From coding to Knowledge work agents — Karan Vaidya, Composio
Knowledge-work agents need code-like infrastructure around tools: centralized context, action records, verification, enforced permissions, and preflight checks for irreversible work.
Composio attributes coding agents’ reliability to surrounding infrastructure: repositories centralize truth, history records work, and tests verify output. It proposes **six primitives** for knowledge work, including context, governance, and reversibility, where information and actions span many applications.
Treat prompts as guidance, not containment. Put permissions outside the model, log each tool action, test destructive operations against mocked tools, and require review before irreversible effects. The talk cites an outreach agent that sent mass email as instructed but without an adequate preflight check.
Composio attributes coding agents’ reliability to surrounding infrastructure: repositories centralize truth, history records work, and tests verify output. It proposes **six primitives** for knowledge work, including context, governance, and reversibility, where information and actions span many applications. Treat prompts as guidance, not containment. Put permissions outside the model, log each tool action, test destructive operations against mocked tools, and require review before irreversible effects. The talk cites an outreach agent that sent mass email as instructed but without an adequate preflight check. True undo is unavailable for actions such as sent messages or hard deletes. For those cases, **sandbox before production** is the proposed substitute, but the talk provides no measured error reduction and natural-language policies still need validation.
This broadens the coding-agent harness pattern into a six-part foundation for knowledge work across applications. It confirms that permissions, logging, review, and preflight checks must sit outside prompts, while narrowing “undo” to sandboxed rehearsal for irreversible actions. The lack of measured error reduction leaves the framework operationally plausible but not quantitatively validated.