Intellect Design Accelerates Modernization by 200% with MongoDB and Gen AI

Vinod Bagal
June 26, 2025

It’s difficult to overstate the importance of modernization in the age of AI. Because organizations everywhere rely on software to connect with customers and run their businesses, how well they manage the AI-driven shift in what software does—from handling predefined tasks and following rules, to being a dynamic, problem-solving partner—will determine whether or note they succeed.

Companies that want to stay ahead must evolve quickly. But this demands speed and flexibility, and most tech stacks weren’t designed for the continuous adaptation that AI requires. Which is where MongoDB comes in: we provide organizations a structured, proven approach to modernizing critical applications, reducing risk, and eliminating technical debt.

Our approach to modernization has already led to successful, speedy, cost-effective migrations—and efficiency gains—for the likes of Bendigo Bank and Lombard Odier.

So, I’m delighted to share the story of Intellect Design, one of the world’s largest enterprise fintech companies, which recently completed a project modernizing critical components of its Wealth Management platform using MongoDB and gen AI tools. The company, which works with large enterprises around the world, offers a range of banking and insurance technology products. Intellect’s project with MongoDB led to improved performance and reduced development cycle times and its platform is now better positioned to onboard clients, provide richer customer insights, and to unlock more gen AI use cases across the firm.

Alongside those immediate benefits, the modernization effort is the first step in Intellect Design's long-term vision to have its entire application suite seamlessly integrated into a single AI service the company has built on MongoDB: Purple Fabric. This would create a powerful system of engagement for Intellect's customers but would only be possible once these key services have all been modernised.

"This partnership with MongoDB has transformed how we approach legacy systems, turning bottlenecks into opportunities for rapid innovation. With this project, we’ve not only modernized our Wealth Management platform, but have unlocked the ability to deliver cutting-edge AI-driven services to clients faster than ever before," said Deepak Dastrala, Chief Technology Officer at Intellect Design.

Legacy systems block scaling and innovation

Intellect Design’s Wealth Management platform is used by some of the world's largest financial institutions to power key services—including portfolio management, systematic investment plans, customer onboarding, and know-your-customers processes—while also providing analytics to help relationship managers deliver personalized investment insights. However, as Intellect’s business grew in size and complexity, the platform’s reliance on relational databases and a monolithic architecture caused significant bottlenecks.

Key business logic was locked in hundreds of SQL stored procedures, leading to batch processing delays of up to eight hours, and limiting scalability as transaction volumes grew. The rigid architecture also hindered innovation and blocked integration with other systems, such as treasury and insurance platforms, reducing efficiency, and preventing the delivery of unified financial services.

In the past, modernizing such mission-critical legacy systems was seen as almost impossible —it was too expensive, too slow, and too risky. Traditional approaches relied on multi-year consulting engagements with minimal innovation, often replacing old architecture with equally outdated alternatives. Without modern tools capable of handling emerging workloads like AI, efforts were resource-heavy and prone to stalling, leaving businesses unable to evolve beyond incremental changes.

MongoDB’s modernization methodology broke through these challenges with a structured approach, combining an agentic AI platform with modern database capabilities, all enabled by a team of experienced engineers.

MongoDB demonstrates AI-driven scalability with Purple Fabric

Before modernizing its Wealth Management platform, Intellect Design had already experienced the transformative power of a modern document database: the company began working with MongoDB in 2019, and its enterprise AI platform Purple Fabric is built on MongoDB Atlas. Purple Fabric processes vast amounts of structured and unstructured enterprise data to enable actionable compliance insights and risk predictions—both of which are critical for customers managing assets across geographies. An example of this is IntellectAI’s work with one of the largest sovereign wealth funds in the world, which manages over $1.5 trillion across 9,000 companies.

By taking advantage of MongoDB Atlas's flexibility, advanced vector search capabilities, and multimodal data processing, Purple Fabric delivers over 90% accuracy in ESG compliance analyses, scaling operations to analyze data from over 8,000 companies—something legacy systems simply couldn’t achieve.

This success demonstrated MongoDB’s ability to handle complex AI workloads and was instrumental in Intellect Design’s decision to adopt MongoDB for the modernization of its Wealth Management platform.

Overhauling mission-critical components

In February 2025, Intellect Design kicked off a project with MongoDB to modernize mission-critical functionalities within its Wealth Management platform. Areas like customer onboarding, transactions, and batch processing all faced legacy bottlenecks—including slow batch processing times and resource-intensive analytics.

With MongoDB’s foundry approach to modernization—in which repeatable processes are used—and AI-driven automation and expert engineering, Intellect Design successfully overhauled these key components within just three months, unlocking new efficiency and scalability across its operations.

Unlike traditional professional services or large language model (LLM) code conversion, which focus solely on rewriting code, MongoDB’s approach enables full-stack modernization, reengineering both application logic and data architecture to deliver faster, smarter, and more scalable systems.

Through this approach, Intellect Design decoupled business logic from SQL-stored procedures, enabling faster updates, reduced operational complexities, and seamless integration with advanced AI tools. Batch-heavy workflows were optimized using frameworks like LMAX Disruptor to handle high-volume transactional data loads, and MongoDB’s robust architecture supported predictive analytics capabilities to pave the way for richer, faster customer experiences.

The modernization project delivered measurable improvements across performance, scalability, and adaptability:

  • With onboarding workflow times reduced by 85%, clients can now access critical portfolio insights faster than ever, speeding their decision-making and investment outcomes.

  • Transaction processing times improved significantly, preparing the platform to accommodate large-scale operations for new clients without delays.

  • Development transformation cycles were completed by as much as 200% faster, demonstrating the efficiency of automating traditionally resource-intensive workflows.

This progress gives Intellect Design newfound freedom to connect its Wealth platform to broader systems, deliver cross-functional insights, and compete effectively in the AI era.

Speeding insights, improving analytics, and unlocking AI

While Intellect Design’s initial project with MongoDB focused on modernizing critical components, the company is now looking to extend its efforts to other essential functionalities within the Wealth platform. Key modules like reporting, analytics workflows, and ad-hoc data insights generation are next in line for modernization, with the goal of improving runtime efficiency for real-world use cases like machine learning-powered customer suggestions and enterprise-grade reporting.

Additionally, Intellect Design plans to leverage MongoDB’s approach to modernization across other business units, including its capital markets/custody and insurance platforms, creating unified systems that enable seamless data exchange and AI-driven insights across its portfolio.

By breaking free from legacy constraints, Intellect Design is unlocking faster insights, smarter analytics, and advanced AI capabilities for its customers. MongoDB’s modernization approach, tools, and team are the engine powering this transformation, preparing businesses like Intellect Design to thrive in an AI-driven future. As industries continue to evolve, MongoDB is committed to helping enterprises build the adaptive technologies needed to lead—and define—the next era of innovation.

To learn more about how MongoDB helps customers modernize without friction—using AI to help them transform complex, outdated systems into scalable, modern systems up to ten times faster than traditional methods—visit MongoDB Application Modernization. Visit the Purple Fabric page for more on how Intellect Design’s Purple Fabric delivers secure, decision-grade intelligence with measurable business impact.

For more about modernization and transformation at MongoDB, follow Vinod Bagal on LinkedIn.

← Previous

Boost Search Relevance with MongoDB Atlas’ Native Hybrid Search

We’re excited to introduce a native hybrid search experience that seamlessly combines the power of MongoDB Atlas’ native text search and vector search capabilities. Now in public preview, this capability leverages reciprocal rank fusion (RRF) to rank result sets from both text and vector searches, significantly improving relevance and user experiences. It simplifies application development by eliminating the need for separate search engines and vector databases, allowing developers to implement hybrid search out-of-the-box and quickly refine search accuracy for their use cases. The new $rankFusion aggregation stage has helped us implement hybrid search much more easily and efficiently, as we can combine the power of keyword search and semantic search under one umbrella in MongoDB Atlas. This has improved the context retrieval accuracy for our Eddy AI chatbot by 30%. Dr. Selvaraaju Murugesan, Head of Data Science, Kovai.co Read the documentation to learn more. Hybrid search: Precision meets semantic relevance Search is the cornerstone of information discovery and application development. Whether you're shopping online, researching a medical condition, or analyzing business data, search helps us find the information we need. As technology evolves, so do user expectations of how they interact with searches and how their searches will perform. Modern applications—from catalog search and product recommendations to retrieval-augmented generation (RAG) and emerging AI agents —require high-quality retrieval to handle unstructured data effectively. Relying solely on text or vector search as a single retrieval technique may not deliver the highest relevance and accuracy. While excellent for precise keyword retrieval, text search can struggle to understand nuanced language or identify semantically similar concepts. On the other hand, vector search is ideal for open-ended queries and high-dimensional data (images, audio, video, etc.), but it may miss crucial information that requires exact matches. Consider the search query “quick and easy Italian dinner recipes.” While traditional text search efficiently identifies recipes containing these keywords in their titles, descriptions, or tags, it often lacks a deeper understanding of concepts like "quick and easy" or the nuances of Italian cuisine beyond literal terms. Adding vector search significantly enhances results by capturing semantically related ideas such as "simple," "minimal prep," or "10-minute meal," alongside recipes featuring classic Italian flavors like tomatoes, olive oil, garlic, oregano, and mozzarella, all suitable for a savory evening meal. This hybrid approach ultimately provides users with a more comprehensive and relevant search experience, balancing accuracy with broader discovery. Combine the best of both worlds for engaging user experiences Organizations are increasingly turning to hybrid search, using the combined strength of text and vector search to maximize the value of data and provide enhanced user experiences. Improved accuracy for search, RAG, and AI agents: By leveraging both approaches, you deliver search results that are semantically relevant and precisely accurate. Hybrid search provides the foundation for more insightful and accurate responses from your generative AI models, reducing hallucinations. Streamlined architecture: Organizations running hybrid search via separate search engines and vector databases typically encounter high complexity and costs. MongoDB simplifies hybrid search implementations by providing this integrated capability in the operational database, eliminating the need to manage multiple systems, reducing costs, and increasing efficiency. Enhanced user experiences: Users benefit from more relevant and comprehensive search results, increasing user satisfaction. How the Financial Times spearheaded AI-powered content discovery with hybrid search The Financial Times, the leading business news organization, has successfully implemented hybrid search, combining MongoDB’s native full-text and vector search capabilities to power content discovery on its website (aiming to deploy the capability across all its digital properties). This enables relevant results for natural language queries and delivers robust content recommendations, providing readers with an enhanced web experience. The highly relevant article suggestions boost engagement and retention by saving valuable time for busy executives—the Financial Times' core subscriber demographic. Hear more about the story in this video . Nowadays with AI becoming more popular for solving different problems, the ability to do vector search alongside the standard keyword search is crucial. MongoDB Atlas is not just offering a database or search. What drew our attention to it was that it's kind of a full package… It gives a lot of things that you can get from a platform out-of-the-box. Dimitar Terziev, Technical Director for Core Platforms, Financial Times Get started with hybrid search in MongoDB Atlas You can now streamline hybrid search implementations with a single $rankFusion aggregation stage. This allows for effortlessly combining full-text and vector search result sets into a unified ranked list, quickly surfacing the most relevant information. Leveraging native and powerful query capabilities within Atlas, you can flexibly combine $rankFusion with various MongoDB aggregation stages—$vectorSearch, $search, $geoNear, $sort, and $match. This allows for the adjustment of weighted criteria, the production of custom relevance scores, and result sorting to address diverse requirements and use cases. See the demo of hybrid search in action. View the documentation to get started.

June 25, 2025
Next →

Don’t Just Build Agents, Build Memory-Augmented AI Agents

Insight Breakdown: This piece aims to reveal that regardless of architectural approach—whether Anthropic's multi-agent coordination or Cognition's single-threaded consolidation—sophisticated memory management emerges as the fundamental determinant of agent reliability, believability, and capability. It marks the evolution from stateless AI applications toward truly intelligent, memory-augmented systems that learn and adapt over time. AI agents are intelligent computational systems that can perceive their environment, make informed decisions, use tools, and, in some cases, maintain persistent memory across interactions—evolving beyond stateless chatbots toward autonomous action. Multi-agent systems coordinate multiple specialized agents to tackle complex tasks, like a research team where different agents handle searching, fact-checking, citations and research synthesis. Recently, two major players in the AI space released different perspectives on how to build these systems. Anthropic released an insightful piece highlighting their learnings on building multi-agent systems for deep research use cases. Cognition also released a post titled: " Don't Build Multi-Agents ," which appears to contradict Anthropic's approach directly. Two things stand out: Both pieces are right Yes, this sounds contradictory, but working with customers building agents of all scales and sizes in production, we find that both the use case and application mode, in particular, are key factors to consider when determining how to architect your agent(s). Anthropic's multi-agent approach makes sense for deep research scenarios where sustained, comprehensive analysis across multiple domains over extended periods is required. Cognition's single-agent approach is optimal for conversational agents or coding tasks where consistency and coherent decision-making are paramount. The application mode—whether research assistant, conversational agent, or coding assistant—fundamentally shapes the optimal memory architecture. Anthropic also highlights this point when discussing the downside of multi-agent architecture. For instance, most coding tasks involve fewer truly parallelizable tasks than research, and LLM agents are not yet great at coordinating and delegating to other agents in real time. Anthropic, Building Multi-Agent Research System Both pieces are saying the same thing Memory is the foundational challenge that determines agent reliability, believability, and capability. Anthropic emphasizes sophisticated memory management techniques (compression, external storage, context handoffs) for multi-agent coordination. Cognition emphasizes context engineering and continuous memory flow to prevent the fragmentation that destroys agent reliability. Both teams arrived at the same core insight: agents fail without robust memory management . Anthropic chose to solve memory distribution across multiple agents, while Cognition chose to solve memory consolidation within single agents. The key takeaway from both pieces for AI Engineers or anyone developing an agentic platform is not just build agents, build Memory Augmented AI agents . With that out of the way, the rest of this piece will provide you with the essential insights from both pieces that we think are important and point to the memory management principles and design patterns we’ve observed in our customers’ building agents. The key insights If you are building your agentic platform from scratch, you can extract much value from Anthropic's approach to building multi-agent systems, particularly their sophisticated memory management principles, which are essential for effective agentic systems. Their implementation reveals critical design considerations, including techniques to overcome context window limitations through compression, function calling, and storage functions that enable sustained reasoning across extended multi-agent interactions—foundational elements that any serious agentic platform must address from the architecture phase. Key insights: Agents are overthinkers Multi-agent systems trade efficiency for capability Systematic agent observation reveals failure patterns Context windows remain insufficient for extended sessions Context compression enables distributed memory management Let's go a bit deeper into how these insights translate into practical implementation strategies. Agents are overthinkers Anthropic researchers mentioned using explicit guidelines to steer agents into allocating the right amount of resources (tool calls, sub-agent creation, etc.), or else, they tend to overengineer solutions. Without proper constraints, the agents would spawn excessive subagents for simple queries, conduct endless searches for nonexistent information, and apply complex multi-step processes to tasks requiring straightforward responses. Explicit guidance for agent behavior isn't entirely new—system prompts and instructions are typical parameters in most agent frameworks. However, the key insight here goes deeper than traditional prompting approaches. When agents are given access to resources such as data, tools, and the ability to create sub-agents, there needs to be explicit, unambiguous direction on how these resources are expected to be leveraged to address specific tasks. This goes beyond system prompts and instructions into resource allocation guidance, operational constraints, and decision-making boundaries that prevent agents from overengineering solutions or misusing available capabilities. Take, for example, the OpenAI Agent SDK with several parameters to describe behaviours of resources to the agent, such as handoff_description , which will be utilized in a multi-agent system built with the OpenAI SDK. This argument specifies how the subagent should be leveraged in a multi-agent system. Or the explicit argument tool_use_behavior that describes to the agent how a tool should be used, as the name suggests. The key takeaway for AI Engineers is that multi-agent system implementation requires an extensive thinking process that involves what tools the agents are expected to leverage, the subagents in the system, and how resource utilization is communicated to the calling agent in a multi-agent system. When implementing resource allocation constraints for your agents, consider traditional approaches of managing multiple specialized databases (vector DB for embeddings, graph DB for relationships, relational DB for structured data) compound the complexity problem, and introduce tech stack sprawl, an anti-pattern to rapid AI innovation. Multi-agent systems trade efficiency for capability While multi-agent architectures can utilize more tokens and parallel processing for complex tasks, Anthropic found operational costs significantly higher due to coordination overhead, context management, and the computational expense of maintaining a coherent state across multiple agents. In some cases, two heads are better than one, but they are also expensive within multi-agent systems. One thing we note here is that the use case used in Anthropic's multi-agent system is deep research. This use case requires extensive exploration of resources, including heavily worded research papers, sites, and documentation, to accumulate enough information to formulate the result of this use case (which is typically a 2000+ word essay on the user’s starting prompt). In other use cases, such as automated workflow with agents representing processes within the workflow, there might not be as much token consumption, especially if the process encapsulates deterministic steps such as database reads and write operations, and its output is execution results that are sentences or short summaries. The coordination overhead challenge becomes particularly acute when agents need to share state across different storage systems. Rather than managing complex data synchronization between specialized databases, MongoDB's native ACID compliance ensures that multi-agent handoffs maintain data integrity without external coordination mechanisms. This unified approach reduces both the computational overhead of distributed state management and the engineering complexity of maintaining consistency across multiple storage systems. Context compression enables distributed memory management Beyond reducing inference costs, compression techniques allow multi-agent systems to maintain shared context across distributed agents. Anthropic's approach involves summarizing completed work phases and storing essential information in external memory before agents transition to new tasks. This, coupled with the insight that Context windows remain insufficient for extended sessions, points to the fact that prompt compression or compaction techniques are still relevant and useful in a world where LLMs have extensive context windows. Even with a 200K token (approximately 150,000 words) capacity, Anthropic’s agents in multi-round conversations require sophisticated context management strategies, including compression, external memory offloading, and spawning fresh agents when limits are reached. We previously partnered with Andrew Ng and DeepLearning AI on a course on prompt compression techniques and retrieval-augmented generation (RAG) optimization. Systematic agent observation reveals failure patterns Systematic agent observation represents one of Anthropic's most practical insights. Essentially, rather than relying on guesswork (or vibes), the team built detailed simulations using identical production prompts and tools and then systematically observed step-by-step execution to identify specific failure modes. This phase in an agentic system has an extensive operational cost. From our perspective, working with customers building agents in production, this methodology addresses a critical gap most teams face: understanding how your agents actually behave versus how you think they should behave . Anthropic's approach immediately revealed concrete failure patterns that many of us have encountered but struggled to diagnose systematically. Their observations uncovered agents overthinking simple tasks, like we mentioned earlier, using verbose search queries that reduced effectiveness, and selecting inappropriate tools for specific contexts. As they note in their piece: " This immediately revealed failure modes: agents continuing when they already had sufficient results, using overly verbose search queries, or selecting incorrect tools. Effective prompting relies on developing an accurate mental model of the agent. " The key insight here is moving beyond trial-and-error prompt engineering toward purposeful debugging . Instead of making assumptions about what should work, Anthropic demonstrates the value of systematic behavioral observation to identify the root causes of poor performance. This enables targeted prompt improvements based on actual evidence rather than intuition. We find that gathering, tracking, and storing agent process memory serves a dual critical purpose: not only is it vital for agent context and task performance, but it also provides engineers with the essential data needed to evolve and maintain agentic systems over time. Agent memory and behavioral logging remain the most reliable method for understanding system behavior patterns, debugging failures, and optimizing performance, regardless of whether you implement a single comprehensive agent or a system of specialized subagents collaborating to solve problems. MongoDB's flexible document model naturally accommodates the diverse logging requirements for both operational memory and engineering observability within a single, queryable system. One key piece that would be interesting to know from the Anthropic research team is what evaluation metrics they use. We’ve spoken extensively about evaluating LLMs in RAG pipelines, but what new agentic system evaluation metrics are developers working towards? We are answering these questions ourselves and have partnered with Galileo, a key player in the AI Stack, whose focus is purely on evaluating RAG and Agentic applications and making these systems reliable for production. Our learning will be shared in this upcoming webinar , taking place on July 17, 2025. However, for anyone building agentic systems, this represents a shift in development methodology—building agents requires building the infrastructure to understand them, and sandbox environments might become a key component of the evaluation and observability stack for Agents. Advanced implementation patterns Beyond the aforementioned core insights, Anthropic's research reveals several advanced patterns worth examining: The Anthropic piece hints at the implementation of advanced retrieval mechanisms that go beyond vector-based similarity between query vectors and stored information. Their multi-agent architecture enables sub-agents to call tools (an approach also seen in MemGPT ) to store their work in external systems, then pass lightweight references—presumably unique identification numbers of summarized memory components—back to the coordinator. We generally emphasize the importance of the multi-model retrieval approach to our customers and developers, where hybrid approaches combine multiple retrieval methods—using vector search to understand intent while simultaneously performing text search for specific product details. MongoDB's native support for vector similarity search and traditional indexing within a single system eliminates the need for complex reference management across multiple databases, simplifying the coordination mechanisms that Anthropic's multi-agent architecture requires. The Anthropic team implements continuity in the agent execution process by establishing clear boundaries between task completion and summarizing the current phase before moving to the next task. This creates a scalable system where memory constraints don't bottleneck the research process, allowing for truly deep and comprehensive analysis that spans beyond what any single context window could accommodate. In a multi-agent pipeline, each sub-agent produces partial results—intermediate summaries, tool outputs, extracted facts—and then hands them off into a shared “memory” database. Downstream agents will then read those entries, append their analyses, and write updated records back. Because these handoffs happen in parallel, you must ensure that one agent’s commit doesn’t overwrite another’s work or that a reader doesn’t pick up a half-written summary. Without atomic transactions and isolation guarantees, you risk: Lost updates , where two agents load the same document, independently modify it, and then write back, silently discarding one agent’s changes. Dirty or non-repeatable reads , where an agent reads another’s uncommitted or rolled-back write, leading to decisions based on phantom data. To coordinate these handoffs purely in application code would force you to build locking layers or distributed consensus, quickly becoming a brittle, error-prone web of external orchestrators. Instead, you want your database to provide those guarantees natively so that each read-modify-write cycle appears to execute in isolation and either fully succeeds or fully rolls back. MongoDB's ACID compliance becomes crucial here, ensuring that these boundary transitions maintain data integrity across multi-agent operations without requiring external coordination mechanisms that could introduce failure points. Application mode is crucial when discussing memory implementation . In Anthropic's case, the application functions as a research assistant, while in other implementations, like Cognition's approach, the application mode is conversational. This distinction significantly influences how agents operate and manage memory based on their specific application contexts. Through our internal work and customer engagements, we extend this insight to suggest that application mode affects not only agent architecture choices but also the distinct memory types used in the architecture. AI agents need augmented memory Anthropic’s research makes one thing abundantly clear: context window is not all you need. This extends to the key point that memory and agent engineering are two sides of the same coin. Reliable, believable, and truly capable agents depend on robust, persistent memory systems that can store, retrieve, and update knowledge over long, complex workflows. As the AI ecosystem continues to innovate on memory mechanisms, mastering sophisticated context and memory management approaches will be the key differentiator for the next generation of successful agentic applications. Looking ahead, we see “Memory Engineering” or “Memory Management” emerge as a key specialization within AI Engineering, focused on building the foundational infrastructure that lets agents remember, reason, and collaborate at scale. For hands-on guidance on memory management, check out our webinar on YouTube, which covers essential concepts and proven techniques for building memory-augmented agents. Head over to the MongoDB AI Learning Hub to learn how to build and deploy AI applications with MongoDB.

July 9, 2025