Tiledesk Server is the main API component of the Tiledesk platform Tiledesk is an open-source alternative to Voiceflow, allowing you to build advanced LLM-powered agents with easy human-in-the-loop (HITL) when necessary.
git clone https://github.com/Tiledesk/tiledesk-server.gitTiledesk Server serves as the core API component of the Tiledesk platform, offering an open-source alternative to Voiceflow. This skill allows developers to build advanced LLM-powered AI agents seamlessly, integrating human-in-the-loop (HITL) capabilities when necessary. By leveraging Tiledesk Server, teams can create conversational agents that enhance customer interactions and automate responses effectively. One of the key benefits of using Tiledesk Server is its ability to streamline workflow automation. Developers can implement this skill in approximately 30 minutes, making it an efficient choice for those looking to enhance their AI automation capabilities. While the exact time savings are not quantified, the reduction in manual intervention through HITL processes can lead to significant efficiency gains over time, allowing teams to focus on more strategic tasks. This skill is particularly valuable for developers, product managers, and AI practitioners who are looking to create sophisticated conversational interfaces. By utilizing Tiledesk Server, these professionals can develop solutions that cater to various use cases, such as customer support chatbots, virtual assistants, and interactive voice response systems. For example, a product manager could use this skill to quickly prototype a customer service agent that learns from user interactions, improving over time without extensive manual updates. With an intermediate implementation difficulty, Tiledesk Server requires some technical knowledge but is designed to fit seamlessly into AI-first workflows. It empowers teams to build and deploy AI agent skills that are not only functional but also adaptable to changing user needs. By incorporating Tiledesk Server into your automation strategy, you can leverage the power of AI to enhance user engagement and operational efficiency, making it a valuable addition to your toolkit.
[{"step":"Identify the Tiledesk Server endpoint and API key.","action":"Locate your Tiledesk Server URL (e.g., `http://localhost:3000` for local instances or your cloud deployment URL). Retrieve your API key from the Tiledesk dashboard under **Settings > API Keys**.","tip":"Use environment variables (e.g., `TILEDesk_API_KEY`) to securely store the API key in your scripts or CI/CD pipelines."},{"step":"Define the task and required parameters.","action":"Determine whether you need to create, update, or query a resource (e.g., agent, workflow, or conversation). For example, to create an agent, you'll need the agent's name, description, and workflow ID. Use the Tiledesk API documentation (e.g., `https://docs.tiledesk.com/api/v1`) to confirm required fields.","tip":"Use tools like Postman or cURL to test API endpoints before automating with scripts. Example cURL command: `curl -X POST http://localhost:3000/api/v1/agents -H 'Authorization: Bearer YOUR_API_KEY' -H 'Content-Type: application/json' -d '{\"name\": \"Support Agent\", \"workflow_id\": \"wf_123abc\"}'`."},{"step":"Automate the task using the Tiledesk Server API.","action":"Write a script (Python, Node.js, etc.) or use a low-code tool (e.g., Zapier, Make) to call the Tiledesk API. For example, in Python, use the `requests` library to send HTTP requests. Example:\n```python\nimport requests\n\napi_key = \"YOUR_API_KEY\"\nurl = \"http://localhost:3000/api/v1/agents\"\nheaders = {\"Authorization\": f\"Bearer {api_key}\", \"Content-Type\": \"application/json\"}\ndata = {\"name\": \"Support Agent\", \"workflow_id\": \"wf_123abc\"}\n\nresponse = requests.post(url, headers=headers, json=data)\nprint(response.json())\n```","tip":"Handle errors gracefully by checking the `response.status_code` and logging failures. For example, if the response status is 400, log the error and retry with corrected parameters."},{"step":"Verify the changes in the Tiledesk dashboard.","action":"Log in to your Tiledesk dashboard and navigate to the relevant section (e.g., **Agents**, **Workflows**, or **Analytics**) to confirm the changes were applied. For example, check that the new agent appears in the **Agents** list and is active.","tip":"Use the Tiledesk dashboard's built-in tools to test the agent's behavior. For instance, send a test query to the agent and observe its responses in real-time."},{"step":"Monitor and iterate.","action":"Set up monitoring for the agent's performance using Tiledesk's analytics tools. Track metrics like conversation resolution rate, user satisfaction scores, and average response time. Use this data to iterate on the agent's workflow or configuration.","tip":"Automate alerts for critical metrics (e.g., low resolution rate) by integrating Tiledesk with tools like Slack or email notifications. For example, use a cron job to check the analytics API daily and send alerts if the resolution rate drops below a threshold."}]
Automate customer support inquiries to reduce response times and improve user satisfaction.
Integrate chatbots with existing applications to provide real-time assistance and information.
Deploy multi-channel chatbots that adapt responses based on the platform used by the customer.
Utilize human-in-the-loop capabilities to manage complex customer interactions seamlessly.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/Tiledesk/tiledesk-serverCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use the Tiledesk Server API to [ACTION] for [PROJECT_NAME]. Specifically, [SPECIFIC_TASK] such as creating a new agent, updating a workflow, or retrieving conversation logs. Include [PARAMETERS] like agent ID, workflow ID, or time range if applicable. Ensure the response includes [OUTPUT_FORMAT] like JSON data, a confirmation message, or a summary of changes.
```json
{
"status": "success",
"data": {
"agent_id": "agt_789xyz",
"name": "Customer Support Agent",
"status": "active",
"created_at": "2024-05-20T14:30:00Z",
"workflow_id": "wf_123abc",
"last_updated": "2024-05-20T15:45:00Z"
},
"message": "Agent 'Customer Support Agent' created successfully with workflow ID 'wf_123abc'."
}
```
**Next Steps:**
1. Test the agent by sending a sample query to the workflow endpoint: `POST /api/v1/workflows/wf_123abc/query` with the payload `{"query": "How do I reset my password?"}`.
2. Monitor the conversation logs in the Tiledesk dashboard under **Analytics > Conversations** to verify the agent's responses.
3. If the agent requires adjustments, use the `PUT /api/v1/agents/agt_789xyz` endpoint to update its configuration, such as adding new intents or modifying the LLM prompt.
**Note:** Ensure your Tiledesk Server is running locally or on a cloud instance (e.g., `http://localhost:3000` or `https://your-tiledesk-server.com`). Authenticate requests using the `Authorization: Bearer YOUR_API_KEY` header.AI-first notebook for operational data apps
Utilize a flexible document database with rich querying and scalable architecture.
Google's app development platform with hosting and auth
AI assistant for precise answers and information
Podcast discovery and enjoyment
Interactive video chat for kids and families
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan