All templates By NappAI team Tweet Posting Automation
Publish a tweet based on content previously published on the user’s account
graph TD
%%{init: {'theme': 'mc','layout': 'elk'}}%%
ParseData-a5xpo[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data]
style ParseData-a5xpo stroke:#a170ff
Prompt-2wdmr[<div><img src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Prompt]
style Prompt-2wdmr stroke:#a170ff
OpenAIModel-djdyd[<div><img src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>OpenAI]
style OpenAIModel-djdyd stroke:#a170ff
XReader-tbiw6[X Reader]
style XReader-tbiw6 stroke:#a170ff
XPoster-ob91z[X Poster]
style XPoster-ob91z stroke:#a170ff
Prompt-2wdmr -.- OpenAIModel-djdyd
linkStyle 0 stroke:#a170ff
ParseData-a5xpo -.- Prompt-2wdmr
linkStyle 1 stroke:#a170ff
XReader-tbiw6 -.- ParseData-a5xpo
linkStyle 2 stroke:#a170ff
OpenAIModel-djdyd -.- XPoster-ob91z
linkStyle 3 stroke:#a170ff
🧩 Overview
This workflow automates the creation and publication of a new tweet on a user’s X (Twitter) account. It gathers recent tweets, formats them into a concise history, feeds that history to an OpenAI model to generate a fresh, brand‑aligned tweet, and finally posts the generated content to X. The process reduces manual drafting effort, ensures topical relevance, and maintains a consistent posting cadence.
⚙️ Main Features
- Retrieves recent tweets from a specified X user.
- Transforms raw tweet data into a plain‑text history suitable for prompt engineering.
- Builds a prompt that instructs the LLM to produce a novel tweet within character limits.
- Generates tweet text using an OpenAI LLM with controlled temperature and token limits.
- Publishes the generated tweet to X as a new post (or reply, if a tweet ID is supplied).
🔄 Workflow Steps
| Component Name | Role in the Workflow | Key Inputs | Key Outputs |
|---|---|---|---|
| X Reader | Retrieves tweets from a user’s timeline. | Username of the target account; maximum number of tweets to fetch; operation type (“Get Tweets By User”). | Raw tweet data (structured format). |
| Parse Data | Converts tweet data into a readable text history. | Raw tweet data. | Formatted text string containing the recent tweets. |
| Prompt | Crafts the LLM prompt incorporating tweet history. | Formatted tweet history. | Prompt message ready for the language model. |
| OpenAI Model | Generates a new tweet from the prompt. | Prompt message. | Generated tweet text. |
| X Poster | Posts the generated tweet to X. | Generated tweet text; optional reply tweet ID; operation type (“Post Tweet”). | Confirmation data of the posted tweet. |
🧠 Notes
- All components rely on OAuth credentials for X and an API key for OpenAI; credentials must be configured in the corresponding components before execution.
- The OpenAI Model respects the
max_charactersvalue (default 100) to keep the tweet within Twitter’s 280‑character limit, but the final text should still be validated for length. - The Parse Data component can handle nested metadata, enabling more sophisticated prompts if needed.
- Rate limits for both X API calls and OpenAI requests apply; exceeding them will result in temporary failures.
- The workflow assumes the user’s tweet history is publicly accessible; private or protected tweets will not be retrievable.
- The X Poster component only posts the generated tweet; it does not modify or delete existing content unless a tweet ID is supplied for a reply.