Merge pull request #1359 from lgayhardt/pfignite24

AI Studio: Prompt flow overview update

Author: v-dirichards

articles/ai-studio/how-to/prompt-flow.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: conceptual
-ms.date: 5/21/2024
+ms.date: 11/19/2024
 ms.reviewer: yozen
 ms.author: lagayhar
 author: lgayhardt
@@ -23,14 +23,15 @@ Prompt flow is a development tool designed to streamline the entire development
 Prompt flow is available independently as an open-source project on [GitHub](https://github.com/microsoft/promptflow), with its own SDK and [VS Code extension](https://marketplace.visualstudio.com/items?itemName=prompt-flow.prompt-flow). Prompt flow is also available and recommended to use as a feature within both [Azure AI Studio](https://ai.azure.com) and [Azure Machine Learning studio](https://ml.azure.com). This set of documentation focuses on prompt flow in Azure AI Studio.
 
 Definitions:
+
 - *Prompt flow* is a feature that can be used to generate, customize, or run a flow.
 - A *flow* is an executable instruction set that can implement the AI logic.​​ Flows can be created or run via multiple tools, like a prebuilt canvas, LangChain, etcetera. Iterations of a flow can be saved as assets; once deployed a flow becomes an API. Not all flows are prompt flows; rather, prompt flow is one way to create a flow. 
 - A *prompt* is a package of input sent to a model, consisting of the user input, system message, and any examples. User input is text submitted in the chat window. System message is a set of instructions to the model scoping its behaviors and functionality.
 - A *sample flow* is a simple, prebuilt orchestration flow that shows how flows work, and can be customized. 
 - A *sample prompt* is a defined prompt for a specific scenario that can be copied from a library and used as-is or modified in prompt design. 
 
-
 ## Benefits of prompt flow
+
 With prompt flow in Azure AI Studio, you can:
 
 - Orchestrate executable flows with LLMs, prompts, and Python tools through a visualized graph.
@@ -42,7 +43,7 @@ With prompt flow in Azure AI Studio, you can:
 - Interactive authoring experience: Prompt flow provides a visual representation of the flow's structure, allowing you to easily understand and navigate projects. 
 - Variants for prompt tuning: You can create and compare multiple prompt variants, facilitating an iterative refinement process.
 - Evaluation: Built-in evaluation flows enable you to assess the quality and effectiveness of their prompts and flows.
-- Comprehensive resources: Prompt flow includes a library of built-in tools, samples, and templates that serve as a starting point for development, inspiring creativity and accelerating the process.
+- Comprehensive resources: Prompt flow includes a library of built-in tools, samples, and templates that serve as a starting point for development, inspiring creativity, and accelerating the process.
 
 ### Enterprise readiness
 
@@ -52,7 +53,6 @@ With prompt flow in Azure AI Studio, you can:
 
 With prompt flow in Azure AI Studio, you can unleash prompt engineering agility, collaborate effectively, and apply enterprise-grade solutions for successful LLM-based application development and deployment.
 
-
 ## Flow development lifecycle
 
 Prompt flow offers a well-defined process that facilitates the seamless development of AI applications. By using it, you can effectively progress through the stages of developing, testing, tuning, and deploying flows, ultimately resulting in the creation of fully fledged AI applications.
@@ -70,15 +70,14 @@ By following this structured and methodical approach, prompt flow empowers you t
 
 In Azure AI Studio, you can start a new flow by selecting a flow type or a template from the gallery. 
 
-:::image type="content" source="../media/prompt-flow/init-type-or-gallery.png" alt-text="Screenshot of example flow types and templates from the gallery." lightbox="../media/prompt-flow/init-type-or-gallery.png":::
+:::image type="content" source="../media/prompt-flow/type-or-gallery.png" alt-text="Screenshot of example flow types and templates from the gallery." lightbox="../media/prompt-flow/type-or-gallery.png":::
 
 Here are some examples of flow types:
 
 - **Standard flow**: Designed for general application development, the standard flow allows you to create a flow using a wide range of built-in tools for developing LLM-based applications. It provides flexibility and versatility for developing applications across different domains.
 - **Chat flow**: Tailored for conversational application development, the Chat flow builds upon the capabilities of the standard flow and provides enhanced support for chat inputs/outputs and chat history management. With native conversation mode and built-in features, you can seamlessly develop and debug their applications within a conversational context.
 - **Evaluation flow**: Designed for evaluation scenarios, the evaluation flow enables you to create a flow that takes the outputs of previous flow runs as inputs. This flow type allows you to evaluate the performance of previous run results and output relevant metrics, facilitating the assessment and improvement of their models or applications.
 
-
 ## Flows
 
 A flow in Prompt flow serves as an executable workflow that streamlines the development of your LLM-based AI application. It provides a comprehensive framework for managing data flow and processing within your application.
@@ -103,8 +102,7 @@ Each tool is a simple, executable unit with a specific function. By combining di
 
 One of the key benefit of Prompt flow tools is their seamless integration with third-party APIs and python open source packages. This not only improves the functionality of large language models but also makes the development process more efficient for developers.
 
-If the prompt flow tools in Azure AI Studio don't meet your requirements, you can follow [this guide](https://microsoft.github.io/promptflow/how-to-guides/develop-a-tool/create-and-use-tool-package.html) to develop your own custom tool and make it a tool package. To discover more custom tools developed by the open source community, visit [this page](https://microsoft.github.io/promptflow/integrations/tools/index.html).
-
+If the prompt flow tools in Azure AI Studio don't meet your requirements, you can [develop your own custom tool and make it a tool package](https://microsoft.github.io/promptflow/how-to-guides/develop-a-tool/create-and-use-tool-package.html). To discover more custom tools developed by the open source community, visit [prompt flow custom tools](https://microsoft.github.io/promptflow/integrations/tools/index.html).
 
 ## Next steps