AI agents
If the job involves working with a coding agent, you can screen for it. Candidates run Claude Code or Codex in their sandbox terminal on your organization's keys, behind Kendor's gateway, or bring their own account and pick from seven agents, including Antigravity, GitHub Copilot, Cline, OpenCode and Cursor. Reviewers see the conversation afterwards. These articles cover switching the agents on, connecting your keys and capping how many tokens they can spend.
How to let candidates use Claude Code or CodexSwitch on AI assistants in the terminal for a coding screen or a live coding interview. On your keys candidates run Claude Code or Codex; on their own account, any of seven agents.Connect your Anthropic and OpenAI keys for AI agentsOwners add an Anthropic key for Claude Code and an OpenAI key for Codex under Integrations. Keys are encrypted and never enter a candidate's sandbox.Set token budgets for AI agentsCap what Claude Code and Codex can spend with a token budget per candidate on each screen and a monthly token cap for the whole organization.