480+ Blueprints, ready to build.

The first step is always the hardest. Search or browse to kick-start your next flow.

17 AI

AI Business Cloud Core Data Infrastructure

50 Blueprints

Sort by:

AI ServiceNow Incident Triage with RAG

Fetch the latest ServiceNow incident, generate RAG-grounded triage steps with Gemini, and write the proposal back to the incident.

AI Slack Chatbot with Per-User Conversation Memory Using OpenAI and KV Store

A stateful Slack AI chatbot that remembers each user's conversation across messages using OpenAI GPT-4o-mini and the Kestra KV store.

AI Starship Recommender with Conditional Prompts

Branch an AI prompt on a user-selected priority with Pebble conditionals and get a schema-enforced starship recommendation from SWAPI data.

AI-Powered Stock Watchlist Analysis with Daily Alerts and PostgreSQL Logging

Fetch a stock watchlist from Yahoo Finance, compute momentum and RSI, score it with OpenAI GPT-4o, log signals to PostgreSQL, and alert Slack daily.

Batch-Enrich BigQuery Rows with Vertex AI

Scheduled BigQuery row enrichment with a Gemini model on Vertex AI, with concurrency control, write-back, and email alerts.

Batch-Moderate Customer Reviews with Gemini at Controlled Throughput

Fan out a nightly review queue to Gemini for toxicity and spam classification, write each verdict back, and cap concurrency so the batch never exceeds your API quota.

Build a Chat-With-Your-Data System Using Elasticsearch and OpenAI (RAG)

Build a RAG chat-with-your-data flow that retrieves answers from Elasticsearch and generates grounded responses with OpenAI.

Build a RAG Pipeline Ingest Documents and Answer Questions Using OpenAI

Ingest documents into a vector store and answer questions grounded in retrieved content with a Kestra-native RAG pipeline on OpenAI.

Classify and Route Events with Vertex AI

Classify each Pub/Sub event with a Gemini model on Vertex AI, then escalate only the high-priority ones to BigQuery and Discord.

Create an image using OpenAI's DALL-E

Generate an image from a text prompt with OpenAI DALL-E and download it from the execution outputs.

Explain Workflow Failures with OpenAI and Send Insights to Slack

When a task fails, OpenAI explains the error in plain English and posts it to Slack so engineers fix issues faster.

Extract Structured Expense Data from Receipt Images with Gemini Multimodal

Watch an S3 inbox for receipt photos, describe each one with Gemini's multimodal model, reshape the description into typed JSON, and post the result to Google Chat.

Extract, Transform, and Store HackerNews Top Stories with AI-Generated Daily Digest

Fetch trending HackerNews stories, store them in PostgreSQL, generate an AI trend digest with OpenAI, and post a daily briefing to Slack.

Generate an SEO summary of an article using HTTP REST API and OpenAI plugins

Fetch any article by URL and generate an SEO-optimized summary with OpenAI, fully orchestrated in Kestra.

Generate and Deliver an AI-Powered Daily News Digest from RSS Feeds via Slack and Email

Aggregate RSS feeds, summarize the last 48 hours with OpenAI GPT-4o-mini, and deliver an AI-curated daily digest to Slack and email on a schedule.

Generate and Execute SQL Queries from Natural Language Using OpenAI GPT-4o

Turn plain-English questions into PostgreSQL queries with OpenAI GPT-4o, grounded on schema only so no row data ever leaves your database.

Keep Gemini Classification Running Through a Model Outage With Retry and Fallback

Retry a Gemini call for transient noise, then fall back across three model versions on a sustained 503, with concurrency control and a Slack heads-up whenever the fallback chain fires.

Kubernetes AI-powered incident monitoring, analysis, and alerting

AI-powered Kubernetes incident monitor that collects cluster data, diagnoses issues with Gemini, and alerts Slack on high severity.

Nightly RAG Ingestion Pipeline with Google Gemini

Refresh a RAG knowledge base every night by fetching URLs, chunking content, and indexing Google Gemini embeddings into a vector store.

Nightly RAG Ingestion with Gemini Embeddings

Re-ingest documents nightly, embed them with Gemini, and store the vectors so a RAG app retrieves grounded context.

Reduce LLM API Costs with a Redis Semantic Cache for Repeated Questions

Cache LLM answers in Redis so repeated questions are served instantly and OpenAI is only called on a genuine cache miss.

Summarize Weekly Git Commits with AI and Send a Development Report to Slack

Turn a week of Git commits into a plain-text development update with OpenAI and post it to Slack every Friday.

Turn an Apify web crawl into a fresh RAG vector index

Crawl a site with Apify's Website Content Crawler, embed the cleaned content into a vector store, and answer questions grounded in the freshly scraped data.

Use HuggingFace Inference API to classify customer message

Classify customer messages with the HuggingFace Inference API and write the predicted category back to Postgres.