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 rApr 9 · 2 min readengineering.fractional.ai
Tiny OCRIn our paper reading group last month I presented DeepSeek’s Context Optical Compression paper which claimed amazing performance with a much smaller model (3 billion parameters) than the previous fronFeb 11 · 3 min readengineering.fractional.ai
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 conteNov 4, 2025 · 2 min readengineering.fractional.ai
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 keyword Apr 2, 2025 · 4 min readengineering.fractional.ai
Using historical codebase to build an eval suiteZapier has millions of users using thousands of integrations with different platforms. They’re constantly requesting new features they’d like to see, and Zapier has a team dedicated to identifying theNov 11, 2024 · 3 min readengineering.fractional.ai
