Source: https://events.trymimetic.com/events/sf/agentic-ai-night-ai-agents-across-the-app-stack-nov-2026

# Agentic + AI Night: AI Agents Across the App StackSan Francisco, November 2026

**This event has ended.**
Upcoming San Francisco events are listed below.

When
:   Thursday, November 19, 2026, 4:00 PM to 9:30 PM Pacific Time (PST)

Where
:   [Terra Gallery & Event Venue, 511 Harrison St, San Francisco, CA 94105, USA](/events/venue/terra-gallery-event-venue)

City
:   San Francisco, CA

Format
:   In person

Cost
:   Free

Organiser
:   Agentic + AI Observability, Brooke Contreras, Lizzie S and 3 more

Who it's for
:   Software engineers, app builders, ML/AI developers, and AI startup founders

Listing
:   [The original listing on Luma](https://lu.ma/Agentic_AI_Night-11-19?utm_source=trymimetic&utm_medium=calendar&utm_campaign=ai_events)

## What we're seeing

- **Approval required**

## About This Event

Join us for another **Agentic + AI Night** on **Thursday, November 19** from 4:00pm - 9:30pm PT in SF for a multi-track deep dive into agentic web application development and the systems that power it.

This meetup is built for software engineers, app builders, ML/AI developers, and AI startup founders who are building or deploying autonomous agents and want to go deeper into the tech. We'll dive into real-world patterns, failure modes, and architectural models for leveraging AI agents to build and ship full-stack web apps, architect the data and backend layers underneath them, and scale intelligent workflows in production.

Whether you’re at an early-stage startup or an established enterprise, if you care about deploying agents in your organization’s workflows safely with clear controls and observability, this meetup is for you.

**You’ll hear from the following leaders in the AI space: Databricks, Neon, Vercel, OpenAI, Nimble and WorkOS!**

---

### 💡 Why You Should Attend

- **Learn What Actually Works in Production:** Hear real-world patterns, failure modes, and architectural models from teams using AI agents to build and ship full-stack web apps, straight from engineers at Databricks, Neon, Vercel, OpenAI, Nimble and WorkOS.
- **See Agents Set Up the Backend:** Watch live demos of agent-driven infrastructure, where prompts replace traditional configs for provisioning data and backend layers, and learn where human guardrails still matter.
- **Ship Quality, Not Slop:** Pick up practical strategies for generating production-quality apps instead of low-grade code, including how to keep agent-written code reviewable, tested, and maintainable.
- **Build for Non-Developers, Too:** Explore how teams are democratizing app development so non-coders can ship real apps, without giving up clear controls and observability.
- **Connect with Other Builders:** Meet software engineers, ML/AI developers, and startup founders deploying autonomous agents, swap lessons learned, and find potential collaborators. All in a pitch-free, technical setting.

**AGENDA**

- **4:00pm:** Registration & Mingling
- **5:30pm:** Keynote with [Kyle Mathews](https://www.linkedin.com/in/kylemathews/)
- **6:15pm**: Breakout #1 (2 tracks)

  - [TERRA] Ground Truth or Dare: Using Oracles to Make Postgres Reactive with [James Arthur](https://www.linkedin.com/in/thruflo/), Neon
  - [MER] Prompt to Production: Secure Data + AI Apps in Minutes with [Atila Fassina](https://www.linkedin.com/in/atilafassina/), Databricks
- **7:00pm:** Breakout #2 (2 tracks)

  - [TERRA] What Still Matters in Your Stack When Agents Write the Code with [Ricardo Gonzalez](https://www.linkedin.com/in/ricardo-agm/), Vercel
  - [MER] Giving AI Agents Better Access to the Web with [Michael Graham](https://www.linkedin.com/in/michaelleegraham/), Nimble
- **7:45pm:** Breakout #3 (2 tracks)

  - [TERRA] Auth.md - The Open Protocol for Agentic Registration with [Michael Grinich](https://www.linkedin.com/in/grinich/), WorkOS
  - [MER] Beyond Vibe Coding: Strategies for Building Production-Quality Apps with Coding Agents with [Mandeep Singh](https://www.linkedin.com/in/mandeep-singh-ca/), OpenAI
- **8:15pm:** Reception
- **9:30pm:** Goodnight

**SESSION DESCRIPTIONS**

- Prompt to Production: Secure Data + AI Apps in Minutes with [Atila Fassina](https://www.linkedin.com/in/atilafassina/), Databricks

  - You know your data and the workflow your team needs, but turning that into an app has usually meant waiting on an engineering team. Genie App Builder changes that. Describe the app you want in plain language, and the agent explores your data in Unity Catalog, asks the right questions, and builds a working app you can share with your team. Your admins set the rules once in App Spaces: who can use each app, what data it can reach, and how much it can spend. So every app you build is governed from the start, and each person only sees the data they're allowed to see. In this session we build an app live, from first prompt to deployed, look at what Genie App Builder handles for you, share tips for getting good results, and close with what's coming next.
- Ground Truth or Dare: Using Oracles to Make Postgres Reactive with [James Arthur](https://www.linkedin.com/in/thruflo/), Neon

  - Live SQL is the holy grail of realtime. Subscribe to any SQL query, with joins, aggregates and ordering, and the result stays live as your data changes. It’s easy to describe but very hard to build. At Electric, we spent years chasing it. Then we joined Neon and built it in weeks with coding agents, inside Postgres.
    Live queries are database infrastructure. This isn’t code you hand to an agent and hope for the best. So we used Postgres’s own query engine as an oracle. Once the agents had the ability to verify their own work, they could go super fast and burn down through the featue requirements.
    In this talk, I’ll cover what we built, how we built it and how oracles let us have both truth and dare: to get it right and ship fast with agents.
- Auth.md - The Open Protocol for Agentic Registration with [Michael Grinich](https://www.linkedin.com/in/grinich/), WorkOS

  - AI agents are becoming users of software — but most apps still only know how to authenticate humans.
    Auth.md is an open spec for agent-native authentication: a way for AI agents to discover how to register for a service, prove identity, request scopes, receive tokens, and start using an API without breaking out of the agent workflow.
    This talk introduces our work on Auth.md and the emerging pattern for AI agent auth standards — including agent-native signup, identity assertions, ID-JAG, delegated authorization, and service discovery through an auth.md file.
    You’ll also see a live demo where an AI agent discovers that Cloudflare supports agent registration, uses an Acme identity to create an account, receives an API token and account ID, sets up the Wrangler CLI, connects to Firecrawl, and deploys a live app.
    Auth.md is designed to help agents become legitimate users in your system — not fake humans, not spam, and not impersonators — but real agentic users with clear identity and authorization boundaries.
- Blessed Paths: What Still Matters in Your Stack When Agents Write the Code with [Ricardo Gonzalez](https://www.linkedin.com/in/ricardo-agm/), Vercel

  - If agents are writing all the code, does the stack you pick still matter?
    The cost of writing code in previously less-productive languages is becoming marginal, but the other parts of the stack (ecosystem, framework patterns and conventions, testing suites, and documentation) still drive an agent’s token efficiency and correctness.
    Implementing a philosophy of “convention over configuration” by establishing good patterns and blessed paths gives your agents guardrails that keep harmful slop from compounding, because the agent can focus on implementation without making dozens of decisions around how to set up auth, spin up a new service, or talk to the database; at which point, the main problem that remains is your ability to concretely articulate business requirements that you can trust the agent to execute and yourself to validate.
    This talk walks through what those blessed paths look like in practice, explores their effects by asking agents to build the same applications across languages and frameworks and seeing how an agent’s output changes when a convention exists versus when it has to invent one, then covers practical approaches to giving agents a spec and validating what they build.
- Beyond Vibe Coding: Strategies for Building Production-Quality Apps with Coding Agents with [Mandeep Singh](https://www.linkedin.com/in/mandeep-singh-ca/), OpenAI

  - Coding agents can generate an application in minutes, but getting from a working prototype to a reliable, maintainable product takes more than a prompt. In this session, we’ll explore practical strategies for building production-quality apps with coding agents, drawing on OpenAI’s experience with harness engineering. We’ll cover how to give agents the right context, enforce architectural boundaries, and build feedback loops with tests, browser-based verification, and observability. You’ll leave with a framework for improving code quality and reliability as you build faster.
- Giving AI Agents Better Access to the Web with [Michael Graham](https://www.linkedin.com/in/michaelleegraham/), Nimble

  - AI agents can write code and build applications, but many useful tasks depend on information that changes outside the app. Getting that context often means combining search, reading pages, and browsing across tools with different APIs and tradeoffs.
    In this session, Michael will introduce WebRouter, an open-source project for giving agents a common way to work with web tools. He’ll walk through an agent workflow that uses live web data, showing how the interface connects to providers and how routing can help choose an approach for a task. Along the way, he’ll discuss the practical tradeoffs around quality, latency and cost, and what it takes to evaluate the results.

## Hosted by

[Agentic + AI Observability](https://luma.com/AgenticAIObservability)

[Brooke Contreras](https://luma.com/user/brookecontreras)

[Lizzie S](https://luma.com/user/LizzieS)

[Yufa Li](https://luma.com/user/usr-pP0KwheKkCJ4MkL)

[Daniel Liden](https://luma.com/user/djliden)

[Jules Damji](https://luma.com/user/usr-QslrQuFCQy2Lvqz)

Part of [Databricks AI Agents and Observability Meetups](/events/community/databricks-ai-agents-meetup/sf): see their other events and how to co-host.

AI

Meetup

Founders

Investors

Agents

[See the original listing](https://lu.ma/Agentic_AI_Night-11-19?utm_source=trymimetic&utm_medium=calendar&utm_campaign=ai_events)

[20 more SF AI events this week](/events/ai/sf)

Site check

## See what's costing your site sales

See how your website, messaging, and go-to-market strategy stack up, in minutes.

[Check my site](/?utm_source=events&utm_medium=referral&utm_campaign=ai&utm_content=event_detail_cta)

## Coming up in San Francisco

### [The Commons Public Hours ☕](/events/sf/the-commons-public-hours-nov-2026-2)

Today · 9:00 AM PT
TBD
5 attending

### [SF Writing Club](/events/sf/sf-writing-club-nov-2026-2)

Today · 10:00 AM PT
TBD
1 attending

### [Festiverse 2026: Diwali Hackathon](/events/sf/festiverse-2026-diwali-hackathon-nov-2026)

Tomorrow · 9:30 AM PT
AWS Builder Loft, First Market Tower, 525 Market St Entrance, San Francisco, CA 94105, USA

### [Build Lean, Scale Global: India’s STEM Talent to Fundings from UAE & Singapore (Multiplayer AI Special Session)](/events/sf/build-lean-scale-global-indias-stem-talent-to-uae-singapore-markets-multiplayer)

Tomorrow · 3:30 PM PT
AWS Builder Loft, First Market Tower, 525 Market St Entrance, San Francisco, CA 94105, USA
72 attending

### [Founders Demo Night | YC, The Residency & More](/events/sf/founders-demo-night-yc-the-residency-more-nov-2026)

Tomorrow · 5:00 PM PT
San Francisco, California

### [Founder Friendsgiving Dinner](/events/sf/founder-friendsgiving-dinner-nov-2026)

Tomorrow · 5:30 PM PT
San Francisco, CA

[← Back to San Francisco Events](/events/ai/sf)
