---
title: "Context in Practice Summit | Dec 3 | Atlan"
url: "https://atlan.com/context-in-practice-summit/"
description: "A virtual summit on Dec 3. See how leading data & AI teams got the business using their catalog and trusting their AI, with resources to do the same."
---

**Context in Practice Summit. Your peers built AI their business trusts. Now they'll show you how.** A free virtual summit on Thursday, December 3, 2026, 11:00 AM to 1:20 PM ET. Your catalog holds the context your business runs on. Leading data and AI teams show how they use an **Agentic Data Catalog** to take it where people ask questions, and into analytics agents the business trusts.

Register (free, work email): [https://atlan.com/context-in-practice-summit/](https://atlan.com/context-in-practice-summit/)

## Speakers

- **Prukalpa Sankar**, Co-founder, Atlan. Opening and closing keynotes.
- **Abhishek Mishra**, Senior Product Manager, Atlan. Context Lakehouse.
- **Nandini Tyagi**, Strategic Initiatives Lead, Atlan. Rollout & Adoption.
- **Steven Hloros**, Sr. Customer Education Manager, Atlan. MCP Cookbook.
- **Himanshu Sikaria**, Head of Customer Experience, Atlan. Analytics Agents.
- Community speakers from leading data and AI teams: announced soon.

## Product playbooks + production proof

In just over two hours, see where each part of the Agentic Data Catalog is headed, how your peers put it to work, and what you need to start on your own.

- **From peers in production.** Practitioners from leading data and AI teams show how they put each one to work: the architecture, the tradeoffs, and the lessons that only come from building it and running it.
- **From Atlan's product leaders.** Atlan's product leaders see what's working across every customer building on Atlan. They share the decisions behind each capability, where the industry is headed, and the resources to get you started.

## Resources to take home

Tools to use right away: recipes for MCP in any AI tool, skills for trace analysis and AI-ready data reports, and Atlan AI Labs research on structuring context for agents.

| Resource | Type | Session | From |
| --- | --- | --- | --- |
| AI-Ready Data Report Skill | Skill | Lakehouse | Abhishek Mishra |
| MCP Cookbook | Cookbook | Rollout & Adoption | Steven Hloros |
| Trace Analysis Skill | Skill | Rollout & Adoption | Nandini Tyagi |
| AI Labs Research | Research | Agents | Himanshu Sikaria |

## Agenda

December 3, all times ET. Start times are provisional.

### 11:00 AM / Opening keynote (10 min)

Prukalpa Sankar, Co-founder, Atlan.

### 11:10 AM / Lakehouse architecture (25 min): the open foundation for your enterprise context

Data teams want more from their context, like reporting on what's governed and what's ready for AI, straight from the engine they already use. Agents reach for that same context on every call, and catalogs built for people to browse can't keep up. Serving both takes a foundation of its own.

- **Product briefing (10 min): Inside the Context Lakehouse.** Abhishek Mishra, Senior Product Manager, Atlan. Everything your catalog knows, including definitions, lineage, policies, and the business knowledge around them, can now live in an open, Iceberg-native store that any engine or agent can query. The decisions behind it and the architecture patterns emerging across the customers who've turned it on: why it's designed to stay open and portable, how it keeps a record of exactly what context an agent saw on any given day, and how to get started. Resource: AI-Ready Data Report Skill.
- **Presentation (15 min): What it took to put a lakehouse into production.** Community speaker, announced soon. A close look at a Context Lakehouse running at enterprise scale, and the blueprint behind it: the design choices the team made, how it fits alongside the rest of their stack, and how it puts governed context within reach of the AI their business is building.

### 11:35 AM / Rollout & adoption (60 min): what teams with real adoption have in common

Well-documented data is a start. The payoff comes when people actually use it: in the chat windows where they ask their questions, and the AI tools and agents working alongside them. Atlan experts and speakers from across the community share what a strong rollout looks like, what brings people back for more, and how every question they ask can make the catalog better.

- **Field notes (5 min): Changing consumption patterns in an AI-native world.** Nandini Tyagi, Strategic Initiatives Lead, Atlan. People have stopped typing keywords to find data. They ask in plain language, in chat tools like Slack, and more and more from inside the AI tools they already use. Nandini has built alongside more than 100 of the world's leading data and AI teams, and walks through what that shift means for adoption: where people now go for answers, and how to meet them there.
- **Panel (15 min), Conversational Search: Adoption lessons from teams who've done it.** Community speakers, announced soon. Users will try a new way to ask about their data once. Whether they come back depends on the answer. With Conversational Search, anyone can ask from Slack, Teams, or their browser and get an answer grounded in governed context. Panelists who've rolled it out trade notes on how to keep a rollout from stalling, and what kept their people asking long after launch day.
- **Playbook (10 min), MCP: The art of the possible with MCP.** Steven Hloros, Sr. Customer Education Manager, Atlan. MCP can carry your catalog's context into almost any AI tool, but getting it connected is the easy part. The value comes from what you do next: trace a broken dashboard to its root cause, see what a SQL change will break before you merge, ground AI-written code in your real schema, score assets for AI readiness, or grow your business glossary. Steven opens up the MCP Cookbook, more than 30 tested recipes gathered from the ways customers put MCP to work, and explains how to contribute your own as it keeps growing. Resource: MCP Cookbook.
- **Panel (20 min), MCP: MCP use cases worth copying.** Community speakers, announced soon. Many teams already have MCP connecting their context layer to an AI tool or two, but the protocol reaches much further: AI assistants and internal chatbots, engineers' code editors, enterprise search, workflow automation, data pipelines, even agents that keep the catalog documented. Panelists building with it today share the use cases they've put to work, how they decided where MCP fits in their business, and what held up as they built it out.
- **Playbook (10 min), Self-Improving Catalog: Building a self-improving data catalog.** Nandini Tyagi, Strategic Initiatives Lead, Atlan. Coverage tells you how much of your catalog is documented. It can't tell you whether that context actually worked. Every question people and agents ask leaves a trace, and Nandini walks through how teams read those traces to find where answers went wrong, route each gap to the right fix, and make the next answer better than the last. Resource: Trace Analysis Skill.

### 12:35 PM / Agents on the context layer (40 min): what it takes to build an agent that works

Agents get answers wrong when they're missing what a person would know to check, like metrics and semantic models, lineage, access policies, and the business knowledge scattered across documents and people's heads. Practitioners who've shipped analytics agents break down how they built that context together, business domains and end users alongside AI, data engineering, and governance teams, and why it carries over to whatever tool comes next.

- **Research (10 min): The research behind agents that get it right.** Himanshu Sikaria, Head of Customer Experience, Atlan. An analytics agent is only as good as the context it's handed, and the hard part is knowing which context matters most. Atlan spent more than a year finding out, building agents alongside customers and putting every piece to the test, from governed metrics to the evals that catch a wrong answer. Himanshu shares what held up, so you can plan next year's agents on the context your catalog already holds, without the trial and error it took to get there. Resource: AI Labs Research.
- **Lightning talks (30 min): Three agents in thirty minutes.** Community speakers, announced soon. Three teams, ten minutes each, one analytics agent apiece: what it does, who it serves, and the context that makes its answers worth trusting.

### 1:15 PM / Closing keynote (5 min)

Prukalpa Sankar, Co-founder, Atlan.

## Save your seat

The community is showing its work. Context in Practice Summit, Thursday, December 3, 11:00 AM ET, virtual. Practitioners from leading data and AI teams, and Atlan's product leaders. Register with your work email: [https://atlan.com/context-in-practice-summit/](https://atlan.com/context-in-practice-summit/)