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.

Thanks to these combined features, Obside guarantees that every agent is transparent, verifiable and interpretable at every step.