Overview
News
Technologies
Salaries
Products
People
Growth
Financials
Overview
Krv evaluates AI agents and produces evidence packages that justify their behavior and expose uncertainty — so you can deploy safe, compliant agentic systems. We inspect the data (Pulsar), models (Pasteur), and code (Topos) behind every decision, not just inputs and outputs.
News
Introducing Topos: Quality is the New Currency
Correctness is table stakes. Topos evaluates the structural quality of agent-written code so working diffs do not become long-term codebase debt.
Read more
Report
Strategies to accelerate US coal power phase-out using contextual retirement vulnerabilities
Strategically planning the phase-out of coal power is critical to achieve climate targets, yet current approaches often fail to account for the context-specific barriers and vulnerabilities to retirement. Here we introduce a framework that combines graph
Read more
Report