# AI use cases for Useagent (useagenthq/useagent) Repo: [useagenthq/useagent](https://github.com/useagenthq/useagent) | Use cases: 5 | Page: https://dedupedai.com/use-cases/useagenthq-useagent/ UseAgent is an open-source, self-hostable workspace that runs Claude Code, Codex, OpenCode or Pi in isolated cloud workspaces, where you hand off tasks from Slack, the web or the API and get files and pull requests back. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Hand off a code fix and get a pull request back: https://dedupedai.com/use-cases/useagenthq-useagent/hand-off-code-change-get-pull-request/ - Self-host the agent workspace on your own Linux server: https://dedupedai.com/use-cases/useagenthq-useagent/self-host-agent-workspace-on-own-server/ - Run a research report or spreadsheet with a free model: https://dedupedai.com/use-cases/useagenthq-useagent/run-research-or-spreadsheet-task-free-model/ - Schedule a recurring agent task and review its history: https://dedupedai.com/use-cases/useagenthq-useagent/schedule-recurring-agent-task/ - Run UseAgent from source to contribute a fix: https://dedupedai.com/use-cases/useagenthq-useagent/contribute-fix-run-from-source/ ## How to hand off a code fix and get a pull request back with Useagent Repo: [useagenthq/useagent](https://github.com/useagenthq/useagent) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Send a bug or feature request from the web app and receive a pull request from an isolated agent workspace. **Who it is for:** A developer or tech lead with a backlog item in one of their GitHub repositories and no time to do the change themselves. **The problem:** Small fixes and well-defined changes wait in the queue while the team is busy with other work. **The outcome:** An agent works in its own cloud workspace on the repository, and you review a pull request and the files it produced. ### Steps 1. Sign up at app.useagent.org with your email. 2. Open Settings and then Provider connections, and connect your ChatGPT account to run Codex on your own plan, or paste an API key for another model. 3. Start a thread from the home page and describe the change, naming the repository. 4. Pick a model from the Free list in the model menu, or a model you connected. 5. Follow the run live in the agent's browser and terminal, answer any question it asks, then review the pull request it opens. ### Prompt to paste into your agent ```text Using the UseAgent hosted app, start a thread that asks the agent to fix in the GitHub repository , then open the pull request it creates. Expected output: a pull request URL for the change. Verify that the pull request diff touches only the files related to . ``` ### Caveat The README says the models, login methods and tools you get depend on the engine and your configuration, and that the product is alpha software whose APIs can change. Risk, credentials: Pasting a ChatGPT connection or model API key gives the hosted service access to your provider account, so use a key you are willing to connect. 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/useagenthq-useagent/hand-off-code-change-get-pull-request/ ## How to self-host the agent workspace on your own Linux server with Useagent Repo: [useagenthq/useagent](https://github.com/useagenthq/useagent) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Run UseAgent on your own Linux host so code, prompts and files stay where you put them. **Who it is for:** A platform or compliance-minded team that must keep code, prompts and agent output on infrastructure it controls. **The problem:** Hosted coding agents send code and run history to a vendor's cloud, which fails internal data residency or compliance review. **The outcome:** A UseAgent instance on your own server, with Postgres holding the run log and sandboxes on hardware you choose. ### Steps 1. Read the self-hosting guide at infra/self-host/README.md, and choose a sandbox plugin: Daytona, CubeSandbox or Box. 2. Provision any Linux host on AWS, Google Cloud, Azure or bare metal, or use the reference Terraform host in infra/self-host/. 3. Clone the repository: `git clone https://github.com/useagenthq/useagent.git && cd useagent` 4. Run the provider-agnostic deploy script: `SERVER_IP= PG_PASSWORD= OPENROUTER_API_KEY= infra/self-host/deploy-app.sh /path/to/this/repo` (inferred, check the README) 5. Open the deployed app, run one small test thread, and confirm the run appears in the event log. ### Prompt to paste into your agent ```text In the useagent repository, read infra/self-host/README.md, then deploy UseAgent to the server at using infra/self-host/deploy-app.sh. Expected output: a running UseAgent app on that server plus a short note of the sandbox plugin chosen. Verify that a test thread completes and its steps are stored in Postgres. ``` ### Caveat The README calls UseAgent alpha software whose APIs and schemas can change between releases, so pin a tag if you need stability. Risk, remote script: The deploy script runs against a server you specify, so review infra/self-host/deploy-app.sh before passing it your server IP and passwords. Risk, credentials: The command takes a database password and a model API key on the command line, so keep them out of shell history and shared logs. 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/useagenthq-useagent/self-host-agent-workspace-on-own-server/ ## How to run a research report or spreadsheet with a free model with Useagent Repo: [useagenthq/useagent](https://github.com/useagenthq/useagent) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Ask an agent for research, a website or a spreadsheet from the web app and keep the files it makes. **Who it is for:** An analyst, marketer or operations lead who needs a research summary or spreadsheet built from the web and needs no coding. **The problem:** Gathering and formatting research by hand takes hours, and the team has no coding setup to run an agent. **The outcome:** A thread that browses the web, produces a report or spreadsheet, and lets you download the files it created. ### Steps 1. Sign up at app.useagent.org with your email. No credit card is needed. 2. Start a thread from the home page and describe the output, for example a research report or a spreadsheet of competitors. 3. Pick a model from the Free list in the model menu. 4. Watch the agent work in its browser, and answer it when it asks a question. 5. Open the files it produced from the thread and keep the ones you need. ### Prompt to paste into your agent ```text Using the UseAgent hosted app with a free model, start a thread that asks the agent to research and produce a spreadsheet of sources. Expected output: a spreadsheet file attached to the thread. Verify that every row in the spreadsheet includes a source link. ``` ### Caveat The README says the agent can produce documents, spreadsheets and presentations, but it does not state how accurate the research output will be, so check sources yourself. 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/useagenthq-useagent/run-research-or-spreadsheet-task-free-model/ ## How to schedule a recurring agent task and review its history with Useagent Repo: [useagenthq/useagent](https://github.com/useagenthq/useagent) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Set up a task that runs on a schedule and check each run's history without starting it by hand. **Who it is for:** A team lead who needs the same report or repository check run every week without anyone remembering to start it. **The problem:** Recurring checks and reports get skipped when they depend on someone starting them manually. **The outcome:** A scheduled task that runs on its own, with a history you can inspect and an option to run it immediately. ### Steps 1. Sign up at app.useagent.org and connect a model you want to use. 2. Open Automations in the web app. (inferred, check the README) 3. Create an automation that describes the task and its schedule. 4. Run the automation once right away to confirm the output is what you want. 5. Open its history after the next scheduled run and review the steps and files. ### Prompt to paste into your agent ```text Using the UseAgent hosted app, create a recurring automation that asks the agent to on a weekly schedule. Expected output: a stored run history entry for each scheduled run with its output files. Verify that a manual run and the first scheduled run both produce the same kind of output. ``` ### Caveat The README lists recurring work as a feature but does not describe the schedule options or the exact screens, so check the automations page for available choices. 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/useagenthq-useagent/schedule-recurring-agent-task/ ## How to run UseAgent from source to contribute a fix with Useagent Repo: [useagenthq/useagent](https://github.com/useagenthq/useagent) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Set up the full stack locally, run the backend and frontend, and open a pull request for a Hacktoberfest issue. **Who it is for:** A developer who wants to contribute to UseAgent and needs a local setup that matches the project's own instructions. **The problem:** Contributors need a working local environment before they can test a fix or pick an issue. **The outcome:** A running backend and frontend on your machine, a passing typecheck, and a ready branch for a pull request. ### Steps 1. Start Postgres with pgvector: `docker run -d --name useagent-pg -p 127.0.0.1:5432:5432 -e POSTGRES_HOST_AUTH_METHOD=trust pgvector/pgvector:pg16` (inferred, check the README) 2. Set the database URL: `export DATABASE_URL=postgres://postgres@localhost:5432/postgres` 3. Clone and enter the repository: `git clone https://github.com/useagenthq/useagent.git && cd useagent` 4. Install dependencies in each workspace listed in the README, running `bun install --frozen-lockfile` in every package and in backend and frontend. 5. Start the backend and frontend with `bun run dev:backend` and `bun run dev:frontend`, then run `bun run typecheck`. 6. Read CONTRIBUTING.md, comment on an issue with the hacktoberfest label that you are taking it, and open a pull request. ### Prompt to paste into your agent ```text Clone https://github.com/useagenthq/useagent, start Postgres with pgvector, install dependencies in every workspace listed in the README, and run bun run typecheck. Expected output: a passing typecheck and a note on which hacktoberfest issue you would pick. Verify that bun run dev:backend starts the API on port 3201 and bun run dev:frontend serves the UI on port 3400. ``` ### Caveat The README says a real agent task also needs a sandbox provider key and a model key, so a local setup alone will not complete an agent run. 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/useagenthq-useagent/contribute-fix-run-from-source/