> ## Documentation Index > Fetch the complete documentation index at: https://docs.halios.ai/llms.txt > Use this file to discover all available pages before exploring further. # Prompting Halios > Use your coding agent to build, run, debug, and improve agent evals with Halios. Tell your coding agent what you want to evaluate or improve. It can inspect your repository, use the Halios skill and CLI, and decide how to carry out the work. Start simple. Add constraints only when they matter. Add details when a minimal prompt does not work or when you need the agent to act on a specific trace, evaluation run, or check. *** ## Build Create an evaluation suite with realistic scenarios, edge cases, and checks. **Start with:** ```text theme={null} Set up evals for this agent. ``` **Add focus when needed:** ```text theme={null} Set up evals for the refund flow. Focus on identity verification and policy violations. ``` ```text theme={null} Review the current eval suite and add coverage for tool failures and ambiguous user requests. ``` ```text theme={null} Add a check that the agent discloses it is an AI before continuing the conversation. ``` ```text theme={null} Add an LLM-as-judge check to verify that the agent handled the user's request politely. ``` ```text theme={null} Add a deterministic check to verify that the agent disclosed that the conversation may be recorded for quality and training purposes. ``` **Ask your coding agent to explain what it created:** ```text theme={null} Walk me through the scenarios and checks in this eval suite. ``` **Add a CI release gate:** ```text theme={null} Add a GitHub Action to run evals on every PR. Block the merge if the eval score drops below 0.8. ``` **Turn a production failure into a regression test:** ```text theme={null} Add trace as a scenario and check so we catch this failure again. ``` *** ## Run Simulate realistic user interactions and evaluate how your agent behaves across different paths. ```text theme={null} Run the eval suite against the current agent. ``` ```text theme={null} Run the refund scenarios with three trials each and show me any failures. ``` ```text theme={null} Rerun the scenarios affected by my latest changes. ``` ```text theme={null} Compare this run with the previous baseline. ``` Halios runs the agent again with fresh simulations. Each scenario produces a new interaction rather than re-scoring a saved transcript. *** ## Debug Trace failures back to conversations, tool calls, and decisions. ```text theme={null} Why did this evaluation fail? ``` ```text theme={null} Investigate the failed refund scenario and show me what happened. ``` ```text theme={null} Which tool call caused this check to fail? ``` ```text theme={null} Find the common cause behind the failures in this run. ``` ```text theme={null} Trace this failure back to the relevant prompt, tool, or agent code. ``` You can start from a run, scenario, trace, or failed check. Your coding agent uses Halios trace data together with repository context to investigate the root cause. *** ## Improve Verify fixes, catch regressions, and continuously improve your agent. ```text theme={null} Fix this failure and rerun the affected evals. ``` ```text theme={null} Improve the agent on the failing scenarios without regressing the ones that already pass. ``` ```text theme={null} Try a better system prompt and compare it with the current version. ``` ```text theme={null} Optimize this agent against the eval suite. ``` ```text theme={null} Keep the change only if it improves the eval results without introducing regressions. ``` The loop continues as needed: **run → investigate → change → rerun → compare** Halios provides the evaluation data; your coding agent uses that information to propose and apply changes. *** Command reference for automation and CI/CD pipelines. Core mental model and key evaluation terms.