BLOG

Ground truth for the AI era.

Essays on building AI that doesn't make things up.

Context Is The Easy Part

Everyone's talking about context engineering. Context engineering isn't a context problem. It's an engineering problem.

Finance

The AI Era of Finance - A Practitioner's View

Large language models excel at summarizing ideas, but struggle with the one thing finance can’t compromise on: numerical truth. Without grounding, traceability, and verification, AI risks accelerating errors rather than insight.

Engineering

Trust in the Age of AI

When errors look indistinguishable from success, trust depends less on smarter models and more on verification, provenance, and systems that force reasoning into the open.

Company

Why I Joined Kepler

From Meta to four seed-stage startups, Susannah has learned what actually matters when building from zero to one. In this post, Kepler’s Founding Engineer shares why she joined Kepler and why building fully traceable AI systems is a challenge she couldn’t pass up.

CAREERS

Built by the team behind mission-critical infrastructure across defense, healthcare, and finance.

We build data infrastructure that makes AI actually work. Here's who we're looking for.