> For the complete documentation index, see [llms.txt](https://tryflux.gitbook.io/flux-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://tryflux.gitbook.io/flux-docs/5.-core-features.md). # 5. Core Features #### 5.1 Agent Configuration Users can configure agents with full flexibility: * **Pool Selection**: Filter by chain and pool address * **Price Boxes**: Define ranges or bands where the agent should execute trades * **Risk Knobs**: Control slippage tolerance, position size, execution frequency * **Broadcast Guards**: Enforce quote-only mode or require manual approval before broadcast #### 5.2 Execution Safety Multiple layers ensure safe, controllable execution: 1. **Quote-Only Mode**: Agents can run entirely in simulation, validating logic without on-chain risk 2. **Runtime Flags**: Toggle between simulation and live broadcast without reconfiguration 3. **Guardrails**: Transaction size and slippage limits enforced before broadcast 4. **Audit Trail**: Every decision, quote, and receipt is logged for post-execution analysis #### 5.3 Model-Assisted Decisioning Optional integration with OpenAI models enables: * **Price-Box Selection**: LLM recommends dynamic price ranges based on recent market conditions * **Strategy Tuning**: Suggestions for risk parameter adjustments * **Decision Transparency**: Full reasoning trail visible in audit logs This is an *optional* layer; rule-based execution remains the default and is fully deterministic. #### 5.4 Real-Time Monitoring The dashboard provides: * **Agent Health**: Live status indicators for all agents * **Quote Inspector**: Detailed view of proposed transactions before broadcast * **Receipt Tracking**: On-chain settlement status and confirmation time * **Performance Metrics**: Slippage, fill rates, gas costs, and profitability #### 5.5 Comparative Analytics The arena layer enables: * **Pool Rankings**: Which pools consistently yield better execution? * **Strategy Benchmarks**: How does your agent perform vs. similar configurations? * **Time-Series Analysis**: Performance trends across different market conditions #### 5.6 Liquidity Lab An experimental research environment for: * **v4-Style Exploration**: Advanced pool mechanics without production risk * **RPC-Backed Analytics**: Direct on-chain state reads without trading * **Custom LP Workflows**: Design and test sophisticated liquidity provision strategies * **Wallet-Connected**: Full integration with RainbowKit for seamless user UX --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://tryflux.gitbook.io/flux-docs/5.-core-features.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.