Promptdoo is your platform for prompt engineering and AI workflow automation. Create better ChatGPT prompts, use our skills library and share your knowledge.
Passive voice audit: detect be-participle/get/concealed passives, evaluate agent suppression justification, rewrite flagged instances.
Passive voice suppresses the agent: who did what becomes invisible. This is appropriate when the agent is unknown or irrelevant ("The package was deli...
Power analysis: effect size, significance level, power, test type, design-adjusted sample size computation with attrition corrections.
A study with too few participants cannot detect a real effect: it is underpowered. A study with too many wastes resources and detects trivial effects ...
DI strategy comparison: constructor, setter, service locator with evaluation matrix and anti-pattern detection.
Dependency injection is the most misunderstood pattern in software engineering. Most teams use it because 'best practices' say so, without understandi...
Propensity score matching: logistic regression, nearest-neighbor matching, balance diagnostic, causal effect estimation with sensitivity.
Correlation is not causation, but sometimes you cannot run a randomized experiment. Propensity score matching (PSM) estimates causal effects from obse...
Rhetorical editing: anaphora, isocolon, tricolon applied to prose with before/after analysis.
Parallel structure is the single most reliable technique for making prose memorable. It exploits the brain's pattern-recognition system: when a reader...
Immutable infra: blue-green deploy, rollback strategy, artifact management, drift detection policy.
Mutable infrastructure is the root cause of configuration drift—every emergency SSH fix creates a server that cannot be reproduced. Immutable infrastr...
Prompt engineering puzzle: craft solutions from restricted vocabulary, scoring on precision and efficiency.
A game where you must craft a prompt that produces a specific output using only words from a restricted vocabulary. This tests prompt engineering fund...
Multi-arm bandit with Thompson Sampling: Beta-Bernoulli posteriors, regret minimization, convergence criteria.
A/B tests have a fixed hypothesis and duration. Multi-arm bandits continuously allocate traffic to better-performing variants, minimizing regret while...
Dead letter queue architecture: poison message handling, exponential backoff, consumer patterns, DLQ reprocessing.
Production message queues inevitably receive messages that cannot be processed. Without a dead letter queue (DLQ), these messages block the consumer, ...
Outside view calibration: reference class definition, distribution extraction, inside-to-outside estimate formula.
Inside view forecasting — estimating based on the specifics of your project — is systematically optimistic. Outside view asks: how did similar project...