> ## Documentation Index
> Fetch the complete documentation index at: https://docs.athina.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting Started Guides

<Info>
  It might be helpful to start by reading this: [Athina Platform: Overview and
  Concepts](/overview)
</Info>

<Info>
  If you don't have an Athina account yet, then start by [signing up and
  inviting your team](/getting-started)
</Info>

<Accordion title="Prompts">
  * [Create and commit your first Prompt
    Template](https://app.arcade.software/share/icJcCoSFPCNVtn5MOZr4)
</Accordion>

<Accordion title="Flows">
  * [Create and share your first Flow](/guides/flows/create-and-share-flow) `TODO`
</Accordion>

<Accordion title="Observability">
  * [Log a sample LLM inference (Python Notebook)](https://app.athina.ai/apps/e84e6813-d4a0-45eb-bcc9-92875185d354/share)
  * [Configure an online eval](https://app.arcade.software/share/1cUg62VlOnuYxIsuPq3c)
  * [Re-run LLM calls with a different prompt or model](https://app.arcade.software/share/7uxRrTfcMfzy3V4I1jwz)
  * [View analytics and compare different segments](/guides/overview) `TODO`
  * [Create a dataset from your logs](/datasets/create-dataset/create-dataset-from-logs)
  * [Export your logs](/guides/overview) `TODO`
</Accordion>

<Accordion title="Datasets">
  * [Getting started: Datasets Overview & Concepts](/datasets/)
  * [Creating a dataset](/datasets/create-dataset/create-dataset)
  * [Running an offline eval in Athina IDE](/datasets/run-eval)
  * [Running a prompt column in Athina IDE](/datasets/dynamic-columns/dynamic-columns-run-prompt)
  * [Running dynamic columns in Athina IDE](/datasets/dynamic-columns/dynamic-columns)
  * [Running an experiment in Athina IDE](/datasets/run-experiment)
</Accordion>

***

<Accordion title="Other Guides">
  #### Experimentation

  * [Comparing different models and prompts](/guides/datasets/comparing-models)
  * [Comparing different datasets side-by-side](/guides/datasets/comparing-datasets)
  * [Prototyping a prompt chain in 3 mins without writing code](/guides/datasets/prototype-and-evaluate-prompt-chain)

  #### Evaluation

  * [RAG Evaluation: A Guide](/guides/evals/rag-eval-guide)
  * [Measure and Improve retrieval in your RAGs](/guides/evals/measuring-retrieval-accuracy-in-rag)
  * [LLM-as-a-Judge Evaluation](/api-reference/evals/custom-evals/custom-prompt)
  * [Pairwise Evaluation](/api-reference/evals/custom-evals/pairwise-evaluation)

  #### Evaluation Best Practices

  * [Improving eval performance](/guides/evals/improving-eval-performance)
  * [Different stages of evaluation](/guides/evals/llm-eval-workflows)

  #### Safeguarding

  * [Prompt Injection: Attack and Defense](/guides/evals/prompt-injection)
  * [Running evals as real-time guardrails](/guides/evals/running-evals-guardrails)
</Accordion>