og.rsts.dev

Series

Fiserv Forum 2026

Three dispatches from Fiserv Forum 2026: an architecture-first read on agentOS, the reliability that agents inherit from the core beneath them, and the data problem that decides whether any of it grounds. Written for the architect asking what actually ships versus what opens a statement of work.

3 parts · 32 min total · Aug 2026

A short series written before, during, and after Fiserv Forum 2026 (August 17-19, Las Vegas). Three reads for the banking architect walking the floor: which layers of the agentOS stack you can actually touch today, why an agent is only as reliable as the core it inherits from, and why the oldest problem in banking, the data, is the one that decides whether agentic banking grounds at all.

Fiserv Forum 2026: from reading the stack, to the reliability agents inherit, to the data problem underneath it all

  1. Part 01 14 min Announced or Shippable? A Developer Reads the Stack Under Fiserv's agentOS Fiserv Forum will pitch agentOS as the headliner, riding a coherent stack: Finxact's temporal core, Data Compass on Snowflake, a stablecoin that treats dollars as just another ledger position. The architecture is real. A banking architect on the only question worth the flight, which layers you can actually touch today, and which are client-only pilots pitched into a market that wants proof.
  2. Part 02 8 min agentOS Has to Eat Fiserv's Own APIs Fiserv's agentOS promises agents that do real banking work. That promise inherits the reliability of every API and core beneath it, and the hard test isn't the demo at 2pm, it's the unattended agent at 11pm while the core is closing the books. A banking architect on dogfooding, the end-of-day problem nobody demos, and whether the plumbing ships on time.
  3. Part 03 10 min The Data Was Always the Problem The verdict from the Fiserv Forum floor: the agent story is real, but announced is not turnkey, and underneath the keynote sits the problem banks never solved. Fiserv and Salesforce are fighting for the same agent surface on opposite stacks, and both are really fighting over who becomes your data's context layer. The last dispatch of three.
Start with Part 1 →