====== Microsoft PromptFlow ======
**PromptFlow** is an open-source development framework created by Microsoft for building, evaluating, and deploying LLM-based applications through executable workflows called flows.((https://[[github|github]].com/microsoft/promptflow)) It connects LLMs, prompts, Python code, and external tools into directed acyclic graphs (DAGs) that can be tested, debugged, and iterated systematically. PromptFlow integrates tightly with Azure Machine Learning and [[microsoft_foundry|Microsoft Foundry]].

  * **[[github|GitHub]]:** [[https://github.com/[[microsoft|microsoft]]/promptflow|github.com/[[microsoft|microsoft]]/promptflow]]
  * **Available as:** VS Code extension, Python SDK, CLI, Azure portal
  * **License:** MIT

===== Core Concepts =====
**Flows** are executable workflows represented as DAGs where each node is one of:
  * **LLM Node:** Calls a language model (GPT-4, [[codex|Codex]], etc.) with a prompt template
  * **Python Node:** Runs custom Python code for data transformation or business logic
  * **Tool Node:** Invokes external APIs or services
  * **Prompt Node:** Manages prompt templates with variable substitution

Flows chain these nodes together, passing outputs from one as inputs to the next, creating reproducible pipelines for LLM application logic.

===== Prompt Engineering Workflows =====
PromptFlow supports a structured development lifecycle:((https://[[microsoft|microsoft]].[[github|github]].io/promptflow/))

  - **Initialization:** Define business use case, create basic flow with templates
  - **Experimentation:** Test flow on sample data, debug node-by-node with visual tools
  - **Evaluation:** Run batch evaluations on large datasets with built-in quality metrics
  - **Refinement:** Iterate on prompts, model selection, and parameters based on evaluation results
  - **Production:** Optimize, deploy, and monitor in production environment

The visual DAG editor makes complex [[prompt_engineering|prompt engineering]] accessible without deep coding expertise, while the SDK supports programmatic flow construction for advanced users.

===== Evaluation Capabilities =====
PromptFlow excels in systematic LLM application testing:((https://[[microsoft|microsoft]].[[github|github]].io/promptflow/))

  * **Batch evaluation:** Run flows against entire datasets to measure performance
  * **Built-in metrics:** Quality, relevance, groundedness, fluency scores
  * **A/B testing:** Compare different prompt versions or model configurations
  * **Prompt tuning:** Systematic optimization of prompt templates
  * **Experiment tracking:** Version and compare evaluation results over time

In [[microsoft_foundry|Microsoft Foundry]] (classic), additional features include advanced quality assessments and comprehensive tracking dashboards.

===== Azure Integration =====
PromptFlow is deeply embedded in the Microsoft Azure ecosystem:((https://microsoft.[[github|github]].io/promptflow/))

  * **Azure Machine Learning Studio:** Visual flow editor, managed compute, deployment
  * **[[microsoft_foundry|Microsoft Foundry]] (classic):** Enhanced evaluation, blue/green deployments, monitoring
  * **CI/CD Pipelines:** Direct integration with Azure DevOps and [[github|GitHub]] Actions
  * **Managed Endpoints:** One-click deployment to Azure-hosted inference endpoints

The cloud version handles backend complexity (compute, scaling, monitoring) while maintaining the same flow definitions used locally.

===== Local Development =====
  * **VS Code Extension:** Full visual editor with flow debugging and testing
  * **Python SDK:** Programmatic flow construction, evaluation, and deployment
  * **CLI:** Command-line tools for automation and CI/CD integration
  * Run identical flows locally and in the cloud

===== Code Example: PromptFlow DAG Definition =====
<code python>
from promptflow.core import tool, Prompty
from promptflow.client import PFClient

# Define individual tools (nodes) for the flow
@tool
def extract_keywords(text: str) -> liststr:
    """Extract key topics from input text."""
    stop_words = {"the", "a", "is", "in", "to", "and", "of", "for", "on", "with"}
    words = text.lower().split()
    return [w for w in words if len(w) > 3 and w not in stop_words]

@tool
def classify_intent(keywords: liststr) -> str:
    """Classify user intent based on extracted keywords."""
    intents = {
        "technical": ["code", "error", "debug", "api", "function", "deploy"],
        "billing": ["price", "cost", "subscription", "payment", "invoice"],
        "general": ["help", "question", "info", "about", "learn"],
    }
    for intent, triggers in intents.items():
        if any(kw in triggers for kw in keywords):
            return intent
    return "general"

@tool
def route_response(intent: str, original_text: str) -> dict:
    """Route to appropriate handler based on classified intent."""
    handlers = {
        "technical": "Routing to technical support team...",
        "billing": "Routing to billing department...",
        "general": "Routing to general assistant...",
    }
    return {
        "intent": intent,
        "handler": handlers.get(intent, handlers["general"]),
        "original_query": original_text,
    }

# Execute the DAG: extract_keywords -> classify_intent -> route_response
user_input = "I need help debugging an API error in my deployment"
keywords = extract_keywords(user_input)
print(f"Keywords: {keywords}")

intent = classify_intent(keywords)
print(f"Intent: {intent}")

result = route_response(intent, user_input)
print(f"Routing: {result}")

# To run as a full PromptFlow flow, define flow.dag.yaml:
flow_yaml = """
inputs:
  text:
    type: string
nodes:
  - name: extract_keywords
    type: python
    source: {type: code, path: flow_tools.py}
    inputs: {text: ${inputs.text}}
  - name: classify_intent
    type: python
    source: {type: code, path: flow_tools.py}
    inputs: {keywords: ${extract_keywords.output}}
  - name: route_response
    type: python
    source: {type: code, path: flow_tools.py}
    inputs: {intent: ${classify_intent.output}, original_text: ${inputs.text}}
outputs:
  result:
    value: ${route_response.output}
"""
print(f"\nFlow DAG YAML:\n{flow_yaml}")
</code>

===== Comparison to Alternatives =====
^ Aspect ^ PromptFlow ^ [[langchain|LangChain]] ^ [[haystack|Haystack]] ^
| **Paradigm** | Visual DAG flows | Code-first chains (LCEL) | Pipeline-based |
| **Evaluation** | Built-in batch eval, metrics | Requires custom scripting | LLM-based evaluation |
| **Accessibility** | Low-code visual editor | Developer-oriented | Developer-oriented |
| **Cloud** | Native Azure integration | Cloud-agnostic | Cloud-agnostic |
| **Best For** | Microsoft ecosystem teams | General LLM orchestration | Search/RAG pipelines |

===== See Also =====
  * [[promptfoo|Promptfoo]]
  * [[prompt_chaining|Prompt Chaining]]
  * [[flowise|Flowise]]
  * [[prompt_requests|Prompt Requests]]
  * [[system_prompt_architecture|System Prompt Architecture]]

===== References =====
===== Related Pages =====
  * [[langchain|LangChain]]
  * [[llamaindex|LlamaIndex]]
  * [[tool_integration_patterns|Tool Integration Patterns]]
  * [[retrieval_augmented_generation|Retrieval-Augmented Generation]]