[Docs] Prompt management Post-app structure

docs/README.md

@@ -52,3 +52,4 @@ By inserting to these formatting conventions, you'll maintain the integrity and
 ## Notes
 
 - Do not update any libraries or packages as this could disrupt the template structure and cause it to break.
+- Please use kebab-case (this-way) instead of snake_case for naming files and folders

docs/docs/prompt-management/01-overview.mdx

@@ -0,0 +1,115 @@
+---
+title: "Overview"
+---
+
+```mdx-code-block
+import DocCard from '@theme/DocCard';
+import clsx from 'clsx';
+
+```
+
+## What is prompt management?
+
+Building LLM-powered applications is an iterative process. In each iteration, you aim to improve the application's performance by refining prompts, adjusting configurations, and evaluating outputs.
+
+<img
+  style={{ width: "75%", display: "block", margin: "0 auto" }}
+  src="/images/prompt_management/llm_lifecycle.png"
+/>
+
+A prompt management system provides you the tools to do this process systematically by:
+
+- **Versioning Prompts**: Keeping track of different prompts you've tested.
+- **Linking Prompt Variants to Experiments**: Connecting each prompt variant to its evaluation metrics to understand the effect of changes and determine the best variant.
+- **Publishing Prompts**: Providing a way to publish the best prompt variants to production and maintain a history of changes in production systems.
+- **Associating Prompts with Traces**: Monitoring how changes in prompts affect production metrics.
+
+## Capabilities in agenta
+
+Agenta enables you to create **prompts** both from the **web UI** and **from code**. It allows you to publish these **prompts** to **endpoints** with specific environment names and version them. Additionally, it allows you to **run evaluations** from the web UI and code on these prompts and connect their results and **observability** to the respective version.
+
+## Why do I need a prompt management system?
+
+A prompt management system enables everyone on the team—from **product owners** to **subject matter experts**—to collaborate in creating prompts. Additionally it helps you answer the following questions:
+
+- Which prompts have we tried?
+- What were the outputs of these prompts?
+- How do the evaluation results of these prompts compare?
+- Which prompt was used for a specific generation in production?
+- What was the effect of publishing the new version of this prompt in production?
+- Who on the team made changes to a particular prompt in production?
+
+## Configuration management in agenta
+
+Agenta goes beyond prompt management to encompass the entire configuration of your LLM applications. If your LLM workflow is more complex than a single prompt (e.g., Retrieval-Augmented Generation (RAG) or a chain of prompts), you can version the whole configuration together.
+
+In contrast to a **prompt**, a **configuration** of an LLM application can include additional parameters beyond prompt templates and models (with their parameters). For instance:
+
+- An LLM application using a **chain of two prompts** would have a configuration that includes the two prompts and their respective model parameters.
+- An application that includes a **RAG pipeline** would have a configuration that includes parameters such as `top_k` and `embedding`.
+
+```json title="Example RAG configuration"
+{
+  "top_k": 3,
+  "embedding": "text-embedding-3-large",
+  "prompt-query": "We have provided context information below. {context_str}. Given this information, please answer the question: {query_str}\n",
+  "model-query": "openai/gpt-o1",
+  "temperature-query": "1.0"
+}
+```
+
+Agenta enables you to version the entire **configuration** of the LLM app as a unit. This is essential because there is a dependency between the parts of the configuration. For instance, in a chain of two prompts, changes to the first prompt depend on changes to the second prompt. Therefore, you need to version them together to ensure consistency and traceability.
+
+### Get started
+
+<section className='row'>
+<article key='1' className="col col--6 margin-bottom--lg">
+
+  <DocCard
+    item={{
+      type: "link",
+      href: "/prompt-management/quick-start",
+      label: "Quick start",
+      description: "Create a prompt from the web UI, publish it to an endpoint, and integrate it into your code",
+    }}
+  />
+  </article>
+
+  <article key='2' className="col col--6 margin-bottom--lg">
+  <DocCard
+    item={{
+      type: "link",
+      href: "/prompt-management/prompt-engineering-in-the-playground",
+      label: "Using the playground",
+      description: "Perform prompt engineering in the playground",
+    }}
+  />
+  </article>
+  </section>
+
+### Configuration lifecycle management
+
+  <section className='row'>
+
+<article key="1" className="col col--6 margin-bottom--lg">
+  <DocCard
+    item={{
+      type: "link",
+      href: "/prompt-management/how-to-publish-a-prompt",
+      label: "Publishing a prompt",
+      description: "How to publish a prompt to an endpoint from the web UI.",
+    }}
+  />
+</article>
+
+<article key='2' className="col col--6 margin-bottom--lg">
+  <DocCard
+    item={{
+      type: "link",
+      href: "/prompt-management/how-to-use-a-prompt",
+      label: "How to use a prompt",
+      description: "How to use a published a prompt in your code",
+    }}
+    />
+  </article>
+  </section>

docs/docs/prompt-management/02-quick-start.mdx

@@ -0,0 +1,113 @@
+---
+title: "Quick Start"
+---
+
+## Introduction
+
+In this tutorial, we will **create a prompt** in the web UI, **publish** it to a deployment, **integrate** it with our code base.
+
+:::note
+If you want to do this whole process programatically, jump to [this guide](/prompt-management/prompt-management-from-sdk)
+:::
+
+## 1. Create a prompt
+
+We will create a prompt from the web UI. This can be done simply by going to the app overview, clicking on create a prompt. You have here the choice between using a chat prompt or a text prompt:
+
+- A text prompt is useful for single turn LLM applications such as question answering, text generation, entity extraction, and classification, etc.
+- A chat application is designed for multi-turn applications like chatbots.
+
+<img
+  style={{ width: "80%", display: "block", margin: "0 auto" }}
+  src="/images/prompt_management/create-prompt-modal.png"
+/>
+<br />
+
+## 2. Publish a variant
+
+You can create in each LLM application multiple variants. You can think of variants as git branches. Each variant is versioned with each variant version having it's own commit number and being immutable.
+
+When you are satified with a commit (after evaluating it for instance) you can publish it to a deployment. The deployment is tagged with an environment (`production`, `development` or `staging`) and provides you access to endpoint for both the published configuration and to a proxy for the calls.
+
+To publish a variant, go to overview, click on the three dots on the **variant** that you want to publish and select Deploy (see screenshto)
+
+<img
+  style={{ width: "75%", display: "block", margin: "0 auto" }}
+  src="/images/prompt_management/deploy-action.png"
+/>
+<br />
+You can select now which deployments you want to publish the variant to
+
+<img
+  style={{ width: "75%", display: "block", margin: "0 auto" }}
+  src="/images/prompt_management/deployment-modal.png"
+/>
+
+<br />
+:::caution
+
+New change
+to the **variant** will not be automaticly published to the **deployment** unless
+we explicitly **publish it**.
+
+The reason is that we have published the last **version**/**commit** of the **variant** to
+that deployment and not the **variant** itself!
+
+:::
+
+## 3. Integrate with your code
+
+To see the code snippet needed to use the prompt, click on the name of the deployment and you will see a drawer with the integration code. For example for python
+
+```python
+import agenta as ag
+from agenta import DeploymentManager, PromptManager
+
+# os.environment["AGENTA_API_KEY"] = "ag-xxx"
+# os.environment["AGENTA_PROJECT_ID] = "ag-xxx"
+ag.init()
+
+# fetch the deployment (id)
+deployment = DeploymentManager.get_deployment_by_name(deployment_name="production",
+                                                      app_slug="my-app")
+# fetch latest configuration deployed here
+prompt_obj = PromptManager.get_from_registry(deployment_id=deployment.id)
+```
+
+The prompt object will have both the information about the configuration version and the data (under the field data)
+
+```python
+{
+ variant_slug: "my-variant",
+ app_slug: "my-app""
+ version: 3,
+ commit-id: "afae3232",
+ data: {
+    'temperature': 1.0,
+    'model': 'gpt-3.5-turbo',
+    'max_tokens': -1,
+    'prompt_system': 'You are an expert in geography.',
+    'prompt_user': 'What is the capital of {country}?',
+    'top_p': 1.0,
+    'frequence_penalty': 0.0,
+    'presence_penalty': 0.0,
+    'force_json': 0
+}
+```
+
+## 4. Revert to previous deployment (optional)
+
+:::note
+This feature is only available in cloud and enterprise version
+:::
+
+Optionally you would like to revert to a previously published commit. For this click on the deployment in the overview view, then click on **history**, you will see all the previous published version. You can revert to a previous version by clicking on revert.
+
+<img
+  style={{ width: "75%", display: "block", margin: "0 auto" }}
+  src="/images/prompt_management/revert-deployment.png"
+/>
+
+## Next steps
+
+Now that you've created and published your first prompt, you can learn how to do [prompt engineering in the playground](/prompt_management/prompt_engineering) or dive deeper into [the capabilities of the prompt management SDK](/prompt-management/the-sdk)

docs/docs/prompt_management/01-concepts.mdx → docs/docs/prompt-management/07-concepts.mdx

@@ -2,50 +2,6 @@
 title: "Core Concepts"
 ---
 
-# Core Concepts
-
-This page describes the main concepts used in prompt management in **agenta**.
-
-## Prompt and Configuration Management
-
-### What Is Prompt Management?
-
-Building LLM-powered applications is an iterative process. In each iteration, you aim to improve the application's performance by refining prompts, adjusting configurations, and evaluating outputs.
-
-<img
-  style={{ width: "75%", display: "block", margin: "0 auto" }}
-  src="/images/prompt_management/llm_lifecycle.png"
-/>
-
-A prompt management system provides you the tools to do this process systematically by:
-
-- **Versioning Prompts**: Keeping track of different prompts you've tested.
-- **Linking Prompt Variants to Experiments**: Connecting each prompt variant to its evaluation metrics to understand the effect of changes and determine the best variant.
-- **Publishing Prompts**: Providing a way to publish the best prompt variants to production and maintain a history of changes in production systems.
-- **Associating Prompts with Traces**: Monitoring how changes in prompts affect production metrics.
-
-### Why Do I Need a Prompt Management System?
-
-A prompt management system enables everyone on the team—from product owners to subject matter experts—to collaborate in creating prompts. Additionally it helps you answer the following questions:
-
-- Which prompts have we tried?
-- What were the outputs of these prompts?
-- How do the evaluation results of these prompts compare?
-- Which prompt was used for a specific generation in production?
-- What was the effect of publishing the new version of this prompt in production?
-- Who on the team made changes to a particular prompt in production?
-
-### What Is the Difference Between Prompt and Configuration Management?
-
-Agenta goes beyond prompt management to encompass the entire configuration of your LLM applications.
-
-**Prompts** are a special case of a **configuration**. A **prompt** includes the prompt template, the model, and the model parameters. However, a **configuration** of an LLM application can include additional parameters.
-For instance, an LLM application using a chain of two prompts would have a configuration that includes the two prompts and their respective model parameters. Similarly, an application that includes a RAG pipeline would have a configuration that includes parameters such as `top_k` and `embedding`.
-
-Agenta enables you to version the entire `configuration` of the LLM app as a unit. This makes sense since there is a dependency between the parts of the configuration. For instance in a chain of two prompts, the changes of the first depend on the changes of the second. Therefore you need to version them together to ensure consistency and traceability.
-
-## Taxonomy of Terms and Concepts in agenta
-
 Below are the description to the main terms and concepts used in agenta.
 
 <img