[research@ai4se] : ~ $
cd ../
[process] | | 9 min

# Designing Human-Agent Collaboration Workflows: Research → Plan → Execute → Review → Ship

AI4SE process design isn't about inserting AI into an old pipeline — it's about redesigning the end-to-end workflow around 'who makes which decisions, and what the agent executes.'

[workflow-design][process]

The AI4SE Evolution of Classic Workflows

Traditional software engineering processes are designed human-first. The core question in the AI4SE era is: who leads each step?

StepPrimary roleAgent’s roleKey decision point
ResearchHuman + AgentExplore, search, draftDirection confirmation
PlanHuman-ledGenerate solution optionsSpec sign-off
ExecuteAgentSandboxed executionRisk routing
ReviewHuman + independent EvaluatorCannot self-assessQuality gate
ShipHuman accountableAutomated deploymentMerge approval

Three Principles for Process Design

  1. The decision-maker doesn’t execute: the person who writes the spec doesn’t review the code produced against that same spec
  2. Risk routing: low-risk actions are agent-autonomous, high-risk actions require HITL
  3. Complete evidence chain: the Spec, Diff, and Log produced at every step form an auditable record

Anti-Patterns

  • Treating the agent as a search engine — only asking, never changing anything
  • Skipping review and merging directly — amplifies the agent’s blind spots
  • Requiring human approval at every step — process cost eats away AI’s efficiency gains