# Tiledesk Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/tiledesk
> Markdown URL: https://aitinkerers.org/technologies/tiledesk.md
> Technology record last updated: 2026-03-05T10:26:22Z
> Generated: 2026-09-21T06:44:33Z

Tiledesk: The open-source AI agent builder and omnichannel customer support platform, unifying live chat, chatbots, and conversational ticketing.

Tiledesk delivers a complete, open-source AI operating system for customer support. It seamlessly orchestrates instant and asynchronous communication, integrating specialized AI Agents, live chat, and a unified help desk system. Use the visual designer to build and train agents on your specific knowledge base, ensuring accurate, automated responses. The platform guarantees omnichannel consistency across major channels (WhatsApp, Facebook Messenger, email), while providing human agents with an AI Copilot for real-time suggestions and superior efficiency.

- Official technology site: https://tiledesk.com
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [How My AI Agent Learns from Humans — Self-Training via Second-Level Support](https://rome.aitinkerers.org/talks/rsvp_l3EqJ8rC-Nw)

In this 5-minute demo, I’ll show how I built a self-training mechanism for an AI Agent by leveraging second-level human replies. When the AI fails to answer, the conversation is routed to a human. If the human provides a useful answer, it’s automatically extracted and stored as new training data — allowing the agent to improve its performance over time without manual labeling. I’ll walk through the architecture, data flow, and key functions that make this loop work. I’ll walk through the key components: - A webhook that listens to human responses and filters suitable training samples - A function that reformulates user+human messages into canonical Q&A entries using LLMs - A script that updates the RAG index (e.g., Pinecone, Qdrant, or local FAISS) - An optional visual flow using Tiledesk Design Studio to orchestrate the fallback and learning path

- Event context: AI Tinkerers Rome – May 30, 2025 — 2025-05-30 — Rome
- Public talk page: https://rome.aitinkerers.org/talks/rsvp_l3EqJ8rC-Nw

## Related Technologies

- [MongoDB](https://aitinkerers.org/technologies/mongodb) ([Markdown](https://aitinkerers.org/technologies/mongodb.md)) — 15 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos