Jonathon's AI Wiki
Search
Search
Dark mode
Light mode
Explorer
system-prompt
5 items with this tag.
Aug 11, 2026
Refusal Calibration and Constitutional AI — Shaping Claude's Refusals Without Raising Jailbreak Risk
constitutional-ai
claudes-constitution
refusals
over-refusal
jailbreak
safety
system-prompt
anthropic
Aug 05, 2026
The New Rules of Context Engineering for Claude 5 Models (Thariq Shihipar, Anthropic)
claude-ai
anthropic
context-engineering
claude-md
skills
system-prompt
progressive-disclosure
tool-design
auto-memory
doctor-command
first-party
thariq-shihipar
opus-5
fable-5
Jul 16, 2026
Steering Claude Code: When to Use CLAUDE.md, Rules, Skills, Subagents, and Hooks
claude-code
claude-md
rules
skills
subagents
hooks
output-styles
system-prompt
decision-guide
first-party
michael-segner
Jul 16, 2026
Prompt Engineering Trade-offs: Caching, Thinking, Structured Output, and Message Placement
prompt-caching
extended-thinking
structured-output
system-prompt
rag
decision-framework
Jul 03, 2026
Hardening an Agentic Prompt — the Technique Layer and the Harness Layer
prompt-injection
jailbreak
agent-security
guardrails
refusal-calibration
least-agency
defense-in-depth
system-prompt
connection