aiqbench analysis
This article addresses the critical challenge of building trustworthy AI in high-stakes domains like finance by integrating deterministic verification layers around large language models. Kepler's approach prioritizes provenance and traceability, ensuring that every numerical output is clickable and mathematically verifiable rather than relying solely on model intelligence. This engineering strategy effectively mitigates hallucinations and maintains accuracy where reliability is non-negotiable.
This Shit is Hard: Getting AI to prove where a number came from

From Chainguard
ExcerptTrustworthy AI takes more than a powerful model. See how Kepler uses deterministic systems and provenance to make financial analysis verifiable.
Vinoo Ganesh and Sara Kromwijk work at Kepler, a model-agnostic verifiable AI platform that separates what models do well, language and reasoning, from what deterministic tools do well, retrieval and computation.
Chainguard’s "This Shit is Hard" series showcases the difficult engineering work that goes into building software people can rely on. This includes work we’ve done ourselves and by teams solving hard problems adjacent to ours. Today, Kepler explains the challenges of building AI that financial analysts can trust, and why it means writing more software around the model, not waiting for a smarter one. Turns out, this shit is hard.
At its core, Kepler is a deterministic harness for AI. We separate what LLMs are genuinely good at (the nondeterministic work) from what code, math, and other deterministic tools are good at. The platform has one major invariant: provenance and traceability, in service of accuracy.
Excerpt shown under the publisher's RSS terms · 146 words · full text and figures are on the publisher's site
Related coverage

Self-Service Analytics Stalled Once. Will AI Stall It Again?
AtScale · Oct 14, 2026

Links #5: 2026/07
LessWrong · Jul 31, 2026
Stop Chasing Views: How to Reduce x-Risk as an AI Safety Content Creator
LessWrong · Jul 19, 2026

Evaluating Red Team and Blue Team Capability for AI Control Research
LessWrong · Jul 24, 2026