Software Engineering

Automating terminal-based development workflows with AI agents

The author uses a custom CLI plugin with skills, commands, and sub-agents to automate repeatable software development steps such as investigation, planning, implementation, verification, and pull request preparation directly inside a terminal-first workflow.

Why the human is still essential here

The agent handles structured execution of repeatable steps, but the developer still defines the workflow, chooses when to trigger it, reviews outputs, and refines the implementation.

How people use this

Terminal bug investigation agent

An AI agent runs repo-aware terminal commands to inspect logs, search code paths, and summarize likely root causes before the developer starts fixing the issue.

Claude Code / OpenAI Codex CLI

Worktree-scoped implementation runbook

A saved agent workflow creates a plan, edits files, runs commands, and stages changes inside the correct branch or worktree for a specific task.

Claude Code / Aider

CLI pull request drafting

After changes are complete, the agent summarizes the diff, gathers verification output, and drafts a pull request description directly from the terminal session.

GitHub Copilot / Claude Code

Need Help Implementing AI in Your Organization?

I help companies navigate AI adoption -- from strategy to production. Whether you are building your first LLM-powered feature or scaling an agentic system, I can help you get it right.

LLM Orchestration

Design and build LLM-powered products and agentic systems

AI Strategy

Go from idea to production with a clear implementation roadmap

Compliance & Safety

Build AI with human-in-the-loop in regulated environments

Related Prompts (4)

Latest community stories (1)

Blog

How I went AI-native in my terminal workflow

Every developer has a workflow they've spent years refining.

Mine lives almost entirely in the terminal. I'm SSH'd into a development machine. I organize my sessions with tmux, edit code in Vim, and use git worktrees to juggle multiple tasks in parallel.


When people talk about AI-native development, the conversation sometimes assumes developers will converge on the same new workflow. A new IDE, a new interface, a new way of building software.

MP
Mark ParienteMember of Technical Staff
Mar 24, 2026