Category: AI Engineering

  • Upskilling Engineering Teams for the AI Era 

    Upskilling Engineering Teams for the AI Era 

    Technology leaders across every industry are seeking ways to optimize AI’s benefits throughout their software development workflows. This widespread adoption is shaping the software development landscape and raising important questions about the future of work in the tech industry. While many are concerned about how AI’s implementation will affect jobs, it’s more likely that AI…

  • How To Properly Introduce AI Bots to Your App Using Permit.io and Arcjet

    How To Properly Introduce AI Bots to Your App Using Permit.io and Arcjet

    The need to introduce AI Bots into our applications is becoming a major part of software development — but how do you do that securely? Learn to manage access for GenAI bots with fine-grained authorization using Permit.io and Arcjet. Traditionally, we have tried to prevent bots from gaining access to our application. Of course, there…

  • How Salesforce Built an AI-Driven App in Under 4 Days

    How Salesforce Built an AI-Driven App in Under 4 Days

    Word got out that the Salesforce events team planned to build a custom AI for the Dreamforce conference app. This surprised the online CRM’s AI team, which had already created and was using a new AI enterprise technology stack called Agentforce to build AI agents for customers. The Agentforce platform became generally available Tuesday, but…

  • Building a Realistic Pathway to Production-Ready GenAI

    Building a Realistic Pathway to Production-Ready GenAI

    Generative AI (GenAI) is everywhere. It promises to transform IT operations (ITOps) by automating workflows, resolving production issues faster and streamlining our work by eliminating manual tasks. But is this vision of GenAI (especially in service management and AIOps) delivering on the promises? Beneath the excitement lies a fundamental question about the nature of GenAI…

  • Making Adding AI Apps with Postgres Easier for Developers

    Making Adding AI Apps with Postgres Easier for Developers

    Under Embargo Until 10/29 @ 6 AM PT [note to editors: all the lowercase references to pgwhatever are correct.] With the rise of AI and large language models (LLMs), developers called on to create AI applications might feel they’ve been shuttled into alien terrain. Open source PostgreSQL database vendor Timescale’s answer to this is a…

  • A Look at Gradio’s AI Playground for Machine Learning Devs

    A Look at Gradio’s AI Playground for Machine Learning Devs

    Gradio, a component library for Machine Learning developers available on Hugging Face, is now up to version 5. One of its notable new features is “an experimental AI Playground,” which allows you to “use AI to generate or modify Gradio apps and preview the app right in your browser immediately.” Backend devs focusing on AI…

  • Don’t Trust Security in AI-Generated Code

    Don’t Trust Security in AI-Generated Code

    Speaking from more than 20 years of experience in development and cybersecurity, developers need to use all the cutting-edge, time-saving, and productivity-boosting tools. It’s meticulous, time-consuming work to ensure you commit to high-quality, functional code, and the software development life cycle always demands more. As such, nowadays, almost all developers use some form of AI-generated…

  • How Apollo Makes LLMs More Reliable with GraphQL

    How Apollo Makes LLMs More Reliable with GraphQL

    NEW YORK — We all know how AI/ML can be a hit or miss for DevOps support and application development. However, in the case of GraphQL search queries, it appears to function at least reasonably well — and there is much more to come. This was one of the key takeaways from Apollo GraphQL’s Annual…

  • How To Define an AI Agent Persona by Tweaking LLM Prompts

    How To Define an AI Agent Persona by Tweaking LLM Prompts

    In AI Agents: A Comprehensive Introduction for Developers, I introduced the key traits of AI agents by comparing them to an employee working in an organization. In this article, we will explore how to add a persona to an agent by taking advantage of the system prompts available for large language models (LLM) and vision…

  • AI Engineering: Level Up Your IT Career

    AI Engineering: Level Up Your IT Career

    In the modern enterprise landscape, data and artificial intelligence (AI) are reshaping many industries, including telecommunications, financial services and health care. AI engineers are central to this transformation, bridging the gap between data and impactful business outcomes. Scientists and researchers develop the foundational artificial intelligence algorithms and build accurate models as AI artifacts, while AI…

  • Meet Early: The AI That Catches Bugs Before They Bite

    Meet Early: The AI That Catches Bugs Before They Bite

    Early, a Tel Aviv, Israel-based startup that provides a generative AI code quality platform, officially launched earlier this month. The company’s AI-powered solution, EarlyAI, acts as a test AI agent that automatically generates high-quality tests to help developers detect and fix bugs early in the development cycle. Since its soft launch in August, the platform…

  • Self-Driving Software: Solver Launches Autonomous AI Coder

    Self-Driving Software: Solver Launches Autonomous AI Coder

    What self-driving is to the automobile industry, Solver hopes to be for the programming industry. Solver is the brainchild of Mark Gabel, formally the chief scientist at Viv (an AI assistant company founded by the creators of Siri and then sold to Samsung in 2016). Gabel claims Solver is a paradigm shift in AI-assisted coding,…

  • AI Agents: A Comprehensive Introduction for Developers

    AI Agents: A Comprehensive Introduction for Developers

    Agents and agentic workflows are the latest buzzwords in the generative AI ecosystem. But like any emerging technology, the terminology and definition of agents is diverse and often confusing for developers. To help demystify agents, in this article we offer a comprehensive resource for developers who are already familiar with the fundamentals of large language…

  • Graph RAG: How To Squeeze More Value From AI

    Graph RAG: How To Squeeze More Value From AI

    These days, it seems like everyone is doing retrieval-augmented generation (RAG), and more and more are adding knowledge graphs to make graph RAG. But many of them get stuck in the R&D stage, struggling (at least a little bit) to pull their proofs of concept into production. Graph RAG, just like most AI technologies, is…

  • How To Build an AI Agent To Control Household Devices

    How To Build an AI Agent To Control Household Devices

    In the last article, I introduced Sensecap Watcher from Seeed Studio, a physical AI agent that can take action based on what it sees. In this tutorial, I will show you how I built an agent that automatically turns on a Philips Wiz smart bulb when Sensecap Watcher detects that a person is reading a…

  • Make the Most of AI Agents: Tips and Tricks for Developers

    Make the Most of AI Agents: Tips and Tricks for Developers

    The arrival of AI agents has provided software developers with a new method of working with AI. We spoke with several AI agent tool providers and developers to get their take on how AI agents provide new capabilities for devs and what to do to get started. If you’re a bit fuzzy on how AI…

  • Get Started With Meta’s Llama Stack Using Conda and Ollama

    Get Started With Meta’s Llama Stack Using Conda and Ollama

    I like to show tech working in my posts, and on my modest pre-silicon MacBook. So when Meta’s Llama 3.2 and Llama Stack for developers were released, I was keen to try it out. However, I discovered that the process is still a little complex and not quite flexible enough. First of all, what is…

  • The Architect’s Guide to Interoperability in the AI Data Stack

    The Architect’s Guide to Interoperability in the AI Data Stack

    As artificial intelligence (AI) and machine learning continue to scale across industries, data architects face a critical challenge: ensuring interoperability in an increasingly fragmented and proprietary ecosystem. The modern AI data stack must be flexible, cost-efficient and future-proof, all while avoiding the dreaded vendor lock-in that can stifle innovation and blow up your budget. Why…

  • The Secret Sauce for Vector Search: Training Embedding Models

    The Secret Sauce for Vector Search: Training Embedding Models

    In their zeal to reap the countless benefits of generative machine learning models, organizations are rushing to embed their data for various forms of vector similarity search. Many are focused on prompt engineering and getting the best results for ad-hoc question answering, natural language search and summarizations of their data. Some are concerned with prompt…

  • How To Increase Plasticity in LLMs and AI Applications

    How To Increase Plasticity in LLMs and AI Applications

    Deep learning models — including large language models like ChatGPT, Gemini and Claude — seem like powerful tools that have been trained on a large body of knowledge. But there are limits to their knowledge, because deep learning models will often have a cut-off date to their training, meaning they won’t know any up-to-date information…

  • Advanced Retrieval-Augmented Generation (RAG) Techniques

    Advanced Retrieval-Augmented Generation (RAG) Techniques

    Retrieval-Augmented Generation (RAG) has experienced a number of advancements in recent years alongside its increasing popularity. In my talk at All Things Open (ATO) 2024 on Oct. 28, I will cover a number of the techniques needed to build better RAG. These include chunking, choosing an embedding model and metadata structuring. Considerations for Building a…

  • OSI Finalizes a ‘Humble’ First Definition of Open Source AI

    OSI Finalizes a ‘Humble’ First Definition of Open Source AI

    After nearly three years of planning, including community meetings and a months-long global “roadshow” to gather feedback, the Open Source Initiative (OSI) has published Release Candidate 1 of its long-awaited definition for open source AI. The document, published Oct. 2, includes definitions for four different kinds of data: open, public, obtainable and unshareable. It also…

  • Agents Shift GenAI From Order Takers to Collaborators

    Agents Shift GenAI From Order Takers to Collaborators

    From the use of modular components to the well-defined rules and syntax of programming languages, the way we build applications makes software development an ideal use case for generative AI (GenAI). Therefore, it is no surprise that software development is one of the first areas being transformed. While the industry has made great strides in…

  • How AI Agents Are About To Change Your Digital Life

    How AI Agents Are About To Change Your Digital Life

    Imagine learning a new skill or understanding a complex concept, only to forget it entirely the moment you step away. Then when you need that knowledge again, it’s gone and you have to start from scratch. Frustrating, right? This lack of continuity would make it nearly impossible to build on your experiences or tackle increasingly…

  • AI Agents and Copilots: SAP Introduces Deeper Integrations

    AI Agents and Copilots: SAP Introduces Deeper Integrations

    SAP has launched collaborative AI agents in Joule, its generative AI copilot, as a further effort to provide deeper integrations across its software ecosystem. “You’ve likely all heard others in the industry talk about AI agents a lot over the past few months, but one thing you’re not hearing about is the ability for those…

  • PDFs Get an Easier Entry to GenAI via New RAG Architecture

    PDFs Get an Easier Entry to GenAI via New RAG Architecture

    Although a picture is worth a thousand words, preparing visually rich, multimodal documents, such as PDFs, for a retrieval-augmented generation (RAG) workflow can be both time-consuming and error-prone. In industries where accuracy is critical, like healthcare or financial services, documents like radiology reports or financial statements often contain images or charts that provide valuable contextual…

  • Anyscale: New Optimized Runtime for Ray, Kubernetes Operator

    Anyscale: New Optimized Runtime for Ray, Kubernetes Operator

    Anyscale, the fast-emerging company behind the open source AI compute engine Ray, revealed a list of new products and services at its annual user conference in San Francisco earlier this week. Among them: An optimized Ray runtime, created in response to customer feedback, and a Kubernetes operator. The three-day Ray Summit event, which ended Thursday…

  • Go Big or Go Home: What GitHub Learned Building Copilot

    Go Big or Go Home: What GitHub Learned Building Copilot

    Copilot Launched in June 2021, GitHub’s Copilot feature now has 1.8 million paying users, with 50% of their code written by Copilot. For better or worse, the feature, an AI-driven code completion tool, is popular with users. But how did GitHub develop this cutting-edge AI-based app? Earlier this week, Eddie Aftandilian, a principal researcher for GitHub’s…

  • Build an AI-Powered Question-Answering Application

    Build an AI-Powered Question-Answering Application

    You’ve got a ton of data — structured, unstructured, you name it — and you want to put it to use in an application. Whether you’re looking to gain insights or find answers, you need a solution that delivers results quickly and accurately. With the right tools, this might be easier than you think. The…