# Vertex AI Projects at AI Tinkerers > Canonical HTML: https://aitinkerers.org/technologies/vertex-ai > Markdown URL: https://aitinkerers.org/technologies/vertex-ai.md > Technology record last updated: 2026-02-23T20:57:58Z > Generated: 2026-09-23T00:37:45Z Vertex AI is the fully-managed, unified platform for building, deploying, and scaling Generative AI and custom ML models across Google Cloud. Vertex AI unifies the entire machine learning lifecycle: data engineering, data science, and MLOps. The platform provides a single surface for all workloads, accelerating development with tools like Vertex AI Workbench (Jupyter notebooks) and native BigQuery integration. For Generative AI, you get immediate access to Google’s latest models, including Gemini 3, via Vertex AI Studio and Model Garden, featuring over 200 foundation models. MLOps is streamlined with Vertex AI Pipelines for workflow orchestration, Model Registry for version control, Feature Store for serving features, and robust Model Monitoring to detect training-serving skew and drift. - Official technology site: https://cloud.google.com/vertex-ai - Public AI Tinkerers demos and talks: 31 - Result page: 1 of 2 ## Recent Public Talks and Demos ### [Claude Code e Google Vertex para Experimentos de Machine Learning](https://curitiba.aitinkerers.org/talks/rsvp_OoWoCfnBRoo) É uma apresentação sobre como é possível utilizar claude code em seu computador para realizar experimentos de machine learning. A apresentação mostra o fluxo de trabalho para realizar experimentos a partir de uma idéia. Também se demonstra a possibilidade de utilizar Google Vertex AI para trabalhar com a Cloud caso seu computador principal não seja suficiente para experimentos que necessitam de mais recursos. - Event context: AI Tinkerers Curitiba: Evento Inaugural — 2026-06-10 — Curitiba - Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_OoWoCfnBRoo ### [Agentic video editing pipeline](https://montreal.aitinkerers.org/talks/rsvp_5bqTjWicF8s) After interviewing 50+ video editors, head of marketing, film directors, we found the boring part of the professional video editing job that can be automated. I will demo the main video ingestion workflow: transcode to 480p using ffmpeg, upload that video to GCS, takes some frames and use it for classification, ask gemini to look at the video for video understanding, piping the audio to assemblyai for the transcript, use ffmpeg to segment the video, use gemini embedding on each segment so it is searchable. - Event context: AI Tinkerers Montreal - May Demo Meetup @ Ubisoft — 2026-05-26 — Montreal - Public talk page: https://montreal.aitinkerers.org/talks/rsvp_5bqTjWicF8s ### [Streaming Dynamic Selection for Contextual Engagement on Social Media](https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_vNFOGGTQjBU) How my product EngageKit.io dynamically selects persona to engage contextually with social media content. - Event context: AI Tinkerers Ho Chi Minh City: From Prompt to Agent — 2026-03-07 — Ho Chi Minh City - Public talk page: https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_vNFOGGTQjBU ### [MCP Apps: Shipping Interactive UIs with a Translation Server](https://cologne.aitinkerers.org/talks/rsvp_WllqXAqGhlM) Four live demos adding interactive Views to a production MCP server using ext-apps. Demo 1: side-by-side translation diff with glossary term highlighting and model quality comparison. Demo 2: D3 force-directed network graph exploring 10k+ glossary terms across 30 languages. Demo 3: inline glossary marketplace -- browse, preview, one-click install. Demo 4: drop a product photo, Gemini OCR extracts text, DeepL translates it, Imagen 3 regenerates the image with culturally adapted people and scenery. All rendering inline in the chat, all calling back to the server from the iframe. - Event context: AI Tinkerers Cologne 3: Demos, Code, and Architecture — 2026-03-05 — Cologne - Public talk page: https://cologne.aitinkerers.org/talks/rsvp_WllqXAqGhlM ### [Build an LLM and RAG-based Chat Application with AlloyDB and Vertex AI](https://pereira.aitinkerers.org/talks/rsvp_JG2zcfhm9MI) In this session, we will explore how to overcome the knowledge limitations of language models using Recall Augmented Generation (RAG). We will analyze a robust architecture on Google Cloud that uses AlloyDB for the storage and semantic search of vector embeddings, allowing the model to access private information in real time. We will see how the MCP Toolbox acts as secure middleware to manage database operations and how Gemini Pro in Vertex AI synthesizes this information to deliver accurate, multimodal, and context-rich responses. - Event context: Cambio de paradigma AITINKERERS PEREIRA 2026 — 2026-02-26 — Pereira - Public talk page: https://pereira.aitinkerers.org/talks/rsvp_JG2zcfhm9MI ### [Building an agentic text creation and editing harness](https://vienna.aitinkerers.org/talks/rsvp_TRbR4hcClQE) Cursor but for grant applications: It's our mission at StartMatch to make writing grant applications as easy as possible. While generic AI tools are quite capable at generating text, it still takes significant time and expertise to produce texts that meet the strict requirements of grant applications. That's why we built an agentic text creation and editing harness that is able to self- review and correct. Plus, we made the whole thing collaborative and super easy to use. - Event context: AI Tinkerers Vienna: 2026 — 2026-02-19 — Vienna - Public talk page: https://vienna.aitinkerers.org/talks/rsvp_TRbR4hcClQE ### [The AI-First Development Workflow](https://st-louis.aitinkerers.org/talks/rsvp_VHAgcAJsbGY) This presentation details a paradigm shift in software engineering where AI is the primary builder and the human is the Principal Orchestrator. The Core: It replaces traditional human team roles with specialized, adversarial AI agents. The Rigor: It implements the Planning Gauntlet (Architect/Critique/Revise) and the Hardening Cycle (Review/Fix/Test) to ensure that solo output meets industrial production standards. The Impact: It enables a single engineer to operate as a full-force squad, delivering mission-critical software with zero-drift and zero-bug tolerance. This presentation describes the workflow I've developed building production software using AI at my day job (IntelePeer) as well as in my side projects (IgnitionAI) - Event context: AI Tinkerers – St. Louis Meetup: February 4, 2026 — 2026-02-04 — St. Louis - Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_VHAgcAJsbGY ### [AI Job Agent: Automating Job Search with GitHub Actions, Vertex AI, and Strategic Laziness](https://atlanta.aitinkerers.org/talks/rsvp_MAVH3VnIET0) I built an AI agent that autonomously searches LinkedIn, Indeed, and Greenhouse every Tuesday and Thursday, analyzes 40+ jobs using Vertex AI, and emails me a prioritized list with match scores and custom talking points—all while I sleep. The entire system runs serverless on GitHub Actions (completely free) and took two weekends to build. - Event context: AI Tinkerers Atlanta: Code-First Demos & Technical Deep Dives | January 27, 2026 — 2026-01-27 — Atlanta - Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_MAVH3VnIET0 ### [The Secret to Stunning UI: How AI Helped Me Design and Ship InkyCards in 7 Days](https://cologne.aitinkerers.org/talks/rsvp_EmnVHJCgoK0) In just one week, I took InkyCard, a conversational language learning app from an idea in my head to a production-ready product. This session isn’t just about generating code; it’s about using AI to solve the "Developer Design Gap" and build a brand with a soul. I will demo the InkyCards workflow, focusing on: The Design Extraction Hack: How to feed UI inspiration (from sites like Dribbble) into LLMs to generate custom design systems, ensuring your app doesn’t look "AI-generated." Building the "Soul": Using Gemini Nano and Higgsfield to create a unique app mascot and custom iconography, overcoming creative blocks and building an emotional connection with users. Production Speed-running: A look at the "Plan-First" prompting strategy and context management that allowed me to build complex features—like real-time AI conversations (Firebase Vertex AI) and "Tap-to-Learn" flashcard generation—without losing code quality. Technical Deep-Dive: State Management & AI: How to use Claude and AntiGravity to scaffold architecture that stays clean as the project grows. The Fresh Convo Rule: My framework for managing LLM context to prevent "code rot" and quality degradation. - Event context: AI Tinkerers Cologne #2: Let's Build. — 2026-01-21 — Cologne - Public talk page: https://cologne.aitinkerers.org/talks/rsvp_EmnVHJCgoK0 ### [NextSpot: Travel-proof recommendations powered by Google Maps reviews understanding (not keyword search)](https://atlanta.aitinkerers.org/talks/rsvp_Lr0MUd5Hy_4) NextSpot is a live web demo that recommends similar places in a new city by understanding what your favorite spot is known for from public signals (reviews + description). In the demo, I’ll enter a favorite place and a target location (e.g., Dallas/Houston). NextSpot extracts the place’s “signature attributes,” generates a compact intent query, searches locally within a strict radius, and returns recommendations constrained to the same business category (e.g., cafe → cafe, salon → salon). The result is a recommender that works across many categories without hardcoding for any single domain. In 5 minutes, I’ll show the working web app and a short walkthrough of the backend internals: 1) pulling place metadata + top reviews, 2) extracting “signature attributes” into structured fields (not freeform text) 3) turning those fields into a constrained search query, 4) retrieving candidates from Places within a hard geo-radius, then 5) ranking results with embeddings + a lightweight re-ranker - Event context: Co-Co-Code & Cocoa: The AI Tinkerers Atlanta Holiday Meetup — 2025-12-16 — Atlanta - Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_Lr0MUd5Hy_4 ### [Searching through my LinkedIn Portability Data](https://paris.aitinkerers.org/talks/rsvp_EnIzfZNz5wI) I'm (trying to) build a knowledge database with neo4j referencing the LinkedIn posts I reacted to. - Event context: Turn Your Knowledge into an API for LLMs - Meetup — 2025-12-09 — Paris - Public talk page: https://paris.aitinkerers.org/talks/rsvp_EnIzfZNz5wI ### [SecretAIry](https://san-diego.aitinkerers.org/talks/rsvp_ryH19JldtzI) I hate phone calls, so I built an AI with a quirky personality to handle them for me. "SecretAIry" is my personal AI gatekeeper that not only screens calls but also remembers callers and develops a unique relationship with them over time. When a call comes in, my AI secretary chats with the caller to figure out who they are and what they want. Based on past interactions and the caller's vibe, it decides whether to put them through, take a message, or refuse their call. It's a fun, slightly chaotic solution to my phone-call phobia. - Event context: AI Tinkerers x Google AI Meetup, San Diego — 2025-11-21 — San Diego - Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_ryH19JldtzI ### [MonoMorph: An Agentic tool for refactoring monoliths into microservices](https://montreal.aitinkerers.org/talks/rsvp_l2DEga8TIMc) I'll be doing a live demo of MonoMorph, an agentic system built on LangGraph that automatically refactors monoliths into microservices. The talk will focus on the agent workflows we designed and the key lessons we learned during its development. For example, to guarantee the correctness of the refactored code, we needed to heavily ground our code-generation agent with structured outputs and template driven prompts to ensure it fits the target design. However, our bug-fixing agent required a much more flexible, multi-turn method to autonomously debug unexpected compilation errors in a Docker-based loop. During the presentation, we’ll look into the design of the workflows for each of the agents, examples of the templates we used and the implementations of the tools that are critical to the success of the agents. We’ll run a demo of the application which we will keep checking on as we discuss the rest. - Event context: AI Tinkerers Montreal: Demo Night — November 20, 2025 — 2025-11-20 — Montreal - Public talk page: https://montreal.aitinkerers.org/talks/rsvp_l2DEga8TIMc ### [Creating a DSGVO conform LLM Wrapper which lets people enty PPI data and has access to Emails , also a RAG System](https://cologne.aitinkerers.org/talks/rsvp_8TqWeuaJ0Ag) Presenting the code and architecture of my little hobby. Mainly ill focus on the backend , but can show the frontend as well. - Event context: AI Tinkerers Cologne – Inaugural Meetup — 2025-11-05 — Cologne - Public talk page: https://cologne.aitinkerers.org/talks/rsvp_8TqWeuaJ0Ag ### ['I know Kung Fu' - Downloading Brazilian JiuJitsu and Human-in-the-Loop](https://liverpool.aitinkerers.org/talks/rsvp_JeuzLhg7i-0) You remember that scene in the Matrix where Neo 'downloads' Kung Fu? I wondered if and how I could tune a model to 'learn' Brazilian Jiujitsu (BJJ) starting with raw data from videos of BJJ competitions. I'll be focusing on using HITL to provide labels for training data and, perhaps, if its even approaching functionality, provide feedback on the model's predictions. I have visions/ambitions for a very niche AI leaderboard for scoring, refereeing, and even coaching, BJJ.. but we'll see :) Expect (probably) something gnarly to construct a dataset because there isn't anything out there already that I can find, Google's Vertex AI, Prolific to power as the HITL steps/layer. - Event context: AI Tinkerers Liverpool HITL Meetup at FACT Lab — 2025-10-28 — Liverpool - Public talk page: https://liverpool.aitinkerers.org/talks/rsvp_JeuzLhg7i-0 ### [Agentic Wallets and AI-Driven Patronage with Stablecoins](https://austin.aitinkerers.org/talks/rsvp_wIP36d0REp8) I’ll walk through the design and implementation of ClamBot, an agentic wallet system that distributes patronage automatically based on AI-curated recommendations. The core idea: users deposit tokens, and autonomous agents allocate funds across creators, categories, and up-and-coming voices. I’ll demo how recommendation logic, fund distribution, and programmable vaults work, and how we’re extending this into “taste as currency.” - Event context: AI Tinkerers Austin AI Demo Night w/ Google & Comet — 2025-10-09 — Austin - Public talk page: https://austin.aitinkerers.org/talks/rsvp_wIP36d0REp8 ### [GCP Tools Demo by Google's Strategic Missions & Partnerships - Startups & AI Lead](https://seattle.aitinkerers.org/talks/rsvp_7QHXY1Ve_0Q) AI Studio, Vertex AI, and a Generative Media AI application Google is building for the next Startup School (sneak peek) - Event context: AI Tinkerers Seattle September Meetup — September 30, 2025 — 2025-10-01 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_7QHXY1Ve_0Q ### [Is Grok Code Fast 1 underrated?](https://boston.aitinkerers.org/talks/rsvp_hg_qwbyrTGg) On Aug 28 Grok Code Fast 1 got released. I spent the first week of September writing a full backend for an AI chat app with it. That includes the REST API, database, auth handler, and backend services. According to cursor i have over 40k lines with this model. In my talk I will go over how it is different, where it absolutely tanked, and what I like about how it works. - Event context: AI Tinkerers Boston Meetup at Publicis Sapient — 2025-09-29 — Boston - Public talk page: https://boston.aitinkerers.org/talks/rsvp_hg_qwbyrTGg ### [AI/ML for SMBs](https://atlanta.aitinkerers.org/talks/rsvp_ODG8dpI77oo) How to leverage AI/ML to drive automate routine tasks like data entry and scheduling, generate content for marketing, and enhance customer service through chatbots and personalized recommendations. - Event context: AI Tinkerers Atlanta Meetup – August 28, 2025 — 2025-08-28 — Atlanta - Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_ODG8dpI77oo ### [AI-Powered Accident Detection System Using Java and Google Cloud Vertex AI](https://atlanta.aitinkerers.org/talks/rsvp_N911DfMNl18) I’ll walk you through how I built an AI-powered accident detection system — entirely using Java for preprocessing, cloud integration, and prediction calls — combined with Google Cloud Vertex AI for training and deploying a custom object detection model. - Event context: AI Tinkerers Atlanta Meetup – August 28, 2025 — 2025-08-28 — Atlanta - Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_N911DfMNl18 ### [Building 'mission control' for software engineering agents](https://london.aitinkerers.org/talks/rsvp_ufx_6-dsLjY) Live demo showing how Ona orchestrates software engineering agents working in parallel on engineering tasks. I'll walk through the technical architecture of isolated and ephemeral agent/human environments - show how agents securely execute code changes and demonstrate the integration with editors, source control, secrets managers etc. - Event context: AI Tinkerers London Meetup - 28th August 2025 — 2025-08-28 — London - Public talk page: https://london.aitinkerers.org/talks/rsvp_ufx_6-dsLjY ### [Navigating Classrooms with AI: The VidyaNav-ai Sprint Story](https://munich.aitinkerers.org/talks/rsvp_YYFSk84kxpI) In many under-resourced schools across Europe and India, one teacher must simultaneously teach multiple grade levels, each with its own syllabus, pace, and learning needs. In this talk, I will present VidyaNav-ai, an AI-powered assistant designed to support such teachers by generating differentiated worksheets in multiple languages from textbook images, creating visual aids for students from simple prompts, and answering various student questions by giving simple analogies using a retrieval-augmented generation (RAG) approach. I will present about the technologies and LLM models I have used, and why I used them. I will talk about the models like Gemini-pro and Gemini-flash. I will show how I built the frontend using the google firebase studio and share the hacks that I learnt. - Event context: AI Tinkerers Munich - July 25 — 2025-07-25 — Munich - Public talk page: https://munich.aitinkerers.org/talks/rsvp_YYFSk84kxpI ### [Building AI Agents with Google Cloud AI](https://seattle.aitinkerers.org/talks/rsvp_7k1aSrWuSY4) Explore Google’s latest generative AI media capabilities with Imagen and Veo on Vertex AI. You’ll learn about model capabilities and how these APIs can be integrated into agentic workflows on Google Cloud. Learn about core agent components and essential prompting techniques to help you effectively harness these powerful models in your applications. - Event context: Building AI Agents with Google Cloud AI — 2025-07-25 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_7k1aSrWuSY4 ### [Cantonese with GenAI Images](https://hong-kong.aitinkerers.org/talks/rsvp_nh1big94XSo) I will be talking about the technical difficulties of using Google's vertex ai to generate images using a prompt with code written in NodeJS. - Event context: AI Tinkerers - Hong Kong Meetup (June) - Cyberport AI Ecosystem and AI Supercomputing Service Sharing — 2025-06-27 — Hong Kong - Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_nh1big94XSo ## Related Technologies - [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos - [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos - [Cloud Run](https://aitinkerers.org/technologies/cloud-run) ([Markdown](https://aitinkerers.org/technologies/cloud-run.md)) — 12 public demos - [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 446 public demos - [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos - [Imagen](https://aitinkerers.org/technologies/imagen) ([Markdown](https://aitinkerers.org/technologies/imagen.md)) — 10 public demos - [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos - [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos - [Amazon Bedrock](https://aitinkerers.org/technologies/amazon-bedrock) ([Markdown](https://aitinkerers.org/technologies/amazon-bedrock.md)) — 20 public demos - [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos - [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 216 public demos - [Cloud Build](https://aitinkerers.org/technologies/cloud-build) ([Markdown](https://aitinkerers.org/technologies/cloud-build.md)) — 2 public demos - [Cloud SQL](https://aitinkerers.org/technologies/cloud-sql) ([Markdown](https://aitinkerers.org/technologies/cloud-sql.md)) — 3 public demos - [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos - [Firebase](https://aitinkerers.org/technologies/firebase) ([Markdown](https://aitinkerers.org/technologies/firebase.md)) — 23 public demos - [Gemini Pro](https://aitinkerers.org/technologies/gemini-pro) ([Markdown](https://aitinkerers.org/technologies/gemini-pro.md)) — 3 public demos - [Google Cloud](https://aitinkerers.org/technologies/google-cloud) ([Markdown](https://aitinkerers.org/technologies/google-cloud.md)) — 8 public demos - [Google Cloud Platform](https://aitinkerers.org/technologies/google-cloud-platform) ([Markdown](https://aitinkerers.org/technologies/google-cloud-platform.md)) — 25 public demos ## More Results - Next: https://aitinkerers.org/technologies/vertex-ai.md?page=2