Registration of interest open
Sydney
- Date
- TBC
- Venue
- TBC
- Host
- TBC
Enterprises building AI agents keep discovering the model is not the hard part. The data layer underneath it is, because agents need memory, not just retrieval.
For AI engineering, platform, architecture and technology leaders.
A retrieval call returns a document. An agent needs to know what it already tried, what the user corrected, and what state the task is in. Those are different problems, and most stacks solve the first by adding a system and the second by not solving it.
That is the starting point for this series. Not a product session, and not a briefing. A table of senior people working through how many separate systems currently sit under one agent, which of them exist only because something else could not do the job, and what consolidating them would actually change.
Six cities across APAC, between October and November 2026. Each table runs under the Chatham House Rule.
MongoDB press release, 7 May 2026, and company boilerplate. Figures pending client verification.
Each table works through the same three questions, shaped by what the room brings to them.
The first question is an inventory: how many separate stores a single agent touches, how many of them were added to patch a gap rather than by design, and what the operational cost of that sprawl looks like on a bad day.
// tension: a stitched stack is a stack you operateIf an agent can remember across sessions, the product changes shape and so does the risk surface. This session looks at what teams have built on top of persistent state, and what they had to decide about retention and correction.
// differentiator: database, search, memory and embeddings in one platformConsolidation is not automatically the right answer. The table works through where a single platform genuinely reduces failure modes and where it just relocates them.
// trigger: unified AI data platform with native embeddingsEach city is its own table with its own room, confirmed independently. Registration of interest is open now, with dates and venues confirmed city by city.
The hardest part of running agents in production is not the model. It is the data layer underneath it.
CJ Desai President and CEO, MongoDB
Published MongoDB material behind the questions on the table. Share your details once to unlock all three.
Tell us which city suits you and we will come back to confirm your spot.
MongoDB began as a document database built for developers who found relational schemas an obstacle rather than a help. That developer-first instinct is still the clearest thing about the company two decades later.
It is now a general-purpose data platform spanning transactional workloads, vector and full-text search, embeddings and agent memory, with more than 65,000 customers.
Innovatus Media is a Sydney based B2B events agency that runs invitation-only executive roundtable series across APAC, EMEA and North America.
We convene senior decision makers for closed door conversations on the problems they are actually working on, and produce every element of the series end to end, from the room and the table to the follow up.
Connect for more details on the series.