Build Fast with AI

Your LangGraph agent isn't looping. Your state is. If the state doesn't change, the graph has no reason to move forward. same node → same failure → infinite retry No state change = no escape condition.

@googledrive @gmail Every single @Google's product will going to get AI features, either its require or not.

With Ask Gemini in Drive, you can now ask complex questions across your files, calendar, and @Gmail all at once. Try: "What should I ask my tax advisor based on these files?" and get a detailed breakdown based on your actual data. ⏱️✨ goo.gle/3PqH9Aq

@caleb_friesen The one you ❤️

First and only Indian robot in Humanoid Atlas - can you spot it?

There are plenty of AI SDKs & frameworks to use but nobody's really knows about how they actually fit together - and that's where real AI systems get built. actually you don't have to pick one. you can layer them. SDKs → fast, direct model calls LangGraph → multi-step logic with memory CrewAI → multiple agents, different roles MCP → connects AI to your actual tools and data Here is the example of AI stack you can built 👇 what's your favorite AI SDK or framework? 💬

@davidzh @livekit That's great!

@BuildFastWithAI @livekit It works with most STT models

How can a voice agent tell when you’re actually interrupting it? VAD is too sensitive—laughs, “mm-hmm,” or a sneeze shouldn’t stop the agent. We trained an audio model for adaptive interruption handling so agents can distinguish real interruptions from noise.

@sir4K_zen @OpenAI Thanks! Overall both are excellent models.

@BuildFastWithAI @OpenAI Nice test run. Mini vs nano tradeoffs in one place are handy

We ran @OpenAI's gpt-5.4-mini and gpt-5.4-nano through the full builder stack. tool calling, streaming, structured output, multi-turn, LangChain integration. both are production-ready if you pick the right one for the job.

@antonosika Did we just get video generation in Lovable? 👀

Introducing Lovable for more general tasks. Lovable has always been for building apps. Today it also becomes your data scientist, your business analyst, your deck builder, and your marketing assistant. This is a big step toward what Lovable is becoming: a general-purpose co-founder that can do anything. See examples below.

@perplexity_ai Can it connect to Google Fit app?

Perplexity Computer now connects to your health apps, wearable devices, lab results, and medical records. Build personalized tools and applications with your health data, or track everything in your health dashboard.

@OfficialLoganK Guess what, they vibe coded all these, so we can vibe code.

Our AI Studio vibe coding roadmap for the new few weeks: - Design mode - Figma integration - Google Workspace integration - Better GitHub support - Planning mode - Immersive UI - Agents - Multiple chats per app - Simplified deploys - G1 support And more, should be fun : )

@GoogleAI @GoogleAIStudio @antigravity @Firebase someone's startup is now a feature of Google's product.

We’re launching a brand new, full-stack vibe coding experience in @GoogleAIStudio, made possible by integrations with the @Antigravity coding agent and @Firebase backends. This unlocks: — Full-stack multiplayer experiences: Create complex, multiplayer apps with fully-featured UIs and backends directly within AI Studio — Connection to real-world services: Build applications that connect to live data sources, databases, or payment processors and the Antigravity agent will securely store your API credentials for you — A smarter agent that works even when you don't: By maintaining a deeper understanding of your project structure and chat history, the agent can execute multi-step code edits from simpler prompts. It also remembers where you left off and completes your tasks while you’re away, so you can seamlessly resume your builds from anywhere — Configuration of database connections and authentication flows: Add Firebase integration to provision Cloud Firestore for databases and Firebase authentication for secure sign-in This demo displays what can be built in the new vibe coding experience in AI Studio. Geoseeker is a full-stack application that manages real-time multiplayer states, compass-based logic, and an external API integration with @GoogleMaps 🕹️

@MicrosoftAI @arena #5 on the leaderboard is solid, want to try how well it is in infographic generation and consistent style.

Meet MAI‑Image‑2. Built with creatives, for real creative work. Ranked #5 on @arena’s text‑to‑image leaderboard. Available now: msft.it/6014QUCBe

full cookbook ➡️ github.com/buildfastwitha…

Paying per OCR call when this runs on your laptop doesn't make sense anymore. GLM-OCR is a 0.9B model. runs locally via Ollama. handles math, LaTeX, tables, and 8+ languages. we put together a full cookbook - extraction, structured parsing, formula recognition. all with code.

built a small cookbook while testing, covers Responses API, Chat Completions, and the mini vs nano tradeoffs in one place. - github.com/buildfastwitha…

@ai_for_success The moment data is ready.

Data is everything. Big companies are now paying people for real, high quality, real world data. micro1 is doing exactly that. Everyday skills like cooking, organizing, and using tools are what robotics models actually need to improve.

OpenAI's new GPT-5.4 mini model is 2x faster ⚡ than GPT 5 mini but also 3x pricier. GPT 5.4 mini - $0.75 input / $4.50 output per M tokens GPT5 mini - $0.25 input / $2.00 output per M tokens 3x pricier in input. 2.5x pricier in output.

GPT-5.4 mini and nano just dropped. @OpenAI's two new small models, different jobs. mini: 2x faster than GPT-5 mini, built for coding, computer use, and subagents nano: smallest and cheapest in the 5.4 family, for lightweight tasks

Check out the app ai.studio/apps/7deb0607-…

Vibe coded a @monkeytype clone but for developers. built it entirely in @GoogleAIStudio. type real code to build muscle memory, (not helpful if you just prompt 🙃)