# AI use cases for Abacusai Bot (abacusai/abacusai-bot) Repo: [abacusai/abacusai-bot](https://github.com/abacusai/abacusai-bot) | Use cases: 4 | Page: https://dedupedai.com/use-cases/abacusai-abacusai-bot/ AbacusAI Bot is a free, open-source desktop app for creating standing personal agents that you can message from WhatsApp, Telegram, Discord, or the desktop and connect to work services. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Get a morning brief from a bot on a daily schedule: https://dedupedai.com/use-cases/abacusai-abacusai-bot/daily-brief-bot-on-a-schedule/ - Hand a task to a bot from WhatsApp or Telegram: https://dedupedai.com/use-cases/abacusai-abacusai-bot/message-a-bot-from-your-phone/ - Delegate a code fix, test run, and pull request to a bot: https://dedupedai.com/use-cases/abacusai-abacusai-bot/delegate-a-coding-fix-to-a-bot/ - Run AbacusAI Bot from source to test changes: https://dedupedai.com/use-cases/abacusai-abacusai-bot/build-and-run-the-app-from-source/ ## How to get a morning brief from a bot on a daily schedule with Abacusai Bot Repo: [abacusai/abacusai-bot](https://github.com/abacusai/abacusai-bot) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Set up a bot that drafts your daily brief from connected mail and calendar on a routine. **Who it is for:** A busy professional who wants a short summary of mail, meetings, and follow-ups each morning without opening every app. **The problem:** Checking mail, calendar, and task lists every morning takes time and details slip through. **The outcome:** A bot that wakes on a routine, reads connected services, and produces a brief you can review in the desktop app. ### Steps 1. Download the installer for your platform from GitHub Releases and finish onboarding with a free Abacus.AI account. 2. Connect Gmail and Google Calendar when onboarding or when the bot asks for them. 3. Create a bot from the Morning Brief template and edit its instructions and model. 4. Open the Routines page and set a daily schedule for the bot's check-in. 5. Run the routine once from the Routines page and read the output record. ### Prompt to paste into your agent ```text Using the AbacusAI Bot desktop app, create a bot from the Morning Brief template for , connect Gmail and Google Calendar, and schedule a daily routine. Run it once and report the brief's sections. Verify that the routine run has its own saved output. ``` ### Caveat Local routines only run while the desktop app is open, so the brief will not arrive if the computer is off. Risk, credentials: The bot reads mail and calendar through your connected accounts, so disconnect those services if you stop using the bot. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/abacusai-abacusai-bot/daily-brief-bot-on-a-schedule/ ## How to hand a task to a bot from WhatsApp or Telegram with Abacusai Bot Repo: [abacusai/abacusai-bot](https://github.com/abacusai/abacusai-bot) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Link a messaging app to a bot so you can give it work from your phone. **Who it is for:** A person who is away from the desk and needs a bot to look up or draft something from their phone. **The problem:** Work requests come up when you are away from the desktop, and waiting until you return delays them. **The outcome:** A bot that answers your own messages from WhatsApp, Telegram, or Discord, with remote approval rules you control. ### Steps 1. Install the desktop app and create a bot with its own instructions and model. 2. Link AbacusAI Bot as a device in WhatsApp, or sign in and link the shared Abacus AI bot in Telegram or Discord. 3. Turn on inbound responses for your own sender and approve any other senders you want the bot to answer. 4. Decide whether risky remote tool calls run immediately or wait for approval in the desktop app. 5. Send a test message from your Message yourself chat and confirm the reply. ### Prompt to paste into your agent ```text Using AbacusAI Bot, link a messaging app for to a bot named , approve only , and keep risky tool calls waiting for desktop approval. Send one test request and report the reply. Verify that messages from unapproved senders are recorded but do not start work. ``` ### Caveat Connecting an account does not make the bot answer everyone, so you must explicitly approve each sender before work starts. Risk, remote script: Unattended remote tool calls are on by default once inbound responses are enabled, so turn that setting off if you want approval before risky actions. Risk, credentials: Linking WhatsApp or signing in to Telegram or Discord gives the bot access to the connected account's messages. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/abacusai-abacusai-bot/message-a-bot-from-your-phone/ ## How to delegate a code fix, test run, and pull request to a bot with Abacusai Bot Repo: [abacusai/abacusai-bot](https://github.com/abacusai/abacusai-bot) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Give a bot a repository and ask it to implement, test, and open a pull request. **Who it is for:** A developer with a repository and a bug or small feature that can be handed off overnight. **The problem:** Routine fixes take focused time that could go to other work, and the change must still be tested and reviewed. **The outcome:** A bot that inspects the repository, edits the code, runs the tests, and opens a pull request for your review. ### Steps 1. Install the desktop app from GitHub Releases and sign in or create a free account. 2. Create a bot with a coding-focused instruction and a model you trust. 3. Connect GitHub and register the local repository as a workspace in the app. 4. Ask the bot to reproduce the bug, make the change, run the tests, and open a pull request. 5. Review the diff and the pull request yourself before merging. ### Prompt to paste into your agent ```text Using AbacusAI Bot, register the local repository at as a workspace for a bot, connect GitHub, and ask it to fix , run the test suite, and open a pull request. Report the branch name and test results. Verify that the test command actually ran and the diff matches the issue. ``` ### Caveat Bot chats use full access by default with no sandbox, so the bot can edit files and run commands in your user account unless you switch the Profile page to Auto. Risk, credentials: Bot chats run with full tool permissions and can act through your connected GitHub account, so limit that account's scope where possible. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/abacusai-abacusai-bot/delegate-a-coding-fix-to-a-bot/ ## How to run AbacusAI Bot from source to test changes with Abacusai Bot Repo: [abacusai/abacusai-bot](https://github.com/abacusai/abacusai-bot) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Install dependencies and start the desktop app in development mode from the repository. **Who it is for:** A contributor who wants to modify or test the AbacusAI Bot desktop application itself. **The problem:** Changes to the app need a local development build before they can be checked. **The outcome:** A running development build of the desktop app that you can use to test your changes. ### Steps 1. Clone the repository from GitHub and open its folder in a terminal. 2. Use Node.js 22 and run `corepack enable`. 3. Run `pnpm install` to install dependencies. 4. Run `pnpm dev` to start the app in development mode. 5. Read the Build from source section in docs/getting-started.md for packaging commands. ### Prompt to paste into your agent ```text In the abacusai-bot repository, use Node.js 22, run `corepack enable`, `pnpm install`, and `pnpm dev`, then report whether the desktop app window starts. Verify that the terminal shows no install errors before reporting success. ``` ### Caveat This repository contains only the desktop app, so it does not provide a CLI, SDK, hosted agent, or remote execution service. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/abacusai-abacusai-bot/build-and-run-the-app-from-source/