LLM Steering

Prompt engineering, agent loops, and model routing across three AI agent codebases.

Prompt assembly spectrum: brainpro (modular YAML + conditional filters) vs openclaw (monolithic static MD) vs ship (phase-injected) - trades assembly complexity for runtime flexibility
Doom loop prevention: brainpro hashes last 3 tool calls, returns error to LLM on repeat - lets model self-correct rather than killing execution
Workspace memory: .brainpro/ stores compacted transcripts (28KB→4KB) with semantic boundaries - enables resume/fork without bloating context
Model routing: brainpro auto-routes to model tier (haiku/sonnet) based on tool complexity scoring - optimizes cost without explicit selection
Multi-agent safety: openclaw uses prompt coordination, brainpro strips file paths, ship isolates via phases - different trust models