#context-engineering

AI & Machine Learning

Building a multi-agent market research assistant: context isolation, scratch files and cost caps

Aarav Mehta · Oct 3, 2026 · 7 min read

We built an internal assistant that researches crypto markets and drafts a briefing for analysts, using a planner and specialised sub-agents. The lessons: isolating sub-agent context, a file scratchpad instead of one huge conversation, cost and tool caps, and evals. It does research, never trading.

AI & Machine Learning

Giving an AI assistant memory of user preferences without breaking context or trust

Aarav Mehta · Jun 13, 2026 · 7 min read

Users of our internal assistant kept repeating the same preferences: their team, report format, time zone. Adding memory sounds simple and is not. How we separated short-term and long-term memory, decided what to store, handled conflicts and stale facts, and gave users control over what the assistant remembers.