core practice · coding problem
Cap agent tool loop
Agent calls tools in a loop. Max 5 steps, same tool 2× in a row triggers stop. Steps: search, search, calc, search, search, calc. When stop?
The mechanism
An agent is a loop: the model proposes an action, a tool executes it, the observation re-enters context, repeat until done. The engineering is in the guardrails — step limits, memory, and human approval — not the prompt.
Expected evidence
Stop at step 3 (duplicate search) or step 5 by max steps — implement both guards.
Try this drill in the practice workspace →
Hints when you need them
- Infinite loops burn tokens.
- Log each tool call.
Watch for these mistakes
- No step limit, so the loop runs away
- Letting context grow unbounded across iterations
- No human approval gate for irreversible actions