By Janus Boye
Practical details
When:
Thursday, 3 September 2026
15:00–15:30 Aarhus / 9:00 TorontoWhere: Online
Format: 30 minutes conversation + Q&A
Free registration below
AI works well when it understands the context in which it is operating. Yet much of that context has never been written down.
Systems carry years of decisions, exceptions and compromises that may look like mistakes to anyone—or any AI—without access to their history. The obvious correction can easily break something that was done deliberately.
Before CMS Connect 26 in Montréal, Andrei Kalamkarov wrote about the memory he was building for AI. His conversations at the conference expanded that thinking: perhaps this is not only about helping an AI work with one system, but about preserving institutional memory more broadly.
In this member call, Andrei will share what he has learned, how Montréal changed his thinking, and invite us to consider the memory our own organisations need to make visible.
Andrei Kalamkarov leads the team behind Concordia University’s web platform
Andrei Kalamkarov leads the team behind Concordia University’s web platform and has worked with its CMS since its beginning. At CMS Connect 26, his session, AI in a 13-year-old CMS, explored what happens when AI encounters a system shaped by years of decisions it cannot see.
What we’ll explore
What Andrei includes in the memory he is building for AI
Why undocumented decisions matter when AI works with established systems
How the conversations in Montréal expanded his thinking
When an apparent mistake is actually an intentional choice
What memory each of us may need to capture in our own organisations
Sign up below and we’ll send you the calendar invite within 24 hours. If you can’t make it, we will record the session so that you can enjoy it later. Everyone who has signed up will get notified when the recording and summary is published.
Finally, feel free to share this call invitation with a colleague or friend who’d enjoy it too.
Free registration for the 3 September call on building memory for AI
The conversation continues
If reading and being a part of an online call is not enough, you’re very welcome to join us more actively. Our community is built around learning together, comparing notes, and exploring how theory meets practice across roles, industries and regions.
You can also:
download the slides (PDF) or even lean back and enjoy the entire recording
join our free, regular member conference calls
find a peer group that matches your role and challenges
attend our unique conferences, designed for deep discussion rather than surface-level inspiration
However you choose to engage, we’re glad you’re here and part of the journey.
