Coming soon: Build Data + AI systems with evidence built in. Preview
Mitari Research

Researching how to make Data + AI systems verifiable

Mitari Research develops methods and infrastructure for domain-aware verification: representing intent, evaluating evidence, detecting silent failures, and improving development loops involving both people and AI agents.

Our work sits at the intersection of applied machine learning, data systems, evaluation, and developer infrastructure.

Authored by AI and Infra experts previously from Expedia, DocuSign, Target (Shipt), and Upwork
How our research fits together

Verification as a systems problem

Our research spans intent representation, evidence evaluation, independent verification, and feedback loops. The same two-layer strategy shapes what we build: a forthcoming build-with-evidence layer, verified by Fathom.

Build with evidence Coming soon

People and agents work with explicit intent, durable context, evaluations, and supporting evidence.

Passes the change and evidence forward
Fathom Available now

Independently verifies the change, surrounding logic, and available evidence before it ships.

Verifies Data + AI code independently
Research themes

Where we focus

Verification systems

How multiple models, deterministic checks, context, and structured evidence can produce more dependable judgments than a single-pass review.

Evaluation and evidence

How teams can define what should be true, collect the results of existing tests and harnesses, and determine whether those results support a change.

Agentic Data + AI development

How coding agents can work with explicit intent, constraints, system context, and independent verification.

Feedback and improvement

How accepted findings, rejected findings, fixes, production outcomes, and practitioner feedback can improve future verification.

Articles