Cover Image for End-to-End AI Stack - From Data to Agents in Production x MLOps Community

Presented by

The MLOps Community fills the swiftly growing need to share real-world Machine Learning Operations best practices from engineers in the field. While MLOps shares a lot of ground with DevOps, the differences are as big as the similarities. We needed a community laser-focused on solving the unique challenges we deal with every day building production AI/ML pipelines.

We’re in this together. Come learn with us in a community open to everyone. Share knowledge. Ask questions. Get answers.

Join us every week for a live virtual meetup, Wednesdays at 5 PM UK, 9 AM PT, where top experts share what they’ve learned running pipelines for organizations big and small. We’re also firing up “coffee sessions” where we dive deep into the emerging stack of ML tools and platforms.

You can also check out our Slack and podcast that’s filled with tips and tricks to overcoming the common obstacles we’ve all hit in the real world. Find the solutions you need. Share, learn and grow with us, as we work to bring standardization to the chaotic world of MLOps.

Hosted By

197 Going

AI

Featured in

Bond AI - San Francisco and Bay Area

End-to-End AI Stack - From Data to Agents in Production x MLOps Community

Name: End-to-End AI Stack - From Data to Agents in Production x MLOps Community
Start: 2026-05-12T17:00:00.000-07:00
End: 2026-05-12T20:30:00.000-07:00
Location: 625 2nd St

San Francisco MLOps Community

625 2nd St

San Francisco, CA

3 Spots Remaining

Hurry up and register before the event fills up!

Approval Required

Your registration is subject to host approval.

Welcome! To join the event, please register below.

You will be asked to verify token ownership with your wallet.

About Event

Most AI demos show one tool, this one shows the whole stack!

Four demos. One unified narrative: how a production AI system actually gets built, from raw web data to an agent taking action in the real world.

The Stack We're Demoing

Data Layer - High-volume web data ingestion at scale. Why most tools break here, and what infrastructure-first looks like in practice.

Reasoning Layer - An agent reasoning over live data inputs. Summarization, planning, multi-step decisions. How raw data becomes usable intelligence.

Build Layer - Live coding a production AI workflow. Wiring APIs, iterating on pipelines, debugging agent logic, fast.

Execution Layer - The agent acts. Triggering workflows, automations, downstream systems. Closing the loop from reasoning → action without getting blocked.

AGENDA:

5:00 – 5:30 PM — Arrival & Networking; Check-in, drinks, informal networking

5:30 – 5:40 PM — Opening Remarks (Bright Data)

5:40 – 7:30 PM — Partner Demos (Stack Walkthrough)

Rafael Levi, DevRel at Bright Data, will showcase how AI agents interact with the live web reliably at scale — navigating dynamic sites, retrieving structured real-time data, and powering downstream reasoning and execution systems with fresh external context.

Maxime Beauchemin, creator of Apache Airflow and Apache Superset, will demo Agor, a multiplayer workspace designed for collaborative, agent-driven software development. In this session, Maxime will show how engineers and AI agents can work together in a shared environment to plan, write, and iterate on code in real time. Agor introduces a new way to build software by combining human judgment with AI assistance, helping teams preserve context, coordinate multiple agents, and accelerate development workflows.

Jiquan Ngiam, Co-founder of MintMCP, demos Claude Code orchestrating 25 agents — GitHub-backed memory, MCP Gateway permissioning, Slack-triggered sandboxes, and hook-driven guardrails. The full agent loop, exposed.

Sterling Chin, Founding developer relations at Inngest, will demo an AI triage agent that traces failures across repos and APIs, identifies root causes, and automatically generates structured RCAs directly into Linear.

Justin Chavez, Head of Applied Engineering at Inkeep, will demo Open Knowledge, Inkeep’s open-source agent-native knowledge engine, where agents ingest live web data, generate “what changed” updates, and compound memory directly into a live knowledge graph.

7:30 - 8:00 PM — Q&A and Closing

8:00 – 8:30 PM — Networking

You'll leave knowing:
→ How a full production AI stack fits together
→ Where the real bottlenecks are (hint: it's not the model)
→ What to build vs. buy at each layer

This is Part 1 of 2 sessions, Our hands-on workshop continues May 27 (https://luma.com/ou5uq4vi).

🍺 Open bar · 👥 Limited capacity · Builders only

Location