# Rules reliability ## How can you be sure the AI-generated code matches your description? Several platform features are designed to guarantee the **reliability, precision and transparency** of AI-generated agents. ### 1. Guided creation You're encouraged to write your description as if you were teaching it to someone else. The more detailed and precise the description, the fewer interpretation gaps remain. ### 2. Rephrasing before agent creation Before creating the agent, Obside Chat **analyzes, interprets and rephrases** your description. This step lets you verify that your intent is correctly understood and highlights any ambiguities. You can correct or complete it before launching the creation. ### 3. Consolidated description after creation Once the agent is created, its **consolidated description** is accessible at any time in the **Description** tab of the agent's page. It restates in a structured way what the agent actually does, and offers an additional layer of verification. ### 4. Generated code accessible The **agent's code** (automatically generated by the AI) is accessible in the **Code** tab. It formalizes the description in executable form and allows precise inspection of the behavior. ### 5. Backtest with full trades list When running a backtest, you can **view or export the full list of trades** generated by the agent. This transparency lets you verify each trade in detail and confirm overall consistency. ### 6. Built-in TradingView chart Each backtest comes with a TradingView chart showing all entry and exit points of the trades. * The chart displays not only the positions, but also the reason for each entry and exit. * You can add technical indicators on the chart to verify that all signals match the defined rules. ### 7. Detailed performance metrics Dozens of **performance metrics** are calculated and displayed automatically. They give you deep insight into the agent's behavior, profitability and risk profile. ### 8. Iterating through the chat If you notice a behavior that doesn't match your intent, you can **continue the conversation** in the chat linked to the agent to correct or fine-tune it. {% hint style="success" %} Thanks to these combined features, Obside guarantees that every agent is **transparent, verifiable and interpretable** at every step. {% endhint %} --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.obside.com/agents/create-an-agent/rules-reliability.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.