Mitchell Hashimoto’s new way of writing code

2026-02-12 · Source: The Pragmatic Engineer · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Intermediate, medium

Summary

This episode features an interview with Mitchell Hashimoto, co-founder of HashiCorp and creator of Ghostty, discussing his journey in software engineering and the evolution of HashiCorp. He recounts how Vagrant originated from a need to streamline development environment setups and how Terraform, despite being seventh to market, succeeded through community building and superior developer experience. Hashimoto also shares HashiCorp's early struggles, including a four-year period without a viable business model and the failure of their first commercial product, Atlas, before pivoting to selling individual services like Vault. He reveals a near-acquisition by VMware for $20M, which was rejected at $100M, and details his current workflow, which heavily integrates AI agents for research and task planning, fundamentally changing his approach to software development and open source contributions.

Key takeaway

For infrastructure engineers and founders navigating the AI-native era, consider adopting AI agents to offload research and planning tasks. This shift can significantly alter your daily workflow, allowing you to focus on core development while agents handle background analysis. Be prepared for potential changes in open source collaboration and version control systems like Git, as AI-driven contributions increase churn and necessitate new approaches to managing codebases.

Key insights

AI agents are transforming software development workflows and challenging traditional open source and version control paradigms.

Principles

• Developer experience drives market adoption.
• Pivoting business models can lead to success.
• AI agents enable parallel work streams.

Method

Integrate AI agents into daily workflow for background tasks like research, edge-case analysis, and library comparisons, allowing engineers to focus on coding and reviewing.

In practice

• Use AI agents for research before coding.
• Delegate library comparisons to AI.
• Explore AI for edge-case analysis.

Topics

• AI Agents
• Open-Source Software
• Infrastructure-as-Code
• Version Control Systems
• Software Engineering Workflow

Code references

• steveyegge/gastown

Best for: Machine Learning Engineer, NLP Engineer, Software Engineer, AI Engineer, Entrepreneur

Related on AIssential

• I don't have time to build these things, will you? — AI agents enable tackling ambitious, foundational software problems previously deemed too complex or expensive.
• The Rise of Cloud Coding Agents — Cloud-based AI coding agents enable asynchronous, autonomous development workflows, enhancing scalability over traditional desktop agents.
• AI plumbing, open source, and weekly readings! 💡 — Hybrid AI architectures and AI's impact on open source redefine engineering workflows and community dynamics.
• From IDEs to AI Agents with Steve Yegge — AI is fundamentally reshaping software engineering, shifting focus from manual coding to agent orchestration and rapid prototyping.
• How frontier teams are reinventing AI-native development — AI-native development, by restructuring workflows around agents and providing rich context, dramatically boosts software delivery.
• AI agents are your new colleagues - how to get the best results — AI agents are transforming workplaces by automating routine tasks, enabling human colleagues to focus on strategic, higher-value work.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Pragmatic Engineer.