On this episode of Masters of Data, we revisit the predictions Adam White, Zoe Hawkins, and David Girvin made at the end of last year, checking our own scorecard halfway through 2026. The hits: agents running amok and deleting databases, MCP becoming the backbone for tracking what agents actually do, growing security gaps around personal data, and a collective rejection of low-quality AI content. The misses: we underestimated how fast companies would cut staff for AI, then quietly start rehiring once the agents couldn’t cover the work, and we’re still arguing about whether token burn is a cost problem or a coming attack vector. Security and marketing leaders weighing their own AI rollout will find plenty to steal here, especially the case for building governance before the connect button gets clicked.
0:00:00 – Revisiting last year’s AI predictions
0:01:13 – Agents running amok, from deleted databases to deleted backups
0:03:45 – MCP becomes the dominant way to track agent activity
0:09:00 – Security gaps and oversharing with AI assistants
0:14:29 – Deepfakes, fake candidates and the recruiting nightmare
0:20:51 – Collectively calling BS on obvious AI content
0:26:31 – Underestimating AI adoption speed and the quiet rehiring wave
0:32:56 – Token burn as corporate strategy and future attack vector
0:36:47 – Rethinking the patching paradox and open source security
0:41:09 – Wrap-up and the next round of predictions