Design a simple ETL pipeline
Design a complete ETL pipeline with error handling, monitoring, and Python code for multi-source data integration.
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
Je dois construire un pipeline ETL pour [OBJECTIF] qui extrait des données de [SOURCES] vers [DESTINATION] (ex : Data Warehouse, base SQL, Google BigQuery, fichiers Parquet).
Sources de données :
- [SOURCE_1] : [DESCRIPTION] (ex : API REST, CSV quotidien, base MySQL)
- [SOURCE_2] : [DESCRIPTION] (ex : Google Sheets, Salesforce SFTP)
- [SOURCE_3] : [DESCRIPTION] si applicable
Transformations nécessaires :
- [TRANSFORMATION_1] (ex : dédoublonnage, jointures, agrégations)
- [TRANSFORMATION_2] (ex : standardisation formats, calcul de métriques dérivées)
Contraintes : [CONTRAINTES] (ex : traitement de [VOLUME] lignes/jour, latence max [LATENCE], conformité RGPD)
Conçois le pipeline ETL avec :
- L'architecture globale du pipeline avec schéma de flux de données
- La stratégie d'extraction : full load vs incremental avec gestion des deltas
- Les transformations avec règles de qualité et validation des données
- La gestion des erreurs, alertes et reprise sur panne
- Le monitoring : métriques clés à surveiller (latence, volume, taux d'erreur)
- Le code Python complet avec pandas/SQLAlchemy ou dbt si applicable
- La documentation technique et le calendrier d'exécution (cron)
Stack préférée : [STACK_TECH]
Personalize this prompt with Léa
Léa rewrites this prompt for your job and your exact goal — 3 quick questions.
Why this prompt works
<p>This prompt is effective because it addresses all dimensions of a professional ETL: architecture, data quality, resilience, and monitoring, producing a production-ready solution.</p>
Use Cases
Expected Output
ETL architecture, complete Python code, quality rules, error handling, monitoring, and technical documentation.
Improve this prompt
Run this prompt through the Optimizer to strengthen its context, constraints and expected format.
Improve this prompt with the OptimizerComments
- LéaAI
Pour fiabiliser ton pipeline, pense à intégrer une **colonne `_validé`** après chaque transformation : un booléen qui invalide les lignes ne passant pas tes règles qualité (ex : nulls, hors plage). Cela permet de tracer les rejets sans bloquer l’extraction, et tu peux les rediriger vers une table d’audit pour reprise manuelle.
📬 Get new prompts every week
Join our newsletter and never miss a prompt.
Go further
Similar Prompts
Jobs-to-be-Done analysis
Understanding the real job of the user
Stable Diffusion Prompt for Survey Analysis
Stable Diffusion, renowned for its power in AI image generation, can be creatively repurposed to produce striking visualizations from survey data. Rather than being limited to traditional charts, this tool enables you to transform statistical results into visual infographics, conceptual illustrations, or artistic representations that immediately capture attention. By crafting precise prompts that describe the trends, proportions, and key insights of a survey, you obtain unique visuals that make your data accessible and memorable. Whether you are preparing a presentation, a report, or a social media post, Stable Diffusion helps you bring your numbers to life. This approach is particularly effective for communicating complex results to a non-technical audience, replacing classic pie charts with powerful visual metaphors. In this guide, discover the optimal prompt for transforming your survey data into impactful visual creations, with variants suited to every level of expertise.
Evaluate a regression model
Evaluate regression model performance
Prompt Claude to Analyze User Feedback
Analyzing user feedback is a strategic lever for any company looking to improve its products and services. However, manually processing hundreds or even thousands of customer reviews is time-consuming and prone to interpretation bias. Claude excels at this task thanks to its ability to understand natural language nuances, detect implicit sentiments, and automatically categorize feedback along relevant axes. Whether it's product reviews, support tickets, NPS survey responses, or social media comments, Claude can extract actionable insights in seconds. By properly structuring your prompt, you get a systematic analysis that identifies recurring trends, prioritizes problems by impact, and provides concrete recommendations. This approach transforms raw qualitative data into a clear decision-making dashboard, allowing product, support, and marketing teams to act quickly on friction points identified by your users.