Tag
An exploration of strategies and techniques used to manage and reduce costs for long-running AI agent deployments.
The author shares insights on building AI agents for small businesses, emphasizing that the hardest part is selecting the right task to automate, not the agent itself. Key considerations include volume, input structure, cost of errors, and existence of manual processes.
The article discusses essential ebike accessories for hauling cargo, sharing personal experience with a Radwagon 4 and recommending products like front baskets, rear seats, and safety lights.
The author shares their three-year experience of feeding PDFs to AI, pointing out that Markdown is a better input format for AI than PDF, because PDF is essentially a mix of coordinates and characters. AI needs to parse the structure first, which is error-prone and consumes more tokens. The article provides specific cases and recommended tools (markitdown, pandoc, LlamaParse), and teases a new series called 'The Art of Feeding AI'.