> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://www.comet.com/docs/opik/development/optimization-runs/llms.txt.

# Optimization runs

> Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

## Docs

- [Agent Optimization](https://www.comet.com/docs/opik/development/optimization-runs/overview.md): Learn about Opik's automated LLM prompt and agent optimization SDK. Discover MetaPrompt, Few-shot Bayesian, and Evolutionary optimization algorithms for enhanced performance.
- [Optimization Studio](https://www.comet.com/docs/opik/development/optimization-runs/optimization_studio.md): Run prompt optimizations from the Opik UI with datasets, metrics, and visual progress tracking.
- [Quickstart](https://www.comet.com/docs/opik/development/optimization-runs/quickstart.md): Install the Agent Optimizer SDK, run your first optimization, and inspect the results in under 10 minutes.
- [Optimizer Introduction Cookbook](https://www.comet.com/docs/opik/development/optimization-runs/quickstart_notebook.md): Learn how to use Opik Agent Optimizer with the HotPotQA dataset through an interactive notebook, covering setup, configuration, and optimization techniques.
- [Optimizer Frequently Asked Questions](https://www.comet.com/docs/opik/development/optimization-runs/faq.md): Find answers to common questions about Opik Agent Optimizer, including optimizer selection, configuration, usage, and best practices.
- [Changelog](https://www.comet.com/docs/opik/development/optimization-runs/changelog.md): Release notes focused on Agent Optimizer features.
- [Known Issues](https://www.comet.com/docs/opik/development/optimization-runs/known_issues.md): Known runtime issues when running Opik Optimizer with current dependencies.
- [Opik Agent Optimizer Core Concepts](https://www.comet.com/docs/opik/development/optimization-runs/optimization/concepts.md): Learn about the core concepts of Opik Agent Optimizer, including key terms, evaluation processes, optimization workflows, and best practices for effective LLM optimization.
- [Configuring LLM Providers](https://www.comet.com/docs/opik/development/optimization-runs/optimization/configure_models.md): Learn how to configure different LLM providers like OpenAI, Anthropic, Gemini, Azure, and Ollama for use with the Opik Agent Optimizer.
- [Define datasets](https://www.comet.com/docs/opik/development/optimization-runs/optimization/define_datasets.md): Design, version, and validate datasets used for optimization runs.
- [Define metrics](https://www.comet.com/docs/opik/development/optimization-runs/optimization/define_metrics.md): Create reliable metrics and composite objectives for Agent Optimizer runs.
- [Optimize prompts](https://www.comet.com/docs/opik/development/optimization-runs/optimization/optimize_prompts.md): Pick the right optimizer, run experiments, and ship better prompts.
- [Optimize tools (MCP)](https://www.comet.com/docs/opik/development/optimization-runs/optimization/optimize_tools.md): Improve MCP tool and parameter descriptions without changing prompt text.
- [Optimize agents](https://www.comet.com/docs/opik/development/optimization-runs/optimization/optimize_agents.md): Connect the Agent Optimizer to Agent Frameworks.
- [Optimize multimodal prompts](https://www.comet.com/docs/opik/development/optimization-runs/optimization/optimize_multimodal.md): Run optimizations for prompts that combine text, images, and other modalities.
- [Dashboard results](https://www.comet.com/docs/opik/development/optimization-runs/optimization/dashboard_results.md): Analyze optimization trials, failure modes, and improvements inside Opik.
- [Optimization algorithms overview](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/overview.md): Compare Agent Optimizer algorithms and pick the right one for your workload.
- [Optimizer benchmarks](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/benchmarks.md): Compare algorithm performance across common datasets and learn how to run the benchmark suite locally.
- [MetaPrompt Optimizer](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/metaprompt_optimizer.md): Learn how to use the MetaPrompt Optimizer to refine and improve your LLM prompts through systematic analysis and iterative refinement.
- [HRPO (Hierarchical Reflective Prompt Optimizer)](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/hierarchical_adaptive_optimizer.md): Learn how to use HRPO (Hierarchical Reflective Prompt Optimizer) to improve prompts through systematic root cause analysis of failure modes and targeted refinement.
- [Few-Shot Bayesian Optimizer](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/fewshot_bayesian_optimizer.md): Learn how to use the Few-Shot Bayesian Optimizer to find optimal few-shot examples for your chat-based prompts using Bayesian optimization techniques.
- [Evolutionary Optimizer: Genetic Algorithms](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/evolutionary_optimizer.md): Learn how to use the Evolutionary Optimizer to discover optimal prompts through genetic algorithms, with support for multi-objective optimization and LLM-driven genetic operations.
- [GEPA Optimizer](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/gepa_optimizer.md): Use the external GEPA package through Opik's `GepaOptimizer` to optimize a single system prompt for single-turn tasks with a reflection model.
- [Parameter Optimizer: Bayesian Parameter Tuning](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/parameter_optimizer.md): Learn how to use the Parameter Optimizer to find optimal LLM call parameters (temperature, top_p, etc.) using Bayesian optimization without changing your prompt.
- [Tool Optimization (MCP & Function Calling)](https://www.comet.com/docs/opik/development/optimization-runs/algorithms/tool_optimization.md): Learn how to optimize prompts that leverage MCP (Model Context Protocol) tools and function calling capabilities across supported optimizers.
- [Synthetic Data Optimizer Cookbook](https://www.comet.com/docs/opik/development/optimization-runs/cookbooks/synthetic_data_optimizer_cookbook.md): Learn how to generate synthetic Q&A data from Opik traces and optimize prompts using the MetaPromptOptimizer through an interactive notebook.
- [ARC-AGI Optimization Tutorial](https://www.comet.com/docs/opik/development/optimization-runs/cookbooks/arc_agi_optimizer_cookbook.md): End-to-end ARC-AGI optimization walkthrough with Opik Agent Optimizer.
- [Multimodal Agent Optimization Tutorial](https://www.comet.com/docs/opik/development/optimization-runs/cookbooks/multimodal_agent_optimizer_cookbook.md): Multimodal agent optimization tutorial inspired by a self-driving car example.
- [Extending Optimizers](https://www.comet.com/docs/opik/development/optimization-runs/advanced/extending_optimizers.md): Learn how to extend Opik's optimization framework with custom algorithms and contribute to the project's development.
- [Custom metrics](https://www.comet.com/docs/opik/development/optimization-runs/advanced/custom_metrics.md): Build specialized metrics, integrate external models, and reuse them across optimizations.
- [Custom Optimizer Prompts](https://www.comet.com/docs/opik/development/optimization-runs/advanced/prompt_customization.md): Learn how to override and customize the internal prompt templates used by Opik optimizers to add domain constraints, safety requirements, or custom formatting.
- [Sampling controls](https://www.comet.com/docs/opik/development/optimization-runs/advanced/n_samples.md): Use n_samples, n_samples_minibatch, and the n parameter to trade cost for stability and exploration.
- [Multiple Completions (n parameter)](https://www.comet.com/docs/opik/development/optimization-runs/advanced/multiple_completions.md): Learn how to use the n parameter to generate multiple candidate outputs per evaluation, reducing variance and improving optimization results through best-of-k selection.
- [Chaining optimizers](https://www.comet.com/docs/opik/development/optimization-runs/advanced/chaining_optimizers.md): Run multiple optimizers in sequence to balance exploration and fine-tuning.
- [Opik Agent Optimizer API Reference](https://www.comet.com/docs/opik/development/optimization-runs/advanced/api_reference.md): Technical SDK reference guide