“Learn to build a local agentic RAG application for report generation using open-source LLMs! 🚀 Our friends at @AIMakerspace are hosting a live event next week (November 27) to teach you: 🔧 How to set up an “on-prem” LLM app stack 📊 LlamaIndex Workflows 🤖 Llama-Deploy 🏢 and
“full-stack webapp after… ~113 bolt chats ~1213 cursor chats… no code, pure prompting the raw truth is: AI won’t build your whole SAAS for you (u gotta deal w/ auth, emails, backend, security, deployment, client/server-side, etc) except… AI can walk u through all of
“Roster rollout! It’s time to meet our AI artists. First up is @NathanBoey, a trailblazer in the world of AI-driven comedy. His humour and heart carry through his work, and we just had to have him on our roster. Check out his work here:
Introducing self-evolving models – Writer
“Building products takes too long. We started Lovable to fix this. Today, we’re officially launching the world’s first AI Full Stack Engineer Lovable reliably replicates the capabilities of a full stack engineer and handles everything from design to database operations by
ESPN testing AI avatar to provide analysis on ‘SEC Nation’ college football broadcast | Mashable
“Agentic RAG w/ sources over 10K policy documents built using @expo streaming and AI SDK by @vercel. Had to roll our own `useChat` hook to make it cook. Rolled out to one of Europe’s biggest healthcare companies 🚀
“Tired of repetitive tasks? Multi-agent systems can help with that! In this blog post, @lorenzejayTech shows you how to build a Multi-Agent RAG system with @crewaiinc, Weaviate, Groq, and ExaTool. Automate everything from • code interpretation and data retrieval • to
“YC F24’s @Abundant_Labs provides an on-demand human workforce for AI Agent edge cases. When Agents need human support, Abundant’s network of experts steps in to assist, while generating training data.
“ShowAndTell (YC F24) builds AI agents for dental operations. Their agents partner with treatment coordinators to deliver scalable, empathetic, and personalized interactions. Practices close more cases, and patients get the care they need.
“1/ WORLD FIRST! Witness the future: A Based AI Agent Creating an LLC in Delaware Today, we show how a Based AI agent autonomously decides to create an LLC in Delaware, fully onchain, for its own needs. (Using @CoinbaseDev, @Replit, @otoco_io, and @OpenAI)
“I think this partnership between @perplexity_ai and @stripe to enable inline purchases directly from search results is very neat. (And, as a reminder, we launched an agent toolkit last week — check it out if you want to enable similar experiences:
“Unreal I just built an app with 1 prompt The most powerful AI tool I’ve ever used just dropped It’s called Windsurf and it’s an AI Agent that builds apps for you in minutes Here’s why I think EVERYONE should be trying it out (trust me, you want to bookmark this one)
“Introducing the Studio, our platform for developers to run automations at scale, and Runner H, the most advanced agent to date — designed to navigate web interfaces through pixel-level interpretation and semantic understanding. You can now turn your instructions into action with
“Today(), @stripe is launching a SDK built for AI agents: – LLMs can call payment, billing, issuing, etc APIs – Integrates with @vercel, @LangChainAI, @crewAIInc – Use any model via functions (w/ per token billing) Excited what you, and your bots, build:
“The LangSmith homepage has a new look! It now features three pillars of LLM development: Observability, Evaluation, and Prompt Engineering. 🔍 Observability: Debug issues in tracing projects and monitor key metrics in dashboards 📊 Evaluation: Curate datasets, run experiments,
“This might be the best agent I’ve seen yet. After raising $220M, @hcompany_ai just introduced an agent that can execute any task from a prompt. Their “Runner H” can basically turn instructions into action with human-like precision. Features: ▸ Navigates web interfaces with
“Unlocking Voice Interaction with LangGraph Agents 🗣️👂 Most AI agents live in a text-only world, limited to chat interfaces. But what if they could hear and speak? In this video, we’ll show you how to transform any LangGraph agent into a voice-enabled assistant. Using task
“AI agent market is insane, havent seen anything like it. Hundred of companies competing, building identical companies with really low barriers to entry” / X
“Over the past extremely few number of weeks, I’ve had the pleasure to work with the @perplexity_ai team as they built Shopping using @stripe — they’re building with stunning speed, ambition, and user focus. Relatedly, learn more about our AI agent SDK 🤖:
“built an inbound AI SDR with @ottogrid_ai now when someone signs up, our agents instantly researches, scores, and creates a personalized message to send them (and pings me on slack) saves a few hours per day + now we know exactly who’s using our product
“Introducing Agent Blocks. AI agents can now work together to solve more complex problems. – Start with simple agents – Combine them into sophisticated solutions – Build on top of other’s work Available now in the AutoGPT Platform ✅ Learn more ➡️
ElevenLabs now offers ability to build conversational AI agents | TechCrunch
“LLM-based Agents for Automated Bug Fixing Analyzes 7 leading LLM-based bug fixing systems on the SWE-bench Lite benchmark, finding MarsCode Agent (developed by ByteDance) achieved the highest success rate at 39.33%. Reveals that for error localization line-level fault
“The inaugural AI Agent Congress. @jowyang from @BlitzVentures assembled leaders in AI agents from all across the 🌎 It was incredible to hear everyone’s perspectives on where they see the industry moving.
“📢Thrilled to introduce the #VirtualLab: a team of AI scientist agents (AI chemist, AI reviewer…). Virtual Lab is led by an AI professor w/ feedback from human scientist. The Lab created new nanobodies that we experimentally validated to bind to recent #covid variants🚀🧵
“Someone is using a team of 10 AI agents to write a fully autonomous book. They each have a different role – setting the narrative, maintaining consistency, researching plot points… You can follow their progress through GitHub commits and watch them work in real-time 🤯
“.@Rankai_ai is replacing marketing agencies with AI agents. Their first agent automates the entire SEO process and makes it 20x more affordable.
“transcript of a talk i gave last week, on turning our ai coding agent into a designer:
“v0 but for building agents with AgentStack should i release it?
“Generating Science From AI-Powered Automated Falsification This paper introduces BABY-AIGS, a multi-agent system for automated scientific discovery that emphasizes falsification through automated ablation studies. BABY-AIGS uses a Domain-Specific Language (DSL) to ensure
“OpenRecovery is redefining addiction recovery with their AI assistant that provides personalized, 24/7 support via text and voice. In a field where trust and adaptability are crucial, they’ve adopted: • LangGraph Platform for scalable, seamless agent interactions tailored to
“We’re thrilled to announce our $30M seed round to accelerate Wordware’s mission of empowering anyone to build in AI with plain English. 💫 With Wordware, anyone—from seasoned engineers to non-technical domain experts—can build AI agents that streamline processes, enhance
“🤖 Stanford researchers created AI agents that can replicate participants’ responses on a survey 85% as accurately as participants replicate their own answers two weeks later. Could allow researchers to test how policies or social changes might affect different communities
Amazon
“Inside scoop on why Amazon’s AI-revamp to voice assistant Alexa is taking so long (hint: lots of problems)
Anthropic
“We’ve added Google Docs integration to claude dot ai. Simply paste a link or select from your recent documents to add them to your chats and projects. Now available for Claude Pro, Teams, and Enterprise users.
“YC F24’s @scrapybara is building instant, secure virtual desktop environments for AI agents. Deploy instances in seconds, and host Claude Computer Use in production via API.
[2411.10323] The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
“This write-up of Claude with Computer Use matches my experience- as a general purpose agent that can do anything in a computer, it is surprisingly good. However it still has enough flaws that it is a sign of the future than a full agent now. But it also shows the future is soon.
“AgentOps 0.3.18 (The Computer Use Update) is out!! 🖥️ Upgraded support for Claude computer use 🪝 Pre-commit hooks for better static analysis checks 💬 Updated docs for @AnthropicAI support Huge shoutout to the OSS contributors @prattyboy @teocns @romanian_raiden @cmd_labs” / X
“Claude getting better at things that actually matter while other labs compete over markdown output
LangChain
“🔗 Agent Protocol: interoperability for language agents LangGraph is a multi-agent framework. It can communicate with agents defined in other frameworks and languages. Today we are releasing: 📱 A standard interface for agent communication (Agent Protocol):
Microsoft Copilot News
Introducing Microsoft Copilot actions, new agents, and tools to empower IT| Microsoft 365 Blog
Microsoft’s new Copilot Actions use AI to automate repetitive tasks – The Verge
@Microsoft AI CEO Mustafa Suleyman x Times Techies | An exclusive interaction | #copilot – YouTube
Software is a team sport: Building the future of software development together – The GitHub Blog
OpenAI
“Crazy interesting paper in many ways: 1) Voice-enabled GPT-4o conducted 2 hour interviews of 1,052 people 2) GPT-4o agents were given the transcripts & prompted to simulate the people 3) The agents were given surveys & tasks. They achieved 85% accuracy in simulating interviewees
ChatGPT can now read some of your Mac’s desktop apps | TechCrunch
“ChatGPT can now access some desktop apps OpenAI released desktop app integration for ChatGPT on macOS, allowing Plus and Team users to connect with VS Code, Xcode and Terminal apps Enterprise and Education users will get access in the coming weeks
Salesforce
Salesforce launches Agentforce Testing Center to put agents through paces | VentureBeat
Siri
Apple Readies More Conversational LLM Siri in Bid to Rival OpenAI’s ChatGPT – Bloomberghttps://www.bloomberg.com/news/articles/2024-11-21/apple-readies-more-conversational-llm-siri-in-bid-to-rival-openai-s-chatgpt
Leave a Reply