Forward-deployed
/
Learning zone
☰
← All courses
Harness engineering
← Track overview
Phase 00 — Setup & tooling
Phase 01 — LLM I/O foundations
Phase 02 — The agent loop
Phase 03 — Tool engineering
Phase 04 — Context engineering
Phase 05 — Prompt & instruction architecture
Phase 06 — File & code operations
Phase 07 — Shell & sandbox execution
Phase 08 — Permissions & safety gating
Phase 09 — Memory & persistence
Phase 10 — Subagents & orchestration
Phase 11 — Planning & task management
Phase 12 — MCP & extensibility
Phase 13 — Retrieval & codebase understanding
Phase 14 — Reliability engineering
Phase 15 — Evals & testing the harness
Phase 16 — Observability & cost
Phase 17 — Security & alignment
Prompt injection from tool results & files
Treating model output as data, never control flow
Data exfiltration & egress guards
Secret redaction in context & logs
Multi-tenant isolation & cache contamination
Use it: a security-review skill
Phase 18 — Production & deployment
Phase 19 — Capstone: build your own coding agent
Loading…
← Previous
Data exfiltration & egress guards
Phase
Overview
Next →
Multi-tenant isolation & cache contamination
Font
Inter (Default)
✓
Tahoma
✓
Arial
✓
Verdana
✓
Helvetica
✓
Size
A
100%
A
Margins
▮
▬
▭
Reset to defaults
Aa
Forward-deployed
/
Learning zone