Curioprompt
Add Explore New Best

Prompt Cards

Truthfulness & Citation Policy for Research Outputs
Create a truthfulness policy: source requirements, citation rules, and how to label speculation. Provide a checklist for editors/analysts and an automated linting concept.
Tags: truthfulness, citations, policy, research, safety
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Uncertainty Calibration: When to Say ‘I’m Not Sure’
Design a calibration approach: confidence estimation, abstention policies, escalation to human, and how to test calibration. Include UI patterns that communicate uncertainty responsibly.
Tags: uncertainty, calibration, abstention, HITL, UX
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Metrics That Matter: Safety + Utility Balanced Scorecard
Create a balanced scorecard: utility metrics (task success), safety metrics (policy adherence), reliability (latency, uptime), and user trust (complaints). Include leading indicators and dashboards.
Tags: metrics, scorecard, safety, utility, reliability, ops
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Eval Design: Avoiding Overfitting to the Test Suite
Design an evaluation strategy that avoids overfitting: holdouts, rotating test sets, adversarial sets, and blind evaluation. Include rules for when to refresh benchmarks.
Tags: evaluation, overfitting, benchmarks, holdout, testing
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Model Update Policy: When to Retrain vs Prompt-Tune
Create decision criteria for retraining vs prompt tuning vs retrieval updates. Include risk analysis, expected impact, validation requirements, and rollback strategies per approach.
Tags: retraining, prompting, RAG, model-updates, governance
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Secure-by-Default Tooling: Safe Defaults Checklist
Create a safe-defaults checklist for the tool layer: deny-by-default, explicit allowlists, safe parameter validation, output filtering, and timeouts. Include common failure modes.
Tags: secure-defaults, tooling, validation, timeouts, guardrails
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Tool Permission Model (Least Privilege)
Create a least-privilege permission model for tools: scopes, rate limits, time bounds, and audit logs. Provide an authorization matrix and guidelines for granting elevated access.
Tags: least-privilege, authorization, tools, audit, security
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Prompt Injection Defense Plan (Tool-Using Agents)
Design defenses against prompt injection for tool-using agents: content provenance, allowlists, tool policy, and sandboxing. Include a suite of adversarial prompts for regression testing.
Tags: prompt-injection, agents, tooling, security, testing
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
PII/Secrets Handling Policy for Recursive Pipelines
Create a policy and technical controls for PII/secrets: detection, redaction, encryption, and safe storage. Include test cases and a plan to prevent secret leakage into training/evals.
Tags: privacy, PII, secrets, redaction, security, safety
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Data Governance for Feedback Loops
Design data governance for user feedback and logs: consent, retention, minimization, access controls, and audit trails. Provide a policy and an implementation checklist.
Tags: data-governance, privacy, retention, audit, feedback-loops
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Canary Release Strategy for Model/Prompt Updates
Create a canary strategy: cohort selection, metrics, guardrails, and automatic rollback conditions. Include steps to prevent canary contamination and to interpret results statistically.
Tags: canary, experimentation, rollout, metrics, rollback
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View
Rollback & Kill Switch Design
Design a rollback system: model version pinning, feature flags, staged rollouts, and a kill switch. Include operational procedures and testing for rollback reliability.
Tags: rollback, kill-switch, feature-flags, release-engineering, safety
Author: Assistant
Created at: 2026-02-02 00:00:00
Average Rating:
Total Ratings:
View

Curio AI Brain

Available in Chrome Web Store!