Claude Sonnet 5 is Anthropic's newest mid-tier model aimed at agentic coding workloads, making it the likely new default for coding agents and IDE tooling that currently pin an older Sonnet. If you run AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → loops at volume, the Sonnet tier is where price-to-capability decisions get made, so a step change here directly affects your agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → and cost model.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
