# generative-ai-tools Published articles for generative-ai-tools. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Building AI Agents in Dart with the Genkit Dart SDK DevFeed: [Building AI Agents in Dart with the Genkit Dart SDK]() Original publisher: [Read original article]() Author: Abhishek Doshi Published: 2026-08-10T23:16:05Z Content type: tutorial Language: en Sources: [Google Developer Experts - Medium]() Topics: [Dart](), [Genkit](), [AI Development](), [Flutter](), [Cloud Functions](), [Firebase](), [SDKs]() Tags: [ai](), [ai-agent](), [ai-agents](), [ai-development](), [cloud-functions](), [dart](), [firebase](), [flutter](), [generative-ai-tools](), [genkit](), [sdk]() ### AI overview This tutorial introduces the Genkit Dart SDK for building AI agents natively in Dart and deploying them to Cloud Functions for Firebase. It explains agent orchestration, conversational state, history, streams, models, tools, flows, and multi-agent delegation. ### Source excerpt Because your Flutter app deserves a brain, and you deserve to never look at a Python traceback again. Let's be honest. We all love Dart. It's clean, it's safe, and it powers our beloved Flutter. But until recently, if you wanted to build serious, multi-step AI agents, the industry basically told you to pack your bags, leave your cozy typed ecosystem, and go write Python. Gross 🤮 Thankfully, Google finally heard our collective sighs and dropped the Genkit Dart SDK. Now, you can build full-stack, hyper-intelligent AI agents natively in Dart and deploy them straight to Cloud Functions for Firebase. No context-switching. No spinning up a random Node.js microservice just to talk to an LLM. Grab your coffee (or your energy drink of choice). Let's look at how Genkit turns your Dart code into an absolute powerhouse. https://medium.com/media/91c2efa4198c043f3f400f216214650e/hrefThe Shift: From "Dumb Chatbots" to "Autonomous Overlords" Building traditional chatbots or strict multi-step UI flows often feels like playing one of those terrible, rigid video games that block you at a level until you do exactly what the developers scripted. Agentic AI, by contrast, is the ultimate open-ended sandbox. An agent doesn't just blindly answer a prompt. It analyzes what the user wants, figures out which tools it needs to achieve the goal, and dynamically orchestrates the steps to get there. With Genkit's new Agents API, all the messy plumbing: maintaining conversational state, keeping track of history, and parsing streams, is handled behind a single API. You just focus on giving it a brain. The Holy Trinity: Models, Tools, and Flows To stop your AI from just hallucinating fan-fiction, Genkit uses a few core primitives. Think of this as the toddler-proofing stage of AI development. Models (ai.generate()): The actual brain. Whether you are using Gemini, Claude, or OpenAI, the API stays exactly the same. Tools (defineTool): This is how you give your AI hands. By defining strict input schemas ## AI Engineer vs. Platform Engineer: Differences in AI Roles DevFeed: [AI Engineer vs. Platform Engineer: Differences in AI Roles]() Original publisher: [Read original article]() Author: Geeta Kakrani Published: 2026-07-22T00:21:05Z Content type: comparison Language: en Sources: [Google Developer Experts - Medium]() Topics: [Artificial Intelligence](), [AI Platform](), [Prompt Engineering](), [MLOps]() Tags: [agentic-ai](), [ai](), [ai-engineer](), [artificial-intelligence](), [career](), [generative-ai-tools](), [llm](), [mlops](), [platform](), [platform-engineering]() ### AI overview The article compares AI Engineer and Platform Engineer roles amid overlapping job titles. It describes AI Engineers as working on model choice, prompts, and agent behavior, while Platform Engineers focus on the infrastructure and operations needed to run AI systems. ### Source excerpt By Geeta Kakrani (GDE in AI & TPU) Open any job board right now and search "AI." Within a few listings, you'll notice something odd: the roles don't line up. Two postings with almost identical requirements have completely different titles. One company's "AI Engineer" is another company's "AI Platform Engineer" is a third company's "MLOps Engineer." This isn't a small naming quirk. For anyone trying to plan a career -- or even just understand where they fit -- it's a real, growing source of confusion. Not because AI itself is hard to understand, but because nobody clearly explains who is responsible for what anymore. The job title problem nobody talks about You'll find titles like: AI Engineer AI Platform Engineer AI Infrastructure Engineer MLOps Engineer LLM Platform Engineer Applied AI Engineer These titles overlap heavily. They pay in similar ranges. They list nearly identical skills. And most of them didn't exist as separate roles even three years ago. This isn't because companies are confused. It's because the industry is still figuring out what to call a very real, very new job -- one that sits between two older disciplines that used to be completely separate. If you're a student or early-career professional trying to plan your path, this title chaos makes it genuinely hard to know what to learn, what to apply for, and what a company actually expects from you on day one. So what's the actual difference? Strip away the job titles, and there are really two different jobs hiding underneath the AI buzzword. The AI Engineer works on the intelligence itself. Choosing which model to use. Designing prompts and instructions. Deciding how an agent should behave, what it should refuse to do, when it should use a tool versus answer directly. This is the "thinking" layer. The Platform Engineer works on everything that lets that intelligence actually run in the real world. Servers, deployment, scaling, security, monitoring, cost control. This is the layer most people never see ## Capital One Announces Open-Source VulnHunter Agentic AI Code Security Tool DevFeed: [Capital One Announces Open-Source VulnHunter Agentic AI Code Security Tool]() Original publisher: [Read original article]() Author: Capital One Tech Published: 2026-07-17T17:01:41Z Content type: release Language: en Sources: [Capital One Tech]() Topics: [open-source-security](), [code security](), [Artificial Intelligence](), [Open Source](), [Vulnerabilities](), [Tooling](), [Developer experience]() Tags: [agentic-ai-security](), [ai-code-security](), [ai-security](), [build](), [claude-code](), [code-vulnerability](), [developer](), [developer-experience](), [developers](), [exploit](), [generative-ai-tools](), [open-source](), [vulnerabilities]() ### AI overview Capital One announces the open-source release of VulnHunter, an agentic AI security tool that analyzes source code from an attacker's perspective. It is designed to identify potentially exploitable defects, map prospective attack paths, and propose targeted code remediations. ### Source excerpt Capital One's open-source, agentic AI code security tool. The rules of software security are changing faster than most defenders can keep pace. Advanced AI models have dramatically lowered the barrier for bad actors to discover and exploit vulnerabilities in software. What once required significant skill and time can now be automated, accelerated, and scaled. The world faces an increasingly short window of time before highly sophisticated, next-generation AI attack capabilities become affordable and accessible to virtually every adversary. Across the industry, organizations are racing to prepare for this paradigm shift. Traditional environmental protections like network segmentation, identity controls, and monitoring remain essential, but are no longer sufficient on their own. The ultimate defense in this new reality requires a shift in approach: organizations need to consider and detect the vulnerabilities in their code and fix them before adversaries can deploy advanced models to discover and exploit them. At Capital One, we decided that the right response to AI-enabled threats wasn't to wait, but to build cutting-edge AI-driven defenses and put them in the hands of defenders everywhere. That's why we are announcing today the open-source release of VulnHunter, an advanced agentic AI security tool designed to apply proactive, attacker-perspective analysis directly to the source code. Developed internally at Capital One, VulnHunter is not a traditional, passive vulnerability scanner. It represents a shift in defensive tooling with an agentic reasoning workflow to identify potentially exploitable defects, map prospective attack paths, and propose highly targeted code remediations. Built for the developer experience To fully unlock the utility of VulnHunter, we knew ease of use mattered. A persistent challenge with traditional security tools is that they are often built primarily to enforce rigid cybersecurity practices, without much consideration for a developer's ac ## AI as the Next Abstraction Layer: How I see engineering evolving at Thumbtack DevFeed: [AI as the Next Abstraction Layer: How I see engineering evolving at Thumbtack]() Original publisher: [Read original article]() Author: Ananda Kanagaraj Sankar Published: 2026-05-22T23:53:03Z Content type: opinion Language: en Sources: [Thumbtack Engineering - Medium]() Topics: [Artificial Intelligence](), [agentic workflows](), [Development](), [Software Engineering](), [engineering-leadership]() Tags: [agentic-workflows](), [ai](), [ai-agent](), [chatgpt](), [copilot](), [development](), [engineering](), [engineering-culture](), [generative-ai-tools](), [software-engineering]() ### AI overview A personal perspective on how AI-assisted development is evolving at Thumbtack, from informal experimentation with ChatGPT and Copilot to end-to-end agentic workflows. The article frames AI as a new abstraction layer and highlights its non-determinism as a major difference from earlier abstractions. ### Source excerpt Over the past year, the way we use AI at Thumbtack has gone through a few phases. Early on it was mostly curiosity, people experimenting with ChatGPT and Copilot on side projects, sharing tips in Slack. Then the models got noticeably better at working inside real, mature codebases (not just greenfield projects) and the conversation shifted. It stopped being about whether we should adopt AI-assisted development and became about how. Lately, it is moving towards the adoption of end to end agentic workflows for development. I've been thinking a lot about what this shift means, not just for our codebase or our velocity, but how it impacts what it actually feels like to be an engineer here. What follows is my personal perspective, shaped by leading engineering on our monetization teams and informed by how Thumbtack's engineering leadership has been approaching this across teams. Another layer of abstraction If you zoom out, software engineering has always been a story of rising abstraction. We went from assembly to C, from C to Java, from hand-rolled servers to cloud-native infrastructure. And each time, the craft shifted rather than shrinking. For example, managing memory manually was replaced by designing distributed systems. I think AI-assisted development is the next version of that pattern.The difference this time isn't that the new layer takes on implementation work. Compilers always did some of that, with their own undefined behavior and implementation-defined choices. The difference is the leap in non-determinism. The earlier abstractions were designed to be mostly deterministic and mostly non-leaky, and AI tools break that pattern. The same prompt produces different code on different days, with different trade-offs and different bugs -- that's a bigger shift than swapping languages. I keep coming back to the same historical pattern: the engineers who thrive are the ones who can operate at the new layer, not the ones who insist on staying anchored to the old one. ## New updates to A2UI and Flutter's GenUI package DevFeed: [New updates to A2UI and Flutter's GenUI package]() Original publisher: [Read original article]() Author: Andrew Brogdon Published: 2026-05-14T14:18:22Z Content type: tutorial Language: en Sources: [Flutter - Medium]() Topics: [Flutter](), [ui](), [Protocol (disambiguation)](), [Framework](), [Large Language Model](), [Error Handling]() Tags: [android](), [architecture](), [error-handling](), [flutter](), [framework](), [generative-ai-tools](), [generative-ui](), [ios](), [language-models](), [protocol](), [retry](), [updates]() ### AI overview This migration guide explains updates to Flutter's genui package and the A2UI protocol. The package adopts A2UI v0.9, shifts from a Structured Output First to a Prompt First approach using JSON blocks in agent responses, and separates UI state and rendering, message transport, and conversation management into distinct layers. ### Source excerpt Generative UI, or GenUI for short, is a user experience pattern in which an agent not only generates content, but also makes decisions about how that content should be displayed and made interactive for the user. For Flutter developers, implementing GenUI means using A2UI, an open protocol that defines a way for agents and clients (or "renderers") to collaborate on the composition and state of a user interface. To capitalize on this, the Flutter team built genui, a package that uses A2UI to connect with an agent and provide it with a catalog of widgets to use, and then presents those widgets to the user. Both the genui package and the A2UI protocol recently got an update! The latest release of genui introduces several architectural changes to the framework. Driven by adoption of v0.9 of the A2UI protocol, this update shifts genui from a "Structured Output First" philosophy in which A2UI messages were streamed through structured output APIs to a "Prompt First" approach in which agents include blocks of JSON as text in their responses. It also decouples the architecture, providing more direct control over how your application interacts with Large Language Models (LLMs). If you are migrating an app from v0.7.0 to v0.9.0 of the genui package, this guide covers the necessary steps, from dependency cleanup to wiring up your new chat loops. Architecture decoupling In previous versions, GenUI relied on a series of classes based on ContentGenerator. These classes hid the details of prompt construction, LLM network calls, and response parsing. The latest version of package:genui removes ContentGenerator. Instead, the framework is now split into distinct layers: Engine (SurfaceController): Manages the state and rendering of your UI. Transport (A2uiTransportAdapter): Streams messages between the agent and renderer. Facade (Conversation): Provides a high-level API for managing chat states. This decoupling means you have control over chat history, retry logic, and error handling. ## Expedia's Service Telemetry Analyzer DevFeed: [Expedia's Service Telemetry Analyzer]() Original publisher: [Read original article]() Author: Nikos Katirtzis Published: 2026-04-28T11:01:01Z Content type: article Language: en Sources: [Expedia]() Topics: [telemetry](), [distributed-systems](), [Prompt Engineering](), [Artificial Intelligence](), [API](), [Cloud](), [Containers](), [Orchestration]() Tags: [ai](), [api](), [distributed-systems](), [generative-ai-tools](), [metric](), [observability](), [prompt-engineering](), [root-cause-analysis](), [site-reliability-engineer](), [software-engineering](), [telemetry]() ### AI overview Expedia's Service Telemetry Analyzer (STAR) is an early web-based system for investigating service degradations and outages with service telemetry data and AI models. It uses predefined multi-step diagnostic workflows, domain-specific prompt engineering, and engineering knowledge spanning applications, infrastructure, cloud, containers, orchestration, and distributed systems. ### Source excerpt Expedia Group Technology -- EngineeringA system that facilitates investigation of service degradations and outages using service telemetry data and AIPhoto by Evangelos Mpikakis on Unsplash. The recent advancements in the artificial intelligence space make us re-evaluate how work is done. From programming, to designing systems, or even operating them in production. While there is considerable focus on automating programming, one area which could undergo transformation is how we monitor and operate our systems and services. A few of us came together and designed Expedia's® Service Telemetry Analyzer (STAR), an early iteration of a system that facilitates investigation of service degradations and outages using service telemetry data and AI models and techniques. Expedia's Service Telemetry Analyzer (STAR) The early product offering includes: Execution of multi-step workflows. Integration of software and systems engineering knowledge, including application and infrastructure, cloud, containerization, and orchestration patterns, into diagnostic workflows for complex distributed systems. Application of domain-specific prompt engineering for metric and root cause analysis. Utilization of advanced off-the-shelf AI models. Implementation of prompt engineering techniques, including role prompting, prompt chaining, and generated knowledge prompting. Design The product offering is a web-based service that provides an application programming interface (API). While AI agents and chatbots are gaining traction, we aimed to start with something a) simple, b) precise (to a certain extent, considering the potential hallucinations of the models), and c) that avoids the additional and currently less understood failure modes of an agent. As this field evolves, we will continue to iterate on the design. Therefore, there is limited context engineering beyond domain-specific prompts; for instance, there is no support for function calling / tool use, short-term and long-term memory, or retri ## From Zero to Hero: Localization-Led Generative AI at Udemy DevFeed: [From Zero to Hero: Localization-Led Generative AI at Udemy]() Original publisher: [Read original article]() Author: Nishanth Gandhidoss Published: 2025-09-22T17:47:18Z Content type: article Language: en Sources: [Udemy Engineering]() Topics: [Localization (l10n)](), [Generative AI](), [Large Language Model](), [datasets]() Tags: [ai](), [features](), [generative-ai](), [generative-ai-tools](), [implementation](), [llm](), [llm-applications](), [machine-learning](), [machine-translation](), [retrieval-augmented-gen](), [techniques](), [translation]() ### AI overview Udemy describes how it localized generative AI features, including Skills Mapping and its in-course AI Assistant, to serve learners in multiple languages. The article compares translation management systems, multilingual LLMs, and hybrid strategies, emphasizing trade-offs among implementation speed, language coverage, fluency, cultural nuance, and domain precision. ### Source excerpt By Nishanth Gandhidoss, Senior Staff Data Scientist @ Udemy Why Multilingual Generative AI Matters Generative AI is rapidly changing how people learn and work, but those gains are only realized when the technology speaks the user's language. Over the past year at Udemy, we prioritized breaking the English-only barrier so our Gen AI features, most critically Skills Mapping and the in-course AI Assistant, could deliver value for learners across the globe. Our approach balanced speed, coverage, and quality, allowing us to move quickly without sacrificing fidelity in markets where nuance matters. Below we describe the localization strategy we adopted, why we made those trade-offs, and the operational practices that made the rollout repeatable, scalable, and quick. Localization Strategies When deciding how to localize a Gen AI product, it is helpful to think of options on a spectrum from low to high complexity. The simplest approach provides broad language coverage fast, while the most involved approach optimizes for fluency, cultural nuance, and domain precision. At Udemy, we researched and organized our work around three primary strategies: a translation management system (TMS) for rapid implementation with broader coverage, a multilingual LLM system (MLS) for high-fidelity experiences, and a hybrid approach to balance reach and quality. As each strategy is introduced below, we briefly explain the industry-standard localization techniques they draw on, with examples, so the differences are clear. Translation Management System (TMS) At the simplest end of the spectrum, we have the TMS approach. With a TMS, the user interacts in their own language, but the AI model itself operates in English input/output. The system first detects the user's input language, say, in Spanish, and sends the input through a machine translation (MT) service that converts it into English. The LLM then generates an English response, and that response is translated back into the user's input lang ## Building Your First MCP Server with Genkit DevFeed: [Building Your First MCP Server with Genkit]() Original publisher: [Read original article]() Author: Pavel J Published: 2025-04-25T14:09:50Z Content type: tutorial Language: en Sources: [Firebase Developers - Medium]() Topics: [Genkit](), [Model Context Protocol](), [MCP Server](), [backends](), [Firestore](), [Structured-data](), [AI Development](), [Testing](), [developer tooling]() Tags: [ai](), [backends](), [firebase](), [firestore](), [generative-ai](), [generative-ai-tools](), [genkit](), [guides](), [mcp](), [mcp-server](), [schema](), [testing]() ### AI overview This tutorial explains how to build a custom MCP server with Genkit. It covers defining order data schemas with zod, generating optional test data and storing it in Firestore, creating flows to retrieve orders, and exposing tools that can be called by AI models or external clients such as Cline. ### Source excerpt Generative AI Building robust backends for AI applications often involves integrating various components. The Model Context Protocol (MCP) offers a standardized communication layer, and Genkit provides a powerful framework to leverage it. This article guides you through creating a custom MCP server using Genkit, from defining data schemas to interacting with the server using development tools like Cline. This article assumes some familiarity with Genkit concepts like flows and tools. Learn more about Genkit: https://firebase.google.com/docs/genkit If you prefer this tutorial in video format, check out: https://medium.com/media/908bbf0df5ad1306b125a4c7411c203c/href1. Defining Your Data Schema Before building any application, you need to define the structure of your data. In this example, we're building a system to manage website orders for a consulting company. We use zod, a popular schema declaration library, integrated with Genkit. The OrderSchema defines the necessary fields for each order: const OrderSchema = z.object({ id: z.string().describe("Order Id. Format: A-XXX-XXX, ex. A-123-456"), name: z.string().describe("Name of the business"), colorScheme: z.object({ mainColor: z.string().describe("RGB color prefixed with #, ex. #FFAA66"), highlight: z.string().describe("RGB color prefixed with #, ex. #AA6611"), textColor: z.string().describe("RGB color prefixed with #, ex. #224455"), }), email: z.string(), jobDescription: z .string() .describe( "Detailed description of the website they need. Ex. if they are a construction " + "company describe what they want on the home, contact age, testimonials, etc. " + "pages. Not too crazy, usually static website." ), address: z.string(), }); This schema clearly outlines each piece of information associated with an order, including nested details like the colorScheme. 2. Generating Realistic Test Data (optional) During development, you need ways to both populate your system with test data and inspect that data. Manually creatin ## Firestore for Image Embeddings DevFeed: [Firestore for Image Embeddings]() Original publisher: [Read original article]() Author: Mete Atamel Published: 2024-10-29T19:13:03Z Content type: tutorial Language: en Sources: [Firebase Developers - Medium]() Topics: [Firestore](), [Embeddings](), [LangChain](), [multimodal](), [Cloud]() Tags: [ai](), [cloud-storage](), [embeddings](), [firestore](), [generative-ai-tools](), [langchain](), [llms](), [multimodal](), [retrieval](), [search](), [software-development](), [web]() ### AI overview A tutorial showing how to use FirestoreVectorStore and LangChain to generate, store, and retrieve image embeddings for similarity search. It covers multimodal embedding models, images from local storage, Google Cloud Storage, and the web, plus text- and image-based queries. ### Source excerpt Powering LLMs with Firestore In my previous post about Firestore for Text Embedding and Similarity Search, I talked about how Firestore and LangChain can help you to store text embeddings and do similarity searches against them. With multimodal embedding models, you can generate embeddings not only for text but for images and video as well. In this post, I will show you how to store image embeddings in Firestore and later use them for similarity search. Image embeddings support in FirestoreVectorStore As a recap from the previous post, the Firestore for LangChain project provides a FirestoreVectorStore which simplifies storage and retrieval of embeddings. Initially, FirestoreVectorStore only supported text embeddings, but we recently added a new add_images method to store image embeddings. Likewise, we added the similarity_search_image method to run similarity searches with image embeddings. Let's take a closer look at how you can use FirestoreVectorStore in LangChain to work with image embeddings. First, you need to create a multimodal embedding model that can embed images: from langchain_google_vertexai import VertexAIEmbeddings embedding = VertexAIEmbeddings( model_name="multimodalembedding", project=PROJECT_ID, location="us-central1" ) Then, you create a Firestore-backed vector store with the embedding model: from langchain_google_firestore import FirestoreVectorStore vector_store = FirestoreVectorStore( collection=COLLECTION_NAME, embedding_service=embedding, ) Now, you can add images stored locally, in Google Cloud Storage, or any image on the web as follows: ids = ["landmark1.png", "landmark2.png", "landmark3.png"] image_paths = [ "gs://your-storage-bucket/landmark1.png", "./images/landmark2.png", "https://your-website/images/landmark3.png", ] vector_store.add_images(image_paths, ids=ids) This creates embeddings for each image and saves them to Firestore. Afterwards, you can perform a similarity search with a text query: vector_store.similarity_search("stadiu ## Scaling PayPal's AI Capabilities with PayPal Cosmos.AI Platform DevFeed: [Scaling PayPal's AI Capabilities with PayPal Cosmos.AI Platform]() Original publisher: [Read original article]() Author: Jun Yang Published: 2024-05-02T16:27:03Z Content type: article Language: en Sources: [PayPal Technology]() Topics: [AI Platform](), [Development](), [MLOps](), [Deployment](), [Machine learning]() Tags: [ai-ml](), [ai-platform](), [artificial-intelligence](), [deployment](), [development](), [enterprise-technology](), [generative-ai-tools](), [mlops](), [paypal]() ### AI overview This article describes PayPal Cosmos.AI Platform, an internal enterprise AI/ML platform conceived around 2020 and generally available since mid-2022. It aims to support the end-to-end machine learning development lifecycle by scaling development, deployment, and operations with MLOps capabilities. The article states that the platform has been adopted across business domains, with thousands of users and hundreds of deployed models serving real-time and batch inference requests. ### Source excerpt By Jun Yang, Zhenyin Yang, and Srinivasan Manoharan, based on the AI/ML modernization journey taken by the PayPal Cosmos.AI Platform team in the past three years. Source: Dall-E 3 AI is a transformative technology that PayPal has been investing in as a company for over a decade. Across the enterprise, we leverage AI/ML responsibly to address a wide range of use cases -- from fraud detection; improving operational efficiencies; providing personalized service and offers to customers; meeting regulatory obligations, and many more things. To accelerate PayPal's innovation and deliver incredible value to our customers through technology, we are working to put the innovative power of artificial intelligence into the hands of more employees across different disciplines and accelerate time-to-market for building and deploying AI/ML powered applications, in service of our customers and in alignment with our Responsible AI principles. The blog below details a key internal platform that is helping us do this: PayPal Cosmos.AI Platform. AI/ML Platform: The Enterprise Approach Over the years, many engineering systems and tools have been developed to facilitate this practice at PayPal, addressing various needs and demands individually as they emerged. Several years ago, as we began to expand AI/ML across all core business domains, it became increasingly evident that the prevailing approach of having a collection of bespoke tools, often built and operated in their own silos, would not meet the needs for large scale AI/ML adoptions across the enterprise. Conceived around 2020, PayPal Cosmos.AI Platform aims at providing end-to-end Machine Learning Development Lifecycle (MLDLC) needs across the enterprise by modernizing and scaling AI/ML development, deployment and operation, with streamlined end-to-end Machine Learning operations (MLOps) capabilities and experiences, making it faster, easier, and more cost effective to enable businesses through AI/ML solutions. Since its official GA