Sign InOpen Brain
Atlas / Context

Prompting

Open JSONConfidence: Auto-collectedLast updated 2026-09-14

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

Loophole: Adversarial Agents To Stress Test Your Morality — Brendan Rappazzo, Morgan Stanley
AI Engineer · 2026-09-14

Loophole turns a natural-language policy into rules, then uses adversarial agents to find forbidden allowances and wrongful refusals. It is a useful pattern for testing agent constitutions.

The Rise of Verbal Reinforcement Learning
arXiv · 2026-09-01

This survey separates verbal feedback by when it acts and what it changes, helping agent builders distinguish task specification, test-time guidance, and parameter updates.

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes
arXiv · 2026-08-27

CritICL turns recurring failures from smaller models into critique examples for stronger models, aiming to improve inference with fewer generations and lower token cost than repeated sampling.

An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis
arXiv · 2026-08-07

Controlled LLM rewriting made harder financial sentences cheaper to process with DisCoCat, cutting circuit size by over 70%, but downstream accuracy improved only modestly.

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
arXiv · 2026-07-30

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.

Persona Engineering: A Field Guide to AI Synthetic Personas — Ishan Anand, InsightSciences.ai
AI Engineer · 2026-07-29

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.

How Evals and Prompts Shape Agent Behavior — Preetika Bhateja & Daniel Bump, YouTube Ads
AI Engineer · 2026-07-24

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.

The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest & Isaac Miller
AI Engineer · 2026-07-23

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.

asgeirtj/system_prompts_leaks
GitHub

A maintained archive of 100+ products’ system prompts exposes how coding-agent vendors structure tools, skills, memory, safety, and behavior—useful reference material for harness design.

How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?

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.

Direct agents with visual prompts in Design Mode

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.

ayghri/i-have-adhd
GitHub

i-have-adhd is a coding-agent skill that enforces action-first, compact responses with numbered steps and a concrete next action. It is a useful prompt-policy example for reducing agent verbosity.

Stable permalink · evidence auto-collected from source labels · synthesis maintained by feed7 editorial