Rohan Doshi

🚀 We just launched Gemini 3 Pro — the strongest multimodal understanding model ever built. I lead product for Gemini’s multimodal vision capabilities, and I want to share more about the massive wins we are seeing across document, screen, spatial, and video understanding. 🧵

RT @swyx: filesystem + code sandbox combo eats another modality. remember when o3 destroyed at geoguessr? gemini agentic vision will find…

An awesome deep dive on how to leverage Gemini 3 Agentic Vision today

Back at Harvard Business School last week speaking on frontier AI + agents 🤖 As a ’23 alum, it was energizing to be back - this time teaching from the other side of the classroom My AI agent workshop was completely packed, with 100+ students - signal on how much Harvard is leaning into AI The students’ agency, raw IQ, and curiosity left me wildly optimistic about the next wave of AI builders 🚀 Grateful to Profs. Jeffrey Bussgang & Allison Mnookin and the Launching Tech Ventures team for the invite 🙏🏼

@hololux Very cool!

what are y'all building with Gemini Agentic Vision??

@danielpearson Let’s chat! DM me!

@RohanLikesAI Agentic vision for video soon?

@RejaullahmdMd Select Gemini 3 Flash as the model, turn on the code execution model, and upload an image!

@RohanLikesAI How to use it in AI studio

🚀 Excited to officially launch 👁Agentic Vision via Gemini 3 Flash. Gemini can run code execution on image uploads to zoom, analyze, and annotate: 🔍 Zoom: 5-10% quality win across vision benchmarks 🧮 Analyze: do image math with code (e.g. calculate the tip for a receipt) ✏️ Annotate: Draw arrows or bounding boxes to answer questions Try via the Gemini API (AI Studio / Vertex) or via the Gemini App (rolling out to Thinking mode today). Learn more→ goo.gle/4bsKdFv Demo: goo.gle/3Z05KxK cc: @IoanaBica95 @anastasija56572 @jalayrac @bcaine @eisenjulian @weichengkuo @phillip_lippe @xf1280 @tulseedoshi @BiboXu @OfficialLoganK

@Jake_Joseph @AdMachineAI Very cool - would love to chat and see if we can help

@RohanLikesAI Thinking about using it as a fidelity/quality layer check for @AdMachineAI on our outputs to check vs. input product. If it doesn’t meet a threshold it automatically regenerates.

@1littlecoder @shresbm both! AIS docs: #images" target="_blank" rel="nofollow noopener">ai.google.dev/gemini-api/doc…

@shresbm @RohanLikesAI is it available inside ai studio or only through api?

Agentic Vision in Gemini 3 Flash converts image understanding into an active, agentic investigation. By combining visual reasoning with code execution, the model formulates plans to zoom in, inspect and manipulate images step-by-step, grounding answers in visual evidence. Below see an example of image

@marcosmarf27 @OfficialLoganK our team should be able to help debug things: feel free to respond to my DM or email me at rohandoshi@google.com.

@marcosmarf27 @OfficialLoganK can you help me better understand your entire pipeline better? what are "vision resources". Are you using another upstream system to do OCR? And are you feeding the OCR text and the PDF images into Gemini from there?

@deedydas @deedydas 👋 glad you’re a fan of the launch (I’m the Gemini multimodal vision PM) - feel free to DM if you have any feedback for the team on doc understanding

Gemini 3 Flash is insane at OCR. It parses this extremely hard to read handwritten letter by Richard Feynman perfectly. It can do ~300 of these for $1. What's crazy is Feynman addresses General Donald J. Kutyna as "Katyna" which Gemini gets. There is no "Meeting Katyna", the first part of the letter, in all of Google search!

@matidotlol @googleaidevs @OfficialLoganK cc: @jalayrac @bcaine

@matidotlol @googleaidevs @OfficialLoganK Gemini Vision PM here! Let's chat (I'll DM you). can you share some queries+PDF examples. I'll have our team debug what's going on

@googleaidevs @OfficialLoganK where is the best place to report problems with Gemini API? for whatever reason, when using structured outputs, Gemini 3 Flash just ignores the vast majority of the PDF input. it works fine without structured outputs

@marcosmarf27 @OfficialLoganK Hey Marcos! I’m the Gemini Vision PM working on doc understanding. Would love to learn more and see if we can help. Will DM you.

⚡️ Gemini 3 Flash just got a major new capability: code execution for images. Gemini can decide when to write code to zoom, count, and annotate—unlocking the next phase of Agentic Vision. 🤖 Wildly fun to PM this 0→1. Stay tuned to hear more 👀

@GeminiApp @MarioLucic_ looks like the sports video work paid off 😂

With Gemini 3 Flash, you can upload a short video to get a quick, easy-to-read analysis. Try Gemini 3 Flash in the app today.