We’ve seen many companies stumble when rolling out AI coding assistants. Success depends on building knowledge, skills, and practical habits. We’re helping across all aspects of rolling out AI tools, but we have found one practice that accelerates proficiency:

2-week (10 work-day) AI Coding Tool Ramp-up Spike

Here’s how it works:

• 2 days of focused training
  • Day 1 (Fundamentals): Core patterns of AI-assisted development – How to write precise prompts, how to review AI results, and how to refine code without creating technical debt. Engineers leave with a systematic workflow rather than just ad-hoc examples.
  • Day 2 (Advanced): Context management, multi-file refactors, breaking down features into AI-manageable chunks, debugging AI outputs, rules, MCP servers/services. Exercises surface common failure modes, ensuring teams build the reflexes to reset context, enforce consistency, and debug AI outputs.
• 8 days of supported, hands-on ticket work
  • Developers pick up a variety of tickets and use the AI tool as part of getting the work done.
  • Task journaling — Each developer keeps a lightweight daily log of what worked and what didn’t, building a shared playbook.
  • Feedback loops: with AI champions — Daily check-ins with champions and facilitators and asynchronous support to help overcome early friction quickly and build skills quickly.

By the end of the two-week spike, engineers have built a foundation of habits, shared practices, and a clearer sense of where the tools genuinely improve code quality and developer experience. Leaders need to provide support for continued learning beyond this two-week period, but we’ve found this to be a critical first step.

Additional Reading:

• AI for Coding: Why Most Developers Are Getting It Wrong (And How to Get It Right)
• GitHub’s internal playbook for building an AI-powered workforce
• Training Developers on GitHub Copilot: Lessons Learned
• How to Lead a GitHub Copilot Rollout That Removes Blockers and Delivers Real Impact
• AI Code Generation: Best Practices for Enterprise Adoption in 2025

The conversation around AI coding assistants keeps speeding up, and we are hearing the following questions from technology leaders:

• Which flavor do we bet on—fully-agentic tools (Claude Code, Devin) or IDE plug-ins (Cursor, JetBrains AI Assistant, Copilot)?
• How do we evaluate these tools?
• How do we effectively roll out these tools?

At the top level, I think about:

• Agentic engines are happy running end-to-end loops: edit files, run tests, open pull requests. They’re great for plumbing work, bulk migrations, and onboarding new engineers to a massive repo.
• IDE assistants excel at tight feedback loops: completions, inline explanations, commit-message suggestions. They feel safer because they rarely touch the filesystem.

Here’s a pretty good roundup:

The Best AI Coding Tools, Workflows & LLMs for June 2025.

Most teams I work with end up running a hybrid—agents for the heavy lifting, IDE helpers for day-to-day quick work items.

Whichever path you take, the practices you use matter the most.

Some examples to get you started:

• Publish a living coding-guidelines file before you turn agents loose—JetBrains’ Junie team shows a good pattern.
  Coding Guidelines for Your AI Agents
• Keep the agent’s toolchain fast and observable; Armin Ronacher’s post explains why slow tests and verbose logs burn tokens and patience alike.
  Agentic Coding Recommendations
• Reset context often—Philipp Spiess’s rule of thumb is “/clear when you change topics.”
  How I Use Claude Code
• Pair early adopters with skeptics and share metrics (time-to-PR, diff size). Thomas Ptacek’s rant is the best antidote to “LLMs are a fad.”
  My AI Developer Skeptic Friends Are All Nuts

Reading list

• Why Developers Should Care about AI-Enabled Software Engineering – A breezy primer you can forward to any hold-outs who think AI is “just for AI people.”
• My AI Developer Skeptic Friends Are All Nuts – A punchy takedown of common objections and a reminder that agents ≠ copy-paste ChatGPT.
• How I Use Claude Code – Real-world workflow tips: when to “/clear,” how to fork threads, and a cheeky alias for yolo mode.
• Agentic Coding Recommendations – Armin Ronacher on keeping loops token-efficient and why Go beats Python for agents.
• How Anthropic Teams Use Claude Code (PDF) – Department-by-department case studies and a template for your own “Claude.md” grounding file.
• Coding Guidelines for Your AI Agents – How to bake language-specific dos & don’ts into a .junie/guidelines.md file so agents spit out idiomatic code.