The context engineering playbook: which lever, in what order, and what each is worth
Five levers, one deployment order: which context feature to reach for by symptom, what each does to your cache and your bill, and one config that runs them all.
3 posts tagged "tool-use".
Every post tagged "tool use" in the journal. Tag archives are auto-generated from post frontmatter -- one entry per unique tag across non-draft posts. Currently 3 posts share this tag. Use the category filter above to scope by editorial type.
Five levers, one deployment order: which context feature to reach for by symptom, what each does to your cache and your bill, and one config that runs them all.
Showing 2 of 3 posts — page 1 of 1
Five MCP servers burn ~55k tokens before you ask anything. Tool search and programmatic tool calling (both now GA) cut that 85%+ — with one caveat that bites.
Anthropic's context editing clears stale tool results from an agent's window, cutting token use up to 84%. How it works, the config, and the prompt-cache catch.