"I've been working on internal "AI" adoption, which is really LLM-tooling and agent adoption, for the past 18 months or so. This is a problem that I think is, at minimum, a side-quest for every engineering leader in the current era. Given the sheer number of folks working on this problem within their own company, I wanted to write up my "working notes" of what I've learned. This isn't a recommendation about what you should do, merely a recap of how I've approached the problem thus far, and what I've learned through ongoing iteration."
"As technologists, I think one of the basics we owe our teams is spending time working directly with new tools to develop an intuition for how they do, and don't work. AI adoption is no different. Towards that end, I started with a bit of reading, especially Chip Huyen's AI Engineering, and then dove in a handful of bounded projects: building my rudimentary own agent platform using Claude code for implementation, creating a trivial MCP for searching my blog posts, and an agent to comment on Notion documents. Each of these projects was two to ten hours, and extremely clarifying."
Successful internal AI adoption requires hands-on experimentation to build intuition about the strengths and limits of LLMs and agents. Short, bounded projects such as simple agent platforms, MCP search, and document-commenting agents reveal practical trade-offs quickly. Adoption work involves iterating on developer tooling, integrations, observability, reliability, and formatting edge-cases to produce reliable outputs. Hiring product-oriented engineers with agent experience accelerates adoption. The process balances infrastructure, safety, and incremental productization to move experiments into dependable internal tooling that teams can use effectively.
Read at Lethain
Unable to calculate read time
Collection
[
|
...
]