# Express Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/express
> Markdown URL: https://aitinkerers.org/technologies/express.md
> Technology record last updated: 2026-02-25T05:49:50Z
> Generated: 2026-09-21T11:43:16Z

Express.js is the fast, unopinionated, and de facto standard web application framework for Node.js (JavaScript backend).

Express.js is your core for building scalable web applications and robust APIs on Node.js. It’s a minimal, flexible framework: it handles routing, HTTP utilities, and the request/response cycle efficiently. We leverage its massive middleware ecosystem for added functionality like cookie parsing or authentication (e.g., Passport.js). As the 'E' in the popular MEAN, MERN, and MEVN stacks, Express provides the proven, high-performance backend layer for modern JavaScript development.

- Official technology site: https://expressjs.com
- Public AI Tinkerers demos and talks: 18
- Result page: 1 of 1

## Recent Public Talks and Demos

### [I Let an AI Avatar Introduce Me On Stage.](https://tokyo.aitinkerers.org/talks/rsvp_EAeb_RAMdGM)

I built a browser-based stage controller that made a 3D AI avatar walk on and deliver the opening introduction at the Perxona Tokyo Hackathon on August 8 — instead of introducing myself, I let the avatar do it. It performs a two-minute bilingual monologue with eighteen hand-placed gestures and no repeats, then swaps its face, voice and room live on keyboard cues, and finally lip-syncs to a voice clip my own laptop synthesised offline with no cloud call. It is a single Express server and one vanilla-JS page — no build step, no framework. Live I'll show: the working system, driven by number keys the way it ran on the day. Then the cue script — the gesture tokens and how they resolve at runtime against whichever character is on stage.

- Event context: AI Tinkerers Tokyo - September 1st Meetup — 2026-09-01 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_EAeb_RAMdGM

### [Don’t Just Build an App: Build a Playground - Designing flexible, high-growth ecosystems that scale seamlessly.](https://orange-county.aitinkerers.org/talks/rsvp_FR1uOvCMPCI)

Oddjob lets you spin up teams of AI agents that plan and execute multi-step work as missions, cycles, and pipelines — extracting knowledge, running research, generating documents and datasets, and completing tasks end to end. It can build and deploy working software and mini-apps on demand through App Forge, stand up org and team structures through Org Forge, and turn a document template into a live form agent that captures a structured schema automatically. It grounds every agent in your own data with retrieval-augmented generation, a knowledge graph, and reusable templates, and routes work through configurable LLM providers with automatic failover to a local model when a provider is unavailable.

- Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_FR1uOvCMPCI

### [Being a dungeon master for agents](https://columbus.aitinkerers.org/talks/rsvp_bciO_4-2f2c)

I built a system where you can DM a contiguous story for agents, describing their light attributes and DM for them entirely via voice. Built with Svelte and node/express

- Event context: AI Tinkerers - Columbus July Meetup — 2026-07-06 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_bciO_4-2f2c

### [Fly, Snap, Know: Wiring Drone Data into a Predictive, Prescriptive Security Platform That Responds Before You Do](https://johannesburg.aitinkerers.org/talks/rsvp_KeOgSIP594M)

DroneQRF is a drone operations platform built around one principle: the pilot's only job is to fly. Everything else is handled in the background. The Drone Pilots capture snapshots mid-flight; the platform does the rest — AI analysis of imagery, real-time parsing of flight telemetry and plans to predict potential issues and prescribe corrective actions, ingestion of deployment and fleet health monitoring, and a live dashboard giving full situational awareness across all active drones and sites. Nothing interrupts the mission. Intelligence surfaces automatically after combining these data points, before it becomes a problem.

- Event context: AI Tinkerers Johannesburg: Inaugural Meetup — 2026-03-31 — Johannesburg
- Public talk page: https://johannesburg.aitinkerers.org/talks/rsvp_KeOgSIP594M

### [Lazy Marketing v3: From Meeting to Content Pipeline in Zero Click](https://seattle.aitinkerers.org/talks/rsvp_TtXOReDjy68)

Most of us have 10+ meetings a week full of insights worth sharing — but turning those into content never happens. Marketing Machine fixes that by wiring together Claude, Gemini, Slack, Google Sheets, and the LinkedIn API into a fully automated content pipeline. A Read.ai transcript hits a webhook. Claude extracts the best marketing hooks and expands them into on-brand LinkedIn posts using a 100+ line brand-voice prompt. You pick and refine posts entirely inside Slack with buttons and modals — no separate app needed. Gemini generates an accompanying image. Approved posts queue up in Google Sheets and auto-publish to LinkedIn on a schedule. In this demo, I'll walk through the full loop live — from raw meeting transcript to a published LinkedIn post — and dig into the prompt engineering, multi-model orchestration, and Slack-as-a-UI patterns that make it work. Built with Node.js, Express, and APIs anyone can sign up for. No GPUs, no fine-tuning, no ML infra required.

- Event context: AI Tinkerers Seattle: GTM Track — March — 2026-03-26 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_TtXOReDjy68

### [\[UofT\] AI-Powered Self-Assessment: Transforming How Students Understand What They Know](https://toronto.aitinkerers.org/talks/rsvp_KTr4NgGJt9c)

Our presentation will introduce a web-based platform designed to help students improve their learning through structured self-assessment. The system is based on Cognitive Structure Analysis (CSA), a method that focuses on identifying the concepts a student understands rather than simply checking whether they can produce the correct answer on a test. Research conducted by MyEdMaster across multiple countries and subject areas shows that students who use CSA can improve their academic performance by an average of 1.5 to 2.5 letter grades. We will demonstrate how our platform allows students to access CSA self-assessment templates, evaluate their understanding of key concepts, and identify gaps in their knowledge. Once these gaps are identified, students can focus their studying on the areas where they need the most improvement. The website also supports classroom use by allowing teachers to register classes and receive aggregated reports that highlight student learning needs, helping guide instruction. Additionally, we will discuss how AI-powered tools integrated into the platform can assist students by simplifying self-assessment, generating study prompts, and improving accessibility. Overall, the project aims to provide a scalable, user-friendly tool that empowers students to better understand their own learning and study more effectively.

- Event context: AI Tinkerers Toronto - March - hosted by Mozilla! — 2026-03-25 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_KTr4NgGJt9c

### [Building Document Consciousness: How I Taught Gemini to Think in 6 Dimensions](https://san-diego.aitinkerers.org/talks/rsvp_CuPjQckMXvM)

I'll demo Clasio, a document intelligence platform I built solo on a 100% Google Cloud stack, showing how I use Gemini 2.5 Flash (extensible to Gemini 3 in a few keystrokes) to extract what I call "6D Document Consciousness" - analyzing every uploaded document across What, Who, When, Where, Why, and How dimensions simultaneously. I received $25K in credits from Google Cloud for Startups for Clasio. The technical meat of the talk: - How I built an async AI queue that processes 25 documents in 75 seconds using 30 parallel Gemini workers on Cloud Run - The structured extraction prompt engineering that gets Gemini to reliably output 6D consciousness JSON (and what failed before it worked) - A 6-tier search waterfall that goes from exact consciousness match down to fuzzy vector similarity using pgvector on Cloud SQL - returning direct answers, not document lists - How I handle connection pool management when you have 30 concurrent Gemini API calls each taking 2-10 seconds (spoiler: release the DB connection before the API call, not after) - Live demo: upload a stack of immigration documents and watch the system classify, extract entities, detect deadlines, and answer natural language questions in real time This is a solo founder build - no team, no VC money, just a product person who learned TypeScript and shipped to production on GCP.

- Event context: AI Tinkerers San Diego: February Meetup at Google — 2026-02-27 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_CuPjQckMXvM

### [Blocks: Turning Natural Language into Production-Grade React Components](https://london.aitinkerers.org/talks/rsvp_rrlKrwRqEm0)

In this talk, I’ll share how I built Blocks, a system inside Paid.ai that transforms natural language into production-ready React components. Blocks are not just code snippets, each one is a self-contained module (React + CSS) that: * Fetches and normalizes real data * Handles loading, error states, and null-safety * Applies consistent conversions (currency, dates, booleans) * Stays composable within a larger design system I’ll walk through the architectural migration from a brittle, endpoint-based pipeline to an agentic, orchestrated system powered by modular tools, Zod schemas, and real-time telemetry. The session will cover the orchestrator design, workflow composition (ClickHouse queries, SQL persistence, and component generation), and the guarantees that make Blocks safe, predictable, and fast to ship. Attendees will also see examples of Blocks in action: from a natural language prompt, through schema-validated toolchains, to a drop-in UI component.

- Event context: AI Tinkerers x MongoDB - Demopalooza — 2025-10-07 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_rrlKrwRqEm0

### [The Lazy Builder's Marketing Machine or: How I Learned to Stop Worrying and Love the Slop](https://seattle.aitinkerers.org/talks/rsvp_2sWi58qwR9w)

What if your customer meetings and daily standups automatically became LinkedIn posts? I built an AI pipeline that turns meeting transcripts into brand-aligned social content—no human required. This talk covers the technical journey: Read.ai webhooks → OpenAI processing → LinkedIn publishing, with all the messy realities of webhook failures, prompt engineering, and API rate limits. You'll see live demos of real transcripts becoming posts, learn why "structured prompts" beat perfect prompts, and discover how embracing AI "slop" actually works better than perfectionist manual posting. Talk preview- short demo, the talk will be strictly technical and non-promotional. and a link to the github will be provided if anyone wants to tinker on this afterwards

- Event context: AI Tinkerers Seattle September Meetup — September 30, 2025 — 2025-10-01 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_2sWi58qwR9w

### [Deburger - An AI powered Debugging tool and community support tool for developers](https://pune.aitinkerers.org/talks/rsvp_AJA6FXjv9xc)

Deburger is your all-in-one AI-powered coding companion designed to make debugging effortless and learning fun. Whether you’re a beginner struggling with syntax errors or an experienced developer chasing down tricky bugs, Deburger is here to guide you every step of the way. On our platform, you can: Debug your code instantly – Get clear, precise error explanations and fixes tailored to your language and logic. Understand your code – Receive AI-generated explanations to truly grasp what your code is doing. Access corrected solutions – Learn the right way to write and structure your code. Discover learning resources – Curated guides, tutorials, and materials to strengthen your skills. Build your profile – Track your progress, showcase your skills, and grow as a developer. And our special feature – Open Community – lets you connect with other developers, post your doubts, and solve problems collaboratively. Whether it’s a quick syntax question or a complex algorithm challenge, someone’s always ready to help. Deburger isn’t just a tool; it’s a community-driven learning hub where code errors turn into opportunities, and developers turn into problem solvers. Debug smarter. Learn faster. Build better.

- Event context: AI Tinkerers Pune - Meetup — 2025-08-23 — Pune
- Public talk page: https://pune.aitinkerers.org/talks/rsvp_AJA6FXjv9xc

### [Automating Jobs](https://hong-kong.aitinkerers.org/talks/rsvp_Ey4kTLQYzZA)

I’ll be presenting Amploy, an AI-powered job platform that streamlines both the job-seeking and hiring process. On the candidate side, Amploy aggregates listings from across the web and offers a browser extension that auto-fills job applications, generates tailored cover letters, and adapts CVs to match specific roles. For employers, Amploy provides an HR tool with AI-powered interviews, enabling faster and more consistent candidate evaluation. The platform is designed to reduce friction in hiring, save time for both applicants and recruiters, and make the job application process more accessible and personalized.

- Event context: AI Tinkerers - Hong Kong Meetup (August) - Meetup with Baidu PaddlePaddle — 2025-08-22 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_Ey4kTLQYzZA

### [Building Real-Time Voice Agents with OpenAI's Agent SDK](https://fort-wayne.aitinkerers.org/talks/rsvp_5viYWjRy4BE)

Live coding demonstration showing how to build real-time voice conversations with AI using LiveKit's WebRTC infrastructure and OpenAI's Realtime API. I'll walk through the actual Javascript code to create a multimodal agent with function calling. Then I'll add memory capabilities to create a "Digital Barista" that remembers customer preferences across sessions.

- Event context: AI Tinkerers Fort Wayne August 2025 Meetup — 2025-08-19 — Fort Wayne
- Public talk page: https://fort-wayne.aitinkerers.org/talks/rsvp_5viYWjRy4BE

### [Group Partner Healthtech & CTO Theodo France](https://paris.aitinkerers.org/talks/rsvp_nQdDHtxpl4Q)

"From Monolith to Modular Architecture: Mapping 500k+ LoC with AI and Graphs" Problem statement : To migrate a complex legacy application (here a monolith in Express to a modular architecture in Hono) we need to map all the existing code to a target architecture (e.g. Controller -> Service -> Model). Because static code analysis alone often fails to capture implicit logic, dynamic routing, or unconventional patterns, manual inspection is typically required—making the mapping process both time-consuming and resource-intensive. By using GenAIScript in combination with an AST parser, we managed to map the whole codebase in 1 hour instead of days, resulting in 6000 nodes that can be visualised with Neo4J.

- Event context: AI Tinkerers - Paris Meetup on June 26th - Google Cloud AI — 2025-06-26 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_nQdDHtxpl4Q

### [End-to-end AI Autograding](https://singapore.aitinkerers.org/talks/rsvp_cecnUyJmsIc)

Many AI autograding tools don't work as expected because Large Language Models are probabilistic. If these tools are not good at grading at this point in time, how can they still be a useful tool for educators. Built by a teacher for teachers, this tool shows the end-to-end pipeline of how an autograder can be built and deployed in the educational setting.

- Event context: AI Tinkerers Singapore: May Meetup - May 21st, 2025 — 2025-05-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_cecnUyJmsIc

### [Lessons from building an LLM-first framework](https://london.aitinkerers.org/talks/rsvp_VppNCC7KPgk)

We've been developing Tonk for shareable, multiplayer applets enriched with context and intelligent from across your life. What makes developing these applets a little different is that they are "malleable", that is, they are meant to be updated quickly by the users of the application through vibecoding. At first, we struggled to keep the coding agents from going off the rails, but now our framework, to our surprise, is totally usable by non-coders. I'll talk about the two ways we achieve this: 1) eliminating the need for context beyond the frontend (ie. what the agent can see) 2) prompting with lots and lots of hint files I can also talk about a few failed experiments: using a recursive task definition framework for the agent and injecting context through MCP plugins.

- Event context: AI Tinkerers London - April Meetup — 2025-04-23 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_VppNCC7KPgk

### [TaxGPT: Using AI to answer tax filing questions for Canadians](https://toronto.aitinkerers.org/talks/rsvp_YSYb16i3uxo)

TaxGPT.ca is an AI app that uses CRA data to answer questions about tax filing. TaxGPT.ca is a live AI app that has answered over 40k questions (26k in its current form as a RAG app). I would be happy to explain how TaxGPT is built and how my data processing pipeline works to answer the right questions, filter out bad ones, and estimate how 'complex' questions are to answer.

- Event context: AI Tinkerers Toronto - March 2025 Meetup at Mozilla — 2025-03-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_YSYb16i3uxo

### [Analyrics](https://ann-arbor.aitinkerers.org/talks/rsvp_FZFDu4lM0Wk)

25,000+ Users | Analyrics: Lyrics Analysis Platform analyrics.info, github.com/shah-aryan/Analyrics Built and deployed "Analyrics," a full-stack web application with a lyrics analysis database of 1M+ songs, artists, and albums, using MongoDB, Express.js, React, Tailwind, RESTful APIs, and Node.js for low latency and well-received iconic UI Developed efficient web scrapers for 1M+ web pages, implementing concurrency in Python, leveraging rate-limiting to avoid IP bans, and employing robust error handling, data validation, and retry mechanisms to ensure data integrity and reliability Implemented NLP algorithms for lyrics analysis, including sentiment and emotion analysis with NRCLex and part of speech recognition with spaCy to identify emotions, vocabularies, trends, sentiments, and collaborations in music Visualized interactive artist collaboration maps, emotion analyses, reading levels, and word clouds creatively using D3.js Received positive feedback from users and tech companies (Apple, Spotify, Genius, Dots(YC21)), contributing to 25,000+ users

- Event context: AI Tinkerers: Ann Arbor - September 18 — 2024-09-18 — Ann Arbor
- Public talk page: https://ann-arbor.aitinkerers.org/talks/rsvp_FZFDu4lM0Wk

### [Testing LLMs in Web Applications](https://nyc.aitinkerers.org/talks/rsvp_XqTMzgh-fEw)

I want to talk about testing LLMs in production web applications. There are a lot of ways to integrate your LLMs into apps: REST API requests, SDKs, etc. but not a lot of easy-to-use tooling to make testing straightforward and high-signal. I'm collaborating with my MIT roommate on a unit testing library - Poyro - that makes it dead-simple to test LLMs that work as part of Node-based web applications (e.g. Next.js, Express, etc.). I wanted to share how we're thinking about testing and how other web app engineers might as well.

- Event context: AI Tinkerers July Meetup — 2024-07-24 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_XqTMzgh-fEw

## Related Technologies

- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 219 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 105 public demos
- [Backend](https://aitinkerers.org/technologies/backend) ([Markdown](https://aitinkerers.org/technologies/backend.md)) — 7 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [AST parser](https://aitinkerers.org/technologies/ast-parser) ([Markdown](https://aitinkerers.org/technologies/ast-parser.md)) — 1 public demo
- [Automerge](https://aitinkerers.org/technologies/automerge) ([Markdown](https://aitinkerers.org/technologies/automerge.md)) — 1 public demo
- [AWS EC2](https://aitinkerers.org/technologies/aws-ec2) ([Markdown](https://aitinkerers.org/technologies/aws-ec2.md)) — 2 public demos
- [Azure OpenAI](https://aitinkerers.org/technologies/azure-openai) ([Markdown](https://aitinkerers.org/technologies/azure-openai.md)) — 7 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [BullMQ](https://aitinkerers.org/technologies/bullmq) ([Markdown](https://aitinkerers.org/technologies/bullmq.md)) — 2 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos