Agentic exploration
An agent with read, search and run tools investigates a change: follows a suspicion across files, runs code, and returns findings with evidence.
Sub-techniques
3
| ID | Name | Description |
|---|---|---|
V1034.001 | Breadth survey | A first pass that lists concerns across the whole diff. |
V1034.002 | Deep exploration | Focused sub-agents that investigate one concern each. |
V1034.003 | Tiered depth | Route small or low-risk changes to a shallow pass and risky ones to deep exploration. |
Craft it
- Give the agent read-only tools first: read file, grep, list directory.
- Split into a survey step and per-concern investigation steps.
- Require each finding to cite file, line and the evidence that supports it.
Reverse engineer it
Signs that a codebase already runs this technique, and where to read how it is configured.
- Agent configuration files (AGENTS.md, CLAUDE.md) and review bot comments that cite multiple files.