# AI use cases for Tel Agent (Dpro-at/Tel-Agent) Repo: [Dpro-at/Tel-Agent](https://github.com/Dpro-at/Tel-Agent) | Use cases: 4 | Page: https://dedupedai.com/use-cases/dpro-at-tel-agent/ Tel-Agent is an open-source, self-hosted gateway that connects phone lines and messaging channels to AI agents, using your own provider keys. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Answer business phone calls with an AI agent on your PBX: https://dedupedai.com/use-cases/dpro-at-tel-agent/ai-receptionist-on-existing-pbx/ - Answer website chat and messaging apps from one assistant: https://dedupedai.com/use-cases/dpro-at-tel-agent/one-assistant-across-chat-and-messaging/ - Run a local AI phone and chat dashboard on Windows: https://dedupedai.com/use-cases/dpro-at-tel-agent/run-local-dashboard-on-windows/ - Add a new messaging channel with an AI coding agent: https://dedupedai.com/use-cases/dpro-at-tel-agent/extend-tel-agent-with-coding-agent/ ## How to answer business phone calls with an AI agent on your PBX with Tel Agent Repo: [Dpro-at/Tel-Agent](https://github.com/Dpro-at/Tel-Agent) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Route inbound calls from an existing PBX extension to an AI agent that can transfer, take messages and log calls. **Who it is for:** A small business owner or IT admin whose 3CX, Asterisk or FreePBX line gets calls that need a first answer while staff are busy or away. **The problem:** Callers wait or reach voicemail, and nobody is available to triage calls or take messages. **The outcome:** Inbound calls are checked against your routing rules, then passed to a human, blocked, or answered by an AI agent that can take a message or transfer the call. ### Steps 1. Clone the repo with `git clone https://github.com/Dpro-at/Tel-Agent.git` and enter it with `cd Tel-Agent`. 2. Copy the environment template with `cp .env.example .env`, then generate a key with `openssl rand -hex 32` and set it as ENCRYPTION_KEY in `.env`. 3. Start the stack with `docker compose up -d --build`, then open http://localhost:38471 and create the administrator. 4. In the dashboard, add your STT, LLM and TTS provider keys and register an extension on your PBX as a SIP endpoint. 5. Set routing rules for caller ID so that selected callers reach the AI agent and others go to a human or are blocked. 6. Place a test call from a known number and check the stored transcript in the conversation archive. ### Prompt to paste into your agent ```text In the Dpro-at/Tel-Agent repo, follow the README quick start and the phone channel requirements to connect a PBX extension for . Expected output: a test call from that routes to the AI agent and appears with a transcript in the conversation archive. Verify that ENCRYPTION_KEY is set in .env and that the dashboard loads at http://localhost:38471 before placing the call. ``` ### Caveat Tel Agent only speaks SIP, so analog lines need an ATA, and the README lists the phone channel as part of an alpha release. Risk, credentials: The STT, LLM and TTS provider keys and the SIP credentials give access to paid services and your phone line, so store them only in the local .env and the dashboard. 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/dpro-at-tel-agent/ai-receptionist-on-existing-pbx/ ## How to answer website chat and messaging apps from one assistant with Tel Agent Repo: [Dpro-at/Tel-Agent](https://github.com/Dpro-at/Tel-Agent) | Difficulty: Intermediate | Time: 1 hour 30 minutes | Basis: From the README Serve web chat, WhatsApp, Telegram, email and SMS from a single AI assistant with notifications for staff. **Who it is for:** A support or sales lead whose customers write in through web chat, WhatsApp, Telegram, email or SMS and need one place to answer. **The problem:** Messages from different platforms arrive in separate inboxes, and replies are slow or inconsistent. **The outcome:** Each conversation is answered by the AI assistant, stored in the conversation archive, and flagged in the notification tray so a person knows someone wrote in. ### Steps 1. Clone the repo with `git clone https://github.com/Dpro-at/Tel-Agent.git` and run `cp .env.example .env`. 2. Set ENCRYPTION_KEY in `.env` using `openssl rand -hex 32`, then start with `docker compose up -d --build`. 3. Open http://localhost:38471, create the administrator, and add your own credentials for each channel you want, such as WhatsApp, Telegram or Twilio for SMS. 4. Create an assistant and add knowledge and catalogue entries so it can answer common questions. 5. Send a test message on each connected channel and confirm the reply streams and appears in the conversation archive. 6. Check the notification tray to confirm staff are alerted to new messages. ### Prompt to paste into your agent ```text Using the Dpro-at/Tel-Agent repo, set up the messaging channels listed in the README for with customer-owned credentials. Expected output: a test message on each channel that gets an AI reply and shows in the conversation archive and notification tray. Verify that each channel credential is stored and that the dashboard API docs load at http://localhost:38472/docs. ``` ### Caveat The README says the channels are wired, but you must configure each one with your own provider credentials before it works. Risk, credentials: Each platform needs your own credentials, so treat WhatsApp, Telegram, Twilio and email tokens as secrets and keep them out of shared files. 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/dpro-at-tel-agent/one-assistant-across-chat-and-messaging/ ## How to run a local AI phone and chat dashboard on Windows with Tel Agent Repo: [Dpro-at/Tel-Agent](https://github.com/Dpro-at/Tel-Agent) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Install the Windows package to start the local service and open the Tel Agent dashboard in a browser. **Who it is for:** A non-developer or small team lead on Windows who wants to try an open AI assistant on their own PC without Docker. **The problem:** Setting up a self-hosted AI assistant usually means containers or a developer toolchain, which blocks trial use. **The outcome:** The local service runs, the dashboard opens in the browser, and an administrator account is created on first visit. ### Steps 1. Open the releases page at https://github.com/Dpro-at/Tel-Agent/releases/latest and download the Windows installer. 2. Run the installer. Windows will ask once before it runs because the installers are unsigned. 3. Wait for the installer to start the local service and open the dashboard in your browser. 4. Create the administrator account on the first visit, since there are no default credentials. 5. Add your STT, LLM and TTS provider keys in the settings before testing a conversation. ### Prompt to paste into your agent ```text From the Dpro-at/Tel-Agent releases page, install the Windows package for and open the dashboard. Expected output: the dashboard loads in the browser and a first administrator account is created. Verify that the service is running on the local loopback address before entering any provider keys. ``` ### Caveat The Windows installer is unsigned while code signing is not configured, and the README describes the project as alpha. 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/dpro-at-tel-agent/run-local-dashboard-on-windows/ ## How to add a new messaging channel with an AI coding agent with Tel Agent Repo: [Dpro-at/Tel-Agent](https://github.com/Dpro-at/Tel-Agent) | Difficulty: Advanced | Time: 3 hours | Basis: From the README Point a coding agent at AGENTS.md and the channel contract to build one new channel as a declarative definition. **Who it is for:** A developer who wants to add a channel from the planned second wave, such as Signal or Matrix, and will use an AI coding agent to do the work. **The problem:** Adding a channel to a messaging gateway usually means forking code and repeating setup logic. **The outcome:** The agent produces a new channel that follows the declarative setup contract, with a focused pull request that follows the CLA and contribution rules. ### Steps 1. Clone the repo with `git clone https://github.com/Dpro-at/Tel-Agent.git` and open `AGENTS.md` and `CLAUDE.md`. 2. Read `CONTRIBUTING.md` and the channel extension contract (#220) before writing code. 3. Pick one open issue with the `channel` label and confirm it is not already claimed. 4. Have the agent run the manual run described in `CONTRIBUTING.md` and implement the channel as a definition plus a transport. 5. Sign the CLA and open one focused pull request that covers one concern. ### Prompt to paste into your agent ```text In the Dpro-at/Tel-Agent repo, read AGENTS.md and CLAUDE.md, then implement the open channel issue using the declarative setup contract. Expected output: a focused branch with the new channel definition and transport, and a pull request description that references the issue. Verify that the change follows the rules in CLAUDE.md and that the project tests pass locally. ``` ### Caveat The second wave of channels is still in progress, and the README requires a signed CLA before any pull request is merged. 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/dpro-at-tel-agent/extend-tel-agent-with-coding-agent/