Initial scope of lessons - placeholders added

.env.sample

@@ -0,0 +1,29 @@
+
+# For GitHub Marketplace Deployments
+# -----------------------------------------
+# These are standardized names (Sep 16, 2024) 
+# from https://github.com/marketplace/models
+# -----------------------------------------
+GITHUB_TOKEN=
+GITHUB_MODEL_DEPLOYMENT=
+SERVERLESS_KEY=${GITHUB_TOKEN}
+
+# For Azure OpenAI Deployments
+AZURE_OPENAI_ENDPOINT=
+AZURE_OPENAI_KEY=
+AZURE_OPENAI_DEPLOYMENT=
+
+# For OpenAI Deployments
+OPENAI_ENDPOINT=
+OPENAI_KEY=
+OPENAI_DEPLOYMENT=
+OPENAI_ORGANIZATION=
+OPENAI_PROJECT=
+
+# For Azure Serverless Deployments
+AZURE_SERVERLESS_ENDPOINT=
+AZURE_SERVERLESS_KEY=
+AZURE_SERVERLESS_DEPLOYMENT=
+
+# API VERSION
+API_VERSION=

.gitignore

@@ -0,0 +1 @@
+.env

docs/1. Core Concepts/01.md

@@ -1 +1,21 @@
-# 1. Motivation
+# 1. Introduction
+
+Building production-ready generative AI applications involves 3 stages:
+
+- **Ideation** - rapid prototyping, testing apps with simple test prompts.
+- **Augmentation** - evaluation, testing quality & safety with larger datasets.
+- **Operationalization** - deploying apps and monitoring them for insights.
+
+The challenge is in providing developers with a developer experience and tooling support to streamline these stages - without requiring a massive learning curve in new semantics, model-specific APIs or plaform-specific SDKs. 
+
+What if we could make the **prompt** the central unit of development - and build tooling to build agency and observability around it? That's the vision behind Prompty. Watch this Microsoft Build 2024 session for a deeper dive into end-to-end AI development using Prompty and AI Studio.
+
+
+
+Using Prompty you can:
+
+ - **Design Prompts** - Create & refine prompt templates in an IDE
+ - **Explore Models** - Configure model parameters, diverse deployments
+ - **Execute Prompts** - Use built-in tools and custom runtimes to test prompts
+ - **Observe Traces** - Use built-in features to track and debug execution
+ - **Compose Apps** - Chain and compose Prompty assets for complex flows

docs/2. Prompty Quickstart/01.md

@@ -1 +1 @@
-# 
+# Create Prompty

docs/2. Prompty Quickstart/02.md

@@ -1 +1 @@
-# 
+# Configure Models

docs/2. Prompty Quickstart/03.md

@@ -1 +1 @@
-# 
+# Create Sample

docs/2. Prompty Quickstart/04.md

@@ -0,0 +1 @@
+# Run Prompty

docs/3. Prompt Engineering/01.md

@@ -1 +1 @@
-# 
+# System Context

docs/3. Prompt Engineering/02.md

@@ -1 +1 @@
-# 
+# Prompt Instructions

docs/3. Prompt Engineering/03.md

@@ -1 +1 @@
-# 
+# Model Parameters

docs/3. Prompt Engineering/04.md

@@ -0,0 +1 @@
+# Add Data

docs/4. Model Choice/01.md

@@ -1 +1 @@
-# 
+# Open AI

docs/4. Model Choice/02.md

@@ -1 +1 @@
-# 
+# Azure Open AI

docs/4. Model Choice/03.md

@@ -1 +1 @@
-# 
+# Azure Serverless

docs/4. Model Choice/04.md

@@ -0,0 +1 @@
+# GitHub Marketplace

docs/5. Observability/01.md

@@ -1 +1 @@
-# 
+# Prompty Tracing

docs/5. Observability/02.md

@@ -1 +1 @@
-# 
+# Trace Decorators

docs/5. Observability/03.md

@@ -1 +1 @@
-# 
+# Trace Runs

docs/5. Observability/04.md

@@ -0,0 +1 @@
+# Open Telemetry

docs/6. Testing/01.md

@@ -1 +1 @@
-# 
+# Hardcoded Input

docs/6. Testing/02.md

@@ -1 +1 @@
-# 
+# Sample File

docs/6. Testing/03.md

@@ -1 +1 @@
-# 
+# Commandline Input

docs/6. Testing/04.md

@@ -0,0 +1 @@
+# Function Call

docs/7. Compostion/01.md

@@ -1 +1 @@
-# 
+# Prompty + Data Binding

docs/7. Compostion/02.md

@@ -1 +1 @@
-# 
+# Prompty + RAG Pattern

docs/7. Compostion/03.md

@@ -1 +1 @@
-# 
+# Prompty + Evaluation

docs/7. Compostion/04.md

@@ -0,0 +1 @@
+# Prompty + Multi-Agent

docs/8. Evaluation/01.md

@@ -1 +1 @@
-# 
+# AI-Assisted Evaluation

docs/8. Evaluation/02.md

@@ -1 +1 @@
-# 
+# Evaluation Metrics

docs/8. Evaluation/03.md

@@ -1 +1 @@
-# 
+# Evaluation Test Data

docs/8. Evaluation/04.md

@@ -0,0 +1 @@
+# Evaluation Workflow

docs/index.md

@@ -1,19 +1,33 @@
 # Welcome
 
-[Prompty](https://prompty.ai) is a new type of **executable asset** that provides agency with observability during the **ideation** phase of your generative AI application development lifecycle.
+By [definition](https://prompty.ai), Prompty is _a new asset class and format for LLM prompts that aims to provide observability, understandability, and portability for developers._ In this workshop, we explore what this means from core concepts to prompty prototyping in a series of hands-on labs.
 
-Using Prompty you can:
+## Learning Objectives
 
- - **Design Prompts** - Create & refine prompt templates in an IDE
- - **Explore Models** - Configure model parameters, diverse deployments
- - **Execute Prompts** - Use built-in tools and custom runtimes to test prompts
- - **Observe Traces** - Use built-in features to track and debug execution
- - **Compose Apps** - Chain and compose Prompty assets for complex flows
+The workshop is structured as a series of hands-on labs taking you from core concepts to prompt evaluation and composition, with code. On completion, you should be able to describe:
 
+1. What Prompty is and the benefits it offers
+2. How to create and execute a simple Prompty asset
+4. How to choose and configure models for your prompt
+3. How to engineer prompts for different scenarios
+5. How to instrument Prompty assets for observability
+6. How to evaluate prompts to assess quality and safety
+7. How to compose Prompty assets for complex flows
 
-## Learning Objectives
+## Pre-Requisites
+
+To complete these labs you will need:
+
+1. A personal GitHub account (create one [for free](https://github.com/signup))
+1. A Microsoft Azure account (create one [for free](https://azure.microsoft.com/free/))
+1. Basic familiarity with Python syntax and tools
+1. Basic familiarity with Generative AI concepts
+1. Basic familiarity with Visual Studio Code tooling
+
+
+## Learning Modules
 
-By the end of the workshop, you should be able to have a better understanding of the following:
+The workshop is organized into modules, each focused on one topic and containing a series of hands-on lab units. Click the module title to see details of the units.
 
 ??? note "1. Core Concepts"
     - Prompty Specification
@@ -68,8 +82,17 @@ By the end of the workshop, you should be able to have a better understanding of
     - By running evaluators with adversarial data
     - By assessing safety with adversarial data
 
-## Related Resources
+## Learning Resources
+
+Bookmark and explore these resources:
+
+- [Documentation](https://prompty.ai/) - official documentation, in-progress.
+- [Repository](https://github.com/microsoft/prompty) - open-source repository.
+- [Prompty in Promptflow](https://microsoft.github.io/promptflow/tutorials/prompty-quickstart.html#) - with [examples](https://github.com/microsoft/promptflow/tree/main/examples/prompty)
+
+
+Watch the Microsoft Build 2024 session for a practical tour of end-to-end usage.
+
+<iframe width="800" height="450" src="https://www.youtube.com/embed/HALMFU7o9Gc" title="Practical End-to-End AI Development using Prompty and AI Studio | BRK114" frameborder="0" allowfullscreen></iframe>
+
 
-- Prompty Documentation
-- Prompty Templates
-- Prompty Videos

src/02-prompty-quickstart/00-azure-openai.prompty

@@ -0,0 +1,40 @@
+---
+name: ExamplePrompt
+description: A prompt that uses context to ground an incoming question
+authors:
+  - Seth Juarez
+model:
+  api: chat
+  configuration:
+    type: azure_openai
+    azure_endpoint: ${env:AZURE_OPENAI_ENDPOINT}
+    azure_deployment: <your-deployment>
+    api_version: 2024-07-01-preview
+  parameters:
+    max_tokens: 3000
+sample:
+  firstName: Seth
+  context: >
+    The Alpine Explorer Tent boasts a detachable divider for privacy, 
+    numerous mesh windows and adjustable vents for ventilation, and 
+    a waterproof design. It even has a built-in gear loft for storing 
+    your outdoor essentials. In short, it's a blend of privacy, comfort, 
+    and convenience, making it your second home in the heart of nature!
+  question: What can you tell me about your tents?
+---
+
+system:
+You are an AI assistant who helps people find information. As the assistant, 
+you answer questions briefly, succinctly, and in a personable manner using 
+markdown and even add some personal flair with appropriate emojis.
+
+# Customer
+You are helping {{firstName}} to find answers to their questions.
+Use their name to address them in your responses.
+
+# Context
+Use the following context to provide a more personalized response to {{firstName}}:
+{{context}}
+
+user:
+{{question}}

src/02-prompty-quickstart/00-azure-serverless.prompty

@@ -0,0 +1,40 @@
+---
+name: Azure Serverless Prompty
+description: Basic chat prompt using n
+authors:
+  - Nitya Narasimhan
+model:
+  api: chat
+  configuration:
+    type: azure_serverless
+    azure_endpoint: ${env:AZURE_SERVERLESS_ENDPOINT}
+    azure_deployment: ${env:AZURE_SERVERLESS_DEPLOYMENT:gpt-4}
+    api_version:  ${env:API_VERSION}
+  parameters:
+    max_tokens: 3000
+sample:
+  firstName: Seth
+  context: >
+    The Alpine Explorer Tent boasts a detachable divider for privacy, 
+    numerous mesh windows and adjustable vents for ventilation, and 
+    a waterproof design. It even has a built-in gear loft for storing 
+    your outdoor essentials. In short, it's a blend of privacy, comfort, 
+    and convenience, making it your second home in the heart of nature!
+  question: What can you tell me about your tents?
+---
+
+system:
+You are an AI assistant who helps people find information. As the assistant, 
+you answer questions briefly, succinctly, and in a personable manner using 
+markdown and even add some personal flair with appropriate emojis.
+
+# Customer
+You are helping {{firstName}} to find answers to their questions.
+Use their name to address them in your responses.
+
+# Context
+Use the following context to provide a more personalized response to {{firstName}}:
+{{context}}
+
+user:
+{{question}}

src/02-prompty-quickstart/00-github-serverless.prompty

@@ -0,0 +1,40 @@
+---
+name: ExamplePrompt
+description: A prompt that uses context to ground an incoming question
+authors:
+  - Seth Juarez
+model:
+  api: chat
+  configuration:
+    type: serverless
+    endpoint: https://models.inference.ai.azure.com
+    model: Mistral-small
+    key: ${env:SERVERLESS_KEY:KEY}
+  parameters:
+    max_tokens: 3000
+sample:
+  firstName: Nitya
+  context: >
+    The Alpine Explorer Tent boasts a detachable divider for privacy, 
+    numerous mesh windows and adjustable vents for ventilation, and 
+    a waterproof design. It even has a built-in gear loft for storing 
+    your outdoor essentials. In short, it's a blend of privacy, comfort, 
+    and convenience, making it your second home in the heart of nature!
+  question: What can you tell me about tents?
+---
+
+system:
+You are an AI assistant who helps people find information. As the assistant, 
+you answer questions briefly, succinctly, and in a personable manner using 
+markdown and even add some personal flair with appropriate emojis.
+
+# Customer
+You are helping {{firstName}} to find answers to their questions.
+Use their name to address them in your responses.
+
+# Context
+Use the following context to provide a more personalized response to {{firstName}}:
+{{context}}
+
+user:
+{{question}}