Roundblock

?? Leazy AI Launches: A New Era for Immigration Law Firms Introducing Leazy AI, the first AI-driven legal application designed to transform immigration services. Leveraging advanced LLM technology, our application includes: - An Immigration Handbook Chatbot: A comprehensive tool offering up-to-date legal knowledge and case insights. - Automated workflows for EB1A / NIW cases, enhancing efficiency and accuracy. - Productivity tools such as case checkers and Visa bulletin updates. Leazy AI is tailored to empower immigration law firms by improving process efficiency and reducing the complexity of case handling. ?? Special Launch Offer: Enjoy a 3-month free trial and get exclusive early access to new features. ?? Interested in a demo? See the difference Leazy AI can make for your practice: Book a Meeting via https://lnkd.in/gkPVTXZ9 We are committed to continuously rolling out new features to meet the evolving needs of your firm. ?? Learn more about us at https://www.leazy.ai Join us as we redefine immigration legal services with state-of-the-art technology. Elevate your practice with Leazy AI. #LeazyAI #ImmigrationLaw #LegalTech #Innovation #LawFirmManagement #AI

This repo covers everything you need to know about MLOps. The goal of the series is to understand the basics of MLOps like model building, monitoring, configurations, testing, packaging, deployment, cicd, etc. Week 0: Project Setup Week 1: Model Monitoring - Weights and Biases Week 2: Configurations - Hydra Week 3: Data Version Control - DVC Week 4: Model Packaging - ONNX Week 5: Model Packaging - Docker Week 6: CI/CD - GitHub Actions Week 7: Container Registry - AWS ECR Week 8: Serverless Deployment - AWS Lambda Week 9: Prediction Monitoring - Kibana https://lnkd.in/gwP4dTpN ?? Repost this if you found it useful. ↓ Are you technical? Check out?https://AlphaSignal.ai?to get a daily summary of breakthrough models, repos and papers in AI. Read by 200,000+ devs.

Announcing new aisuite capability: Easy function calling with LLMs! Function calling (tool use) is an important capability for agentic workflows and other LLM applications, but is cumbersome for developers to use (left column in image). Our open-source aisuite package simplifies it to just one command (right column), and works for multiple LLM providers. Hope this makes implementing agents easier for developers, and thanks Rohit Prsad & team for working with me on this! Credit also goes to Matthew Carrigan for the neat idea of getting tool definitions from docstrings. https://lnkd.in/gB3AWxvh

Microsoft’s quantum researchers have created something remarkable: the world’s first quantum processor powered by topological qubits. This breakthrough paves the way for million-qubit quantum computers that can help solve the world’s most urgent problems, from developing climate-resilient crops to discovering new medical treatments.?Congratulations?to everyone who helped reach this incredible milestone.

Here are a few other updates in the AI Agent Space from this past week. 25/ Braelyn Boynton released a new easy bash script for installing AgentStack from Agency https://lnkd.in/gM5WQedb 26/ “When building AI agents, expertise is far more important than software engineering skills.” - Wayne Hamadi??? https://lnkd.in/g6hYUKgP 27/ Nathaniel Whittemore from Superintelligent shares the current state and future predictions for AI agents ?? Tool Use? https://lnkd.in/gXHGwCS7 28/ Graphiti from Zep AI (YC W24) is an open-source Temporal Knowledge Graph framework that gives AI agents the ability to learn just like humans do Y Combinator https://lnkd.in/gHP5NhC7 29/ Qingyun Wu shared that Mark Sze is using AG2 communication agent suite to handle bug reports and discord community management https://lnkd.in/gbAmEfMe 30/ NEW 1-Click DeepSeek AI Agents are INSANE ?? Julian Goldie https://lnkd.in/gWWibzAA 31/ Manages multiple AI agents for complex conversations ?? Tom D?rr?? https://lnkd.in/gKgFQ5vd 32/ Nugget—an AI-native, no-code customer support platform ?? Deepinder Goyal https://lnkd.in/gF9dpbsX 33/ AutoAgent: LLM agent framework ?? Tom D?rr? https://lnkd.in/gHP4ZMrk 34/ “The final missing piece for AI Assistant advancement (including Agents) is memory.” - Homam Malkawi? https://lnkd.in/gx6cTwN9 35/ Sundar Pichai introduces AI co-scientist, a multi-agent AI system built with Gemini 2.0 https://lnkd.in/gFHJFhdr 36/ Jimmy Slagle built his first agent as a creative strategist who had never written a line of code in his life. https://lnkd.in/gCSyHspr 37/ Paul Klein IV recently completed a refactor of the swap code and tested Stagehand on both flows, with the same test run, but two completely different code paths, and it worked perfectly with no changes!? https://lnkd.in/g_FaH5Pb 38/ Arklex AI Agent Framework: perfect balance between autonomy and control! ?? Zhou (Jo) Yu https://lnkd.in/gpxsn_eP 39/ Twitter client for agents, no API key needed ?? Tom D?rr https://lnkd.in/gxPrvt82 40/ OmniParser V2 is a game changer for GUI Agents, it's catching everything ?? Victor Mustar? https://lnkd.in/gJDUnJNY 41/ Open-source framework designed to streamline the development and deployment of generative AI applications built on top of Meta'sLlama models. ?? Tom D?rr https://lnkd.in/gbnVyFma Here is everything else that happened in AI Agents this week: https://lnkd.in/g2ydfiUy Follow Adam Silverman (Hiring) and Agency for everything agent related.

New course to bring you up to state-of-the-art at using AI to help you code: Build Apps with Windsurf's AI Coding Agents, built in partnership with Windsurf and taught by Anshul Ramachandran! AI-assisted IDEs (Integrated Development Environments) make developers’ workflows faster, more efficient, and much more fun. Agentic tools like Windsurf are more than just code autocomplete—they are collaborative coding agents that help you break down complex applications, iterate efficiently, and generate code that spans multiple files. Although a lot of coding assistants share the same underlying large language models for planning and reasoning, a major point of distinction is how they handle tools, keep track of context, and stay aligned with your intent as a developer. For instance, if you make modifications to a class definition in your code and make the same modifications to other classes in the same directory, you might tell the AI agent "Do the same thing in similar places in this directory." Here, tracking your intent means understanding that “the same thing" refers to that recent edit you just made, which must be followed by appropriate search and tool-calling to implement the changes. In this course, you'll learn the inner workings of coding agents, their strengths and limitations, and how to use Windsurf to quickly build several applications. In detail, you'll: - Build a mental model of how agents work by combining human-action tracking, tool integration, and context awareness to carry out an agentic coding workflow. - Learn the challenges of code search and discovery and how a multi-step retrieval approach helps coding agents address them. - Use Windsurf to analyze and understand a large, old codebase and update it to the latest versions of the frameworks and packages it uses. - Build a Wikipedia data analysis app that retrieves, parses, and analyzes word frequencies. - Enhance the performance of your Wikipedia analysis app by adding caching, and through this, also learn how to course-correct when the AI agent produces unexpected results. - Learn tips and tricks such as keyboard shortcuts, autocomplete, and @ mentions to quickly call on agentic capabilities. - Use image/multimodal capabilities of the AI agent to increase your development velocity; you'll see an example of uploading a mockup with sketched-out UI features, and ask the agent to use that to build new functionality to an app. By the end of this course, you’ll understand agentic coding in-depth and know how to use it to make your development process much faster, more efficient, and enjoyable. Please sign up here! https://lnkd.in/gaw3vq_u

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Sora has arrived in the EU and the UK. Sora is now available to Plus, Pro, and Team users in the EU, the UK, Switzerland, Norway, Liechtenstein & Iceland. https://sora.com/

The Voice Stack is improving rapidly. Systems that interact with users via speaking and listening will drive many new applications. Over the past year, I’ve been working closely with DeepLearning.AI, AI Fund, and several collaborators on voice-based applications, and I will share best practices I’ve learned in this and future posts. Foundation models that are trained to directly input, and often also directly generate, audio have contributed to this growth, but they are only part of the story. OpenAI’s RealTime API makes it easy for developers to write prompts to develop systems that deliver voice-in, voice-out experiences. This is great for building quick-and-dirty prototypes, and it also works well for low-stakes conversations where making an occasional mistake is okay. I encourage you to try it! However, compared to text-based generation, it is still hard to control the output of voice-in voice-out models. In contrast to directly generating audio, when we use an LLM to generate text, we have many tools for building guardrails, and we can double-check the output before showing it to users. We can also use sophisticated agentic reasoning workflows to compute high-quality outputs. Before a customer-service agent shows a user the message, “Sure, I’m happy to issue a refund,” we can make sure that (i) issuing the refund is consistent with our business policy and (ii) we will call the API to issue the refund (and not just promise a refund without issuing it). In contrast, the tools to prevent a voice-in, voice-out model from making such mistakes are much less mature. In my experience, the reasoning capability of voice models also seems inferior to text-based models, and they give less sophisticated answers. (Perhaps this is because voice responses have to be more brief, leaving less room for chain-of-thought reasoning to get to a more thoughtful answer.) When building applications where I need a more control over the output, I use agentic workflows to reason at length about the user’s input. In voice applications, this means I end up using a pipeline that includes speech-to-text (STT) to transcribe the user’s words, then processes the text using one or more LLM calls, and finally returns an audio response to the user via TTS (text-to-speech). This, where the reasoning is done in text, allows for more accurate responses. However, this process introduces latency, and users of voice applications are very sensitive to latency. When DeepLearning.AI worked with RealAvatar (an AI Fund portfolio company led by Jeff Daniel) to build an avatar of me, we found that getting TTS to generate a voice that sounded like me was not very hard, but getting it to respond to questions using words similar to those I would choose was. Even after much tuning, it remains a work in progress. You can play with it at https://lnkd.in/gcZ66yGM [At length limit. Full text, including latency reduction technique: https://lnkd.in/gjzjiVwx ]

Randomized trial AI for legal work finds Reasoning models are a big deal for lawyers: Law students using o1-preview (the first available reasoner) had the quality of their work on most tasks increase (up to 28%) & time savings of 12-28%. There were a few hallucinations, but a RAG-based AI with access to legal material (Vincent) reduced those to human level. Combining both with be the future. Big changes to law appear to be coming: "Our findings demonstrate that reasoning models improve not only the clarity, organization, and professionalism of legal work but also the depth and rigor of legal analysis itself."