Skip to content
Hermes Intelligence
Get started
Research

Whitepaper · Vextrum and Kairos

AI agents for high-stakes work

What we learned building Vextrum and Kairos.

An agent can prepare a convincing assessment while leaving out the fact that would change the decision. A reference beside an answer gives the reader somewhere to look, but still leaves them to establish whether the source supports the claim.

Drawing on Vextrum and Kairos, this paper sets out ten design requirements and five levels of trust, examines how evidence is checked, and explains where human judgement and approval remain essential.

Published

November 2026

Length

25 pages, PDF

Author

Sebastian Kaczmarczyk, Chief Product Officer

Get the whitepaper

Tell us who is reading. The paper is yours to download as soon as you send this.

Type of organisation

Your details go to the Vextrum team and nowhere else. See Privacy.

Inside

  1. The costly mistakes of AI agents read like correct answers
  2. We hold our agents to ten rules
  3. Trust in an agent comes in five levels, set by what the answer shows
  4. A trustworthy answer shows what it rests on
  5. Only questions the agent has never seen count
  6. Most of what makes an agent dependable lies outside the model
  7. Vextrum answers with its evidence attached
  8. Kairos shows every rule of a call in the call’s own words
  9. The person decides, and the system is built to keep it that way
  10. Agents are moving from answers to finished work
  11. Ten questions we ask of our own agents
  12. The hardest questions concern what the evidence can establish

Look inside

  • Cover

  • Page 8 · Five levels of trust

  • Page 16 · Evidence and judgement

  • Page 18 · The applicant decides