2 tagged hubspot, measured the same way as everything else here.
Agent Claude Code
Fills the generation-request result files for exactly ONE demo-world opportunity. Give it the request directory and the artifact list; it writes results/ .md|.json. Use one opp-filler per opportunity, never batch deals.
Agent Claude Code
Principal-engineer-level adversarial reviewer for this repo's diffs. Use before opening a PR. Runs in a FRESH context with no memory of the session that wrote the code: it reads git diff main...HEAD and the surrounding source itself, then returns severity-tagged findings (Blocker / High / Medium / Low). Invoke when…