evaluation of SuperAGI highlighted both its potential and limitations. The evaluation praised SuperAGI's user-friendly interface and its ability to handle complex tasks, but it also noted that the platform may not be suitable for all users and that some of its claimed capabilities may be overhyped.

Similarly, reviews of other agentic AI solutions have pointed out issues such as inconsistencies in performance, difficulties in debugging, and limitations in handling edge cases. It's crucial to consider these independent evaluations alongside company claims when assessing the suitability of an agentic AI solution for specific needs.

Challenges and Limitations of Agentic AI

While agentic AI holds immense promise, it's crucial to acknowledge its current limitations and potential shortcomings:

Explainability and Trust: The complexity of agentic AI algorithms often results in a lack of transparency in decision-making processes. This "black-box" nature can make it difficult to understand or predict the AI's behavior, raising concerns about trust and accountability.
Data Dependency: Agentic AI systems rely heavily on high-quality data to make informed decisions. Inconsistent, incomplete, or outdated data can lead to suboptimal or incorrect AI decisions.
Bias and Fairness: AI models can inherit biases from their training data, potentially leading to discriminatory or unfair outcomes. Ensuring fairness and mitigating bias in agentic AI systems is an ongoing challenge.
Security and Privacy: Integrating agentic AI with enterprise systems that contain sensitive data raises concerns about security and privacy. Protecting sensitive information from breaches or misuse is crucial.
Unforeseen Consequences: Agentic AI systems, due to their adaptability and ability to learn, can potentially engage in unforeseen actions or decisions, leading to unintended consequences.
Overhyped Expectations: The marketing hype surrounding agentic AI can sometimes overshadow its actual capabilities. It's essential to separate hype from reality and have realistic expectations about what agentic AI can achieve today.
Misaligned Objectives: If the objectives of an AI agent are not carefully aligned with those of the organization or individual using it, the AI-driven decisions could fail to capture user preferences, values, and goals adequately ³⁷. This could lead to faulty decision-making and potentially undesirable outcomes.
Operational Vulnerabilities: AI agents can be vulnerable to various operational challenges, such as auditability and compliance issues, as well as the risk of failure cascades in interconnected systems.

Conclusion

Agentic AI represents a significant leap forward in artificial intelligence, offering the potential to transform how we work, interact with technology, and solve complex problems. While the technology is still evolving, and challenges remain, the advancements in agentic AI are undeniable. By understanding its capabilities, limitations, and potential impact, businesses and individuals can harness the power of agentic AI to drive innovation, optimize workflows, and create a more efficient and productive future.

The increasing adoption of agentic AI in various industries highlights its potential to automate complex tasks and improve decision-making. However, it's crucial to address the challenges and limitations associated with this technology, such as ensuring data privacy and security, mitigating bias, and promoting transparency.

As the field continues to advance, we can expect to see more sophisticated, reliable, and transparent agentic AI systems that can be trusted to make critical decisions and contribute to a better future. Research institutions are also exploring the use of agentic AI to address global challenges, such as accurately assessing research output against the United Nations' Sustainable Development Goals (SDGs). This highlights the potential of agentic AI to contribute to a more sustainable and equitable future.

Inteligência Artificial, Machine Learning, e Compreensão Natural de Linguagem

O que a Intelligence Factory faz?

Inteligência Artificial para Clínicas Médicas

Compreendimento de Linguagem Natural

Soluções de IA Customizadas

Soluções da Intelligence Factory

CRM

Call Center

Entre em contato