Explains why Claude performs well on long agent tasks and when multiple agents on one problem beat a single one. Helps decide when to use multi-agent designs.
Key takeaways · AI-distilled
Erik says 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 now beat fixed workflows when quality matters most, while workflows still suit low-latency single-shot answers. He describes workflows of agents, where each step, such as writing a SQL query, loops until the output is right.
Erik explains that to Claude a multi-agentUsing several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.Full definition → looks like a tool it passes a prompt to. Subagents shield the main context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → from token-heavy subtasks, but Claude makes first-time-manager mistakes like unclear instructions and grows more detailed with training.
Erik reports that customers with 100 or 200 tools found it works well to split them among subagents, so the main agent only picks a bucket of tools and each subagent needs to understand maybe 20.
Erik argues tools and MCP servers should map to your UI, not your API. If Slack is exposed as separate endpoints for messages, user IDs and channel IDs, the model needs three calls to understand anything; one tool should present it all at once.
Erik warns that overbuilt multi-agent systems can spend too much time talking to each other instead of making progress. He advises starting simple, adding complexity only as needed, and remembering the model sees only what you showed it.
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.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
test-time compute — Spending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
