Built by the people who built the evals.
Lattice/AI is founder-led. The firm was started by an ex-ML infrastructure and policy practitioner who previously built internal evaluation suites for LLM labs and enterprise teams. We start small and stay focused, and we grow the team alongside our clients rather than ahead of them.
We turn down work we cannot put our name on, which is what keeps the rest of the practice credible.
AI should not be deployed on trust alone. We exist to make trustworthy evaluation practical, turning uncertainty into clear frameworks, evidence-based findings, and actionable runbooks. Whoever ships the AI, we are the ones who sign off on whether it is ready.
Founder-led by design.
Lattice/AI is small because that is the operating model, not because the firm is new. Every artifact on this site was written by the person who did the work, and the person you brief on an engagement is the same person who signs the report.
Our core practice covers the following areas:
- LLM and agent evaluation methodology
- Adversarial red-teaming and prompt-injection research
- Retrieval and RAG grounding evaluation
- Governance mapping for EU AI Act, NIST AI RMF, and ISO 42001
- Engineering integration including shadow gates, regression suites, and CI evals
When an engagement calls for it, specialists join the team, including regulated-industry counsel, vertical domain experts, and security researchers. They are named in the brief and on the report, and they leave the team when the engagement closes.
Tell us what’s under contract.
Three sentences is usually enough. Tell us what you are trying to ship, when it has to land, and the thing that scares you about it.