Prompting
Current Answer
No editorial synthesis yet — the evidence below is collected automatically from source labels. A current answer lands here once an editor approves one.
Evidence
AISPA turns system-prompt review into an eight-dimension audit. Its survey suggests builders should test prompts for user protection and conflicting instructions, not merely check that safeguards exist.
Synthetic personas can extend existing research, but they are forecasts, not extra respondents. Ground prompts richly and validate each setup against human data before using it.
Production agent behavior should be improved through a loop of tool design, small eval sets, trace review, and calibrated judges—not prompt tweaks based on one bad run.
DSPy separates an AI task’s contract from its model, prompt, tools, and harness, letting builders swap or optimize implementations while holding behavior against the same evals.
A RAG study finds that retrieved ideology carries into answers and varies with sampling temperature, so source audits and decoding tests should be evaluated together.
A maintained archive of extracted system prompts from 100+ AI products — Claude Fable 5, Claude Code, ChatGPT 5.5, Gemini, Cursor — useful for studying how vendors actually instruct their agents.
Cursor's Design Mode lets you prompt agents visually in a running app: click or multi-select elements, draw annotations on a frozen frame, or narrate by voice; the agent gets each element's xpath, props, and styles.