AI/ML

Post Image

Using AI to Simplify Developer Onboarding

Today, the market is filled with LLM-powered tools, with new and more advanced options emerging almost daily. In this article, we focus on one use case: integrating AI into the software development process to simplify onboarding for new developers.Onboarding a new developer involves a mix of tasks for both the newcomer and the existing team, often making the process hard to standardise or automate. Early days typically include reading documentation, meeting the team, attending sessions, and waiting for access to...

Read
Post Image

Redefining Risk Management With AI

Across industries, AI is revolutionizing risk management by overcoming the limitations of traditional methods. It achieves this by analyzing large datasets to identify emerging threats and anomalies, while generative AI interprets unstructured information and provides clear answers to complex risk-related questions.To explore these advancements, Sahaj Software recently hosted a roundtable with leaders from multiple industries in New York. The conversation revolved around specific risk challenges in sectors like finance, healthcare, pharma, manufacturing, and publishing, emphasizing the need for AI-driven solutions....

Read
Post Image

MCP and Doc-Monitor Transform External Services Integration

(AI-generated image)In today's interconnected world, integrating with a vast ecosystem of SaaS providers presents a significant challenge. It is not just about understanding and creating OpenAPI REST clients for numerous APIs, but also mapping them to our internal domain model. The real hurdle lies in the continuous maintenance of both the client and the mapping code as these third-party SaaS APIs evolve.Imagine we're building a neobank in the UK. A key feature of our app is providing users with a...

Read
Post Image

Hybrid AI: Leaner and More Scalable Intelligence

In recent years, generative AI has transformed the way we think about building intelligent systems. With models like GPT, Claude, and DALL·E, we have gained tools that can understand, create, and reason in ways that once seemed out of reach. These models have opened the door to powerful new capabilities; from natural language understanding to dynamic content generation. However, as adoption grows, there emerges a pattern of usage. We have started using massive, general-purpose models for tasks that don’t really...

Read
Post Image

My Journey With Cursor AI: More Than Just Code Completion

If you've been coding for a while, you've probably tried dozens of IDEs and editors. Each new tool promises to be the silver bullet that solves all your development problems. Most fall short.When I first heard about Cursor AI, I was skeptical. "Great, another VS Code clone with some fancy autocomplete," is what I thought. I couldn't have been more wrong.My introduction to Cursor was like learning to drive an F1 car after years of riding a bicycle. The power...

Read
Post Image

Smart Workflows: The Key to Boosting Adoption and Fuelling Growth

We are living in an exciting time, right in the middle of a tech revolution. The ever changing technology is helping businesses solve innovative challenges, and at the same time, user expectations are changing faster than ever. To stay ahead, businesses must anticipate and adapt to these changes. Understanding and meeting these expectations is critical because how users perceive and interact with technology can significantly impact their trust and satisfaction.The key to this transformation? —a shift from static experiences to...

Read
Post Image

Multilingual AI in Text and Voice

In recent years, multilingual AI has rapidly evolved, transforming how organizations approach translation, Natural Language Understanding (NLU), and voice processing. As the world becomes increasingly interconnected, the ability for technology to understand and interact with diverse languages is crucial and so is this capability in both text and voice. This article presents an expert-level perspective, highlighting recent innovations, open challenges, and a comparative analysis between proprietary and open-source models. We summarize key highlights of research and applications in this space...

Read
Post Image

Intrinsic Dimension Part 2: Measuring the True Complexity of a Model via Random Subspace Training

In Part I of this series, we delved into the concept of Intrinsic Dimension (ID) and its implications on fine-tuning. To recap, the intrinsic dimension of an objective function measures the minimal number of parameters needed to achieve satisfactory performance on a given task (Li et al.,¹). For example, in their seminal work, the authors demonstrated that a fully connected neural network with a total of parameters (architecture: 784–200–200–10) achieved a 90% performance threshold on the MNIST dataset with an...

Read
Post Image

Intrinsic Dimension Part 1: How Learning in Large Models Is Driven by a Few Parameters and Its Impact on Fine-Tuning

Learned over-parameterized models inherently exist within a low intrinsic dimension {Li et al.¹ and Aghajanyan et al.³}. To understand this concept better, let’s delve into the following questions:What is a model’s dimension?What is an Objective function and its landscape?What is ID and how can it be visualized through graphs of convex and non-convex landscapes?How do you identify the ID of a network?If the ID of an objective function is so low, why do we have such large networks in the...

Read
Post Image

Ten Insights That Took My CrewAI Results to the Next Level

If you are new to the agentic way of problem-solving, then you might be wondering how it differs from writing code the usual way. The focus while writing code is on . The . While working with agents, the to ensuring that . If the i, then and there.Before we dive into how we can improve our results while using CrewAI, let us revisit the most important concepts first.🤖 → a unit that can , and to other suitable agents....

Read