Agentic Engineering

Human-Agent Collaboration Modes



layout: post
title: Human-Agent Collaboration Modes
date: ‘2026-08-24 12:00:00’
permalink: /en/agentic-engineering/human-agent-collaboration-modes/
categories:

  • Agentic Engineering
    tags:
  • collaboration
  • agents
    site_locale: en
    lang_switch: /agentic-engineering/human-agent-collaboration-modes/
    summary_en: >-
    Coding agents do not remove engineering judgment. They amplify it. The practical skill is knowing when to explore with
    an agent, when to turn intent into a spec, when to let the agent execute, and when to slow down for verification. The
    old question was whether you should “vibe code” or "spec…
    summary_zh: >-
    Coding agents do not remove engineering judgment. They amplify it. The practical skill is knowing when to explore with
    an agent, when to turn intent into a spec, when to let the agent execute, and when to slow down for verification. The
    old question was whether you should “vibe code” or "spec…
    topic_cluster: agentic-engineering
    confidentiality_safe: true
    series_id: agentic-engineering
    content_id: human-agent-collaboration-modes
    series_mode: link
    book_url: https://xinheliu.github.io/Coding-with-Agents/en/02-anatomy/human-agent-collaboration-modes.html
    canonical_url: ‘’

Coding agents do not remove engineering judgment. They amplify it. The practical skill is knowing when to explore with an agent, when to turn intent into a spec, when to let the agent execute, and when to slow down for verification. The old question was whether you should “vibe code” or "spec…

Read the full chapter in the book →


Author: Xinhe Liu
Reprint policy: All articles in this blog are used except for special statements CC BY 4.0 reprint policy. If reproduced, please indicate source Xinhe Liu !
  TOC