What counts as evidence: grading the output of a tool-using agent
A pattern for AI agents: make findings the unit of output, gate top-severity claims on objective evidence, and require cross-source corroboration.
Andrey Shamakhov
CTO, co-founder
15 years scaling full-stack architecture and leading monitoring teams, combining deep distributed systems experience with an AI research background.
Articles by Andrey Shamakhov
Tree-search agents: building an AI agent that survives a wrong first guess
Design notes from an incident investigation agent: a tree of hypotheses, specialized subagents, evidence-scored evaluation, and bounded search.