Skip to main content
Use cases

What teams build with AgentBundle.

Real patterns where one person on the team builds an agent and the whole org uses it. The marketing lead writes a brand voice agent; engineers, sales, and support all run outbound through it. The customer-success lead writes a triage agent; engineering bug-triage, product, and marketing all consume the same classification.

What these examples have in common

Every story below follows the same three steps. The agents differ; the shape doesn’t.

  1. One person who knows the work. The founder, head of marketing, customer-success lead, HR partner — whoever owns the canonical playbook today. They click New Agent in the dashboard, pick a starting template (or start from scratch). No engineer in the loop.
  2. The documents that already guide the work go in. The brand guide, the qualification rubric, the handbook, the classification taxonomy — the same docs that today live in a Notion page nobody reads. The agent references them through MCP connections, so it stays current as the docs change.
  3. One reviewer signs off, the whole team installs it. Each teammate installs into whichever runtime they already use — Claude Code, Cursor, Copilot, OpenCode, Gemini, Codex, Windsurf, or the AgentBundle dashboard. When the original author updates the canonical, every team’s next invocation picks up the new version on next sync.

Every use case assumes the governance to back it — N-required reviewers on the canonical version, an audit trail across every change, and policy that travels with the agent. See /security for the governance surface and /pricing for the reviewer-workflow features available on Business and above.

More use cases land as they ship. → /blog for product writeups.

Pick one. Build it. Hand it to your team.

Same flow whether your team is three people or thirty.

Free for teams up to 5. No credit card.

Copied to clipboard