video1.0<iframe src="https://www.loom.com/embed/3e8fd981f2f44cc49eadaaa29b31d0d2" frameborder="0" width="2940" height="2205" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>22052940Loomhttps://www.loom.com22052940https://cdn.loom.com/sessions/thumbnails/3e8fd981f2f44cc49eadaaa29b31d0d2-15223d6cacff9edd.gif191.192This Loom explains a system for capturing conference session knowledge and turning it into a usable “team brain” graph for organizers. The speaker contrasts a failed approach where four engineers attend dozens of sessions for three days but bring back little learning, with an automated workflow that publishes dry data to the live web and pulls actual GitHub Universe documentation where each session becomes a node. It also generates team graphs using FalcoDB to connect repositories to talks via MCP, builds NFC stickers for check-in, and shows the evidence path during the TAP demo. The team can add a new node by typing one line and saving it, so information is shared once instead of staying in four separate brains.