> For the complete documentation index, see [llms.txt](https://docs.palliora.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.palliora.org/ai/use/demo-apps.md). # Try the demo app Palliora AI's demo app, AI Workbench, is live at [**ai.palliora.org**](https://ai.palliora.org/). It looks and works like any modern AI chat app: you type, it responds, and it can search the web, fetch a page, and use other tools. Underneath, every model call and every tool call runs as its own [Compute Contract](https://github.com/palliora-org/palliora-docs-with-ai/tree/main/learn/concepts/compute-contracts.md), and every turn produces a [provenance](/ai/learn/concepts/provenance.md) record: which model ran, which tools were called, and a reference to the agreement that coordinated each one. Signing in creates your own Palliora identity, so every request is signed by you, not by a shared service account. See [Palliora AI](https://github.com/palliora-org/palliora-docs-with-ai/tree/main/products/palliora-ai.md) for how the product works. ## Get started 1. **Open the app.** Go to [ai.palliora.org](https://ai.palliora.org/). 2. **Sign in with your email.** No wallet needed. This creates your Palliora identity, used to sign every request you make from the app. 3. **Redeem a coupon code.** New accounts start without a balance. In the chat box, type `/redeem CODE`, replacing `CODE` with the code you were given. This funds your account so you can start chatting. Don't have a code? Email **** to get one. 4. **Start chatting.** Ask a question, or try a prompt that needs a tool, like a web search. Each response is backed by a Compute Contract you can inspect. ## Looking for the Palliora DeFi demo? It has its own page, see [Try the demo app](https://github.com/palliora-org/palliora-docs-with-ai/tree/main/use/demo-apps.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.palliora.org/ai/use/demo-apps.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.