I wrote a profiling tool for agentsWhile building an agent for a client, we hit a scaling problem: a coordinator agent had 4-5 subagents each with 15-20 tool calls. Each tool result got appended to the context, then what started as a r2 min read·engineering.fractional.aiApr 9
Tiny OCR0.9B parameter model running on CPU matched a 50¢/M token cloud API3 min read·engineering.fractional.aiFeb 11
On the new larger context windowsToday the latest LLMs have large context windows up to ~1 million tokens. There are many occasions when this larger context window can be useful: Context engineering: injecting rich system/user conte2 min read·engineering.fractional.aiNov 4, 2025
Let computers talk to computersOlder computer systems required humans to adapt their behavior to computers. Instead of describing news articles you were interested in, to search a news index you might have to write Boolean keyword4 min read·engineering.fractional.aiApr 2, 2025
Using historical codebase to build an eval suiteHow thousands of pull requests let Fractional automate annotating a ground truth set for a new product.3 min read·engineering.fractional.aiNov 11, 2024