This is the first time I’ve onboarded at a company while modern LLM capabilities are readily available. The experience has been different, and better.

I joined Buffer, an async-first, remote company that builds tools to help creators and businesses manage their social media. The team has been excellent at providing guidance, context, and everything needed for a smooth onboarding. But when it comes to engineering, some things are best learned by doing, getting your hands dirty with the actual work.

AI tools have made it easier than ever to start contributing. Not just for implementation, but for building context and understanding what’s happening in the codebase.

Research and Understanding

The real value isn’t in rushing toward a solution. It’s in using AI to thoughtfully understand the codebase. When I encounter unfamiliar patterns or architecture decisions, I ask questions that help me learn the “why” behind the code, not just the “what.”

GitHub, Linear, and Notion agents have been particularly useful here. Instead of spending hours searching through repos and docs, I get pointed in the right direction quickly, then dive deeper.

This extends beyond the codebase too. When I need to understand company-specific workflows and practices, how we handle retrieval, storage, validation, that sort of thing, I point AI to our documentation and have it research how things work internally. Then I can propose solutions that follow our established patterns rather than starting from scratch.

Getting Unblocked

Local setup issues are common when joining a new codebase. AI has been great at understanding error messages, suggesting fixes, and helping me get unblocked without waiting for someone else to be available. In an async environment, immediate help isn’t always possible.

Plan mode has been useful here too. Before committing to a solution, I explore multiple approaches, weigh trade-offs, and make more informed decisions. I don’t just follow what AI suggests. I use my own engineering experience to evaluate what it proposes and decide what makes sense.

The Balance

It’s tempting to work in a silo when you can unblock yourself more easily. But that misses the point. I still reach out to teammates, ask questions, and pair on complex problems. I come to those conversations better prepared, with more context, with specific questions rather than broad confusion.

Onboarding with AI tools available has been smoother. I can ramp up faster, understand the codebase more quickly, and get unblocked more easily. The tools help me contribute sooner while still building the relationships that make remote, async work successful.

Have you onboarded at a company recently? What interesting ways have you used AI during onboarding? I’d love to hear your thoughts and experiences.