# From coding to Knowledge work agents — Karan Vaidya, Composio

Source: [AI Engineer](https://www.youtube.com/watch?v=xxfMT-bPEmU)  
Feed7 permalink: https://feed7.dev/p/from-coding-to-knowledge-work-agents-karan-vaidya-compos-74c257483c  
Published: 2026-09-03T00:00:00.000Z  
Trust: Source Linked (source_linked)

## Why Included

Keep permissions outside prompts, log tool actions, mock destructive operations, and require review before irreversible effects.

## Source Summary

Knowledge-work agents need code-like infrastructure around tools: centralized context, action records, verification, enforced permissions, and preflight checks for irreversible work.

## Practical Implication

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.

## Agent-Ready Context

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.

## Context Map

- Layer: agent
- Domains: coding, security
- Topics: harness-engineering, tool-use, agent-reliability

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.