Pre-built Templates
Jump-start your automation journey with prebuilt workflows for common use cases.
Getting Started
See moreYour first AI agent in ByteChef. The agent uses an OpenAI model and one tool, the HTTP Client, to fetch a random quote from a public API, then explains the quote in one sentence and logs the answer. It runs on a manual trigger, so after importing it you connect your OpenAI API key, click Run and watch the tool call in the execution log.
This workflow fetches an inspirational quote on weekdays, and a joke on the weekends and then sends it to the email address you specify.
New to ByteChef? This simple workflow is the perfect way to get started. In just a few minutes, you'll build your first automation: it fetches a random quote from the internet and logs it. It uses a manual trigger, so after importing it you click Run and see the result immediately. Swap in a Schedule trigger when you want it to run on its own.
AI
See moreA chat agent that helps a team plan upgrades. For questions about Java or Spring versions, release dates or features, it delegates to a remote agent over the Agent2Agent protocol with the A2A Agent Tool, then combines the answer with its own advice. Built to call the Java release expert template, but works with any A2A agent.
An AI agent that answers questions about Java and Spring release history: versions, release dates, headline features and migration notes. The workflow starts from a workflow call, so you can add it to a ByteChef A2A Server and other agents can delegate questions to it over the Agent2Agent protocol. Pair it with the Tech lead agent template.
Polls Gmail for new emails and uses OpenAI to classify each one into a single department label (Sales, Support, Finance, Operations, HR, or URGENT). The matching Gmail label is applied, the department's recipient address is stored, and the original email is forwarded to the correct team.
A chat agent with the Ask User Question tool. Before planning a team event, it asks three or four multiple-choice questions about budget, location, dates and activities. The run pauses until you answer in the chat, and then the agent writes a plan that fits your answers.
A chat agent with session-based Chat Memory v2. A small turn window keeps only the last few turns in the prompt and archives older ones, while conversation search lets the agent look up anything said earlier in the full log. A Claude Haiku model is attached for the Recursive summarization strategy, if you switch to it.
When a Google Forms response is submitted, downloads the attached CV PDF from Google Drive, extracts its text, and summarizes it with AI. OpenAI scores the candidate from 0 to 10 against a Senior Java Developer job description. The name, email, summary, and score are recorded in a Google Sheet, and the CV file is filed into a Rejected or Potential candidates Google Drive folder based on the score.
Support
See moreWhen a new HubSpot ticket is created, fetches the ticket and uses OpenAI to rewrite its content into a clear, structured format. OpenAI then categorizes the ticket as tech or customer support, and a condition routes a Slack notification with the rewritten ticket to either the tech-team or sales-team channel.
On every new Gmail message, checks whether it arrived within business hours (Mon-Fri, 09:00-17:00 UTC). For emails received outside working hours, OpenAI classifies the urgency, the email is logged to a Google Sheet, and a condition branches: urgent emails get an AI-summarized internal Slack alert plus an urgent auto-reply, while non-urgent emails get an AI-generated helpful auto-reply.
Polls Gmail for new emails. For each email, OpenAI decides whether it is an appointment request and extracts the patient name, doctor type, and requested date-time period; other emails are skipped. Free time slots are fetched from Google Calendar for that period, the workflow loops over them keeping only slots at least 45 minutes long, and OpenAI proposes a list of concrete 45-minute appointment options. The workflow replies to the original email with the suggestions.
Finance
See moreDocument Ops
See moreRetrieves an offices.csv object from AWS S3, reads it into rows, and loops over each row keeping only four selected columns. The reduced rows are collected into a list, written to a new CSV file, and uploaded back to S3 as offices_reduced.csv. The workflow runs on demand.
Deletes a specific sheet from a Google Sheets spreadsheet and logs the result. A minimal, on-demand example workflow.
Lists all sheets in a Google Sheets spreadsheet and logs them. A minimal, on-demand example workflow.
On the first day of every month at 09:00, computes the previous month, creates a new Google Sheet tab for it, and fetches the tracked-time report from Nifty. It loops over each tracked task to retrieve details and compute its duration in hours, writes a row per task, adds a total-hours row, and emails a notification with a link to the spreadsheet.
Reads a local cities.csv file, parses it, and loops over each row. Rows with both a City and a State value are logged and inserted into the PostgreSQL city table; rows missing either value are logged as warnings. After the loop, it queries the row count of the city table and logs the total.
By subscribing you agree to our Privacy Policy. Unsubscribe anytime.
Copyright © ByteChef. All rights reserved.