🧠 PromptStream.AI

---

🧩 Description

PromptStream.AI — Token-aware prompt composition, validation, and conversational context toolkit for .NET.

Built atop Flow.AI.Core and TokenFlow.AI,
PromptStream.AI enables developers to compose, validate, generate, and manage multi-turn AI prompts with token budgeting, interpolation, and contextual memory.

---

⚙️ Key Features

• 🧩 Token-aware prompt builder with variable interpolation ({{variable}} syntax)
• ✅ Validation engine for token limits, structure, and completeness
• 💬 Shared Core Models from Flow.AI.Core (PromptTemplate, PromptInstance, PromptMessage, PromptResponse)
• 🧠 Context manager with replay, merge, summarization, and JSON persistence
• 💾 Persistent context storage (ToJson / LoadFromJson)
• 🧮 Token budgeting tools (EstimateTokenUsage, TrimToTokenBudget)
• ⚡ CLI utility (PromptStream.AI.CLI) for building, validating, analyzing, and generating prompts
• 🔌 Seamless integration with TokenFlow.AI for model-aware tokenization

---

🚀 Installation

dotnet add package PromptStream.AI

Requires:

• .NET 8.0 or higher
• Flow.AI.Core v0.2.0+
• (optional) TokenFlow.AI for advanced token metrics

---

🧠 Quickstart Example

using System;
using System.Collections.Generic;
using Flow.AI.Core.Models;
using Flow.AI.Core.Interfaces;
using TokenFlow.AI.Integration;
using PromptStream.AI.Services;

// Initialize the service with token tracking
var tokenProvider = new BasicTokenFlowProvider();
var modelClient = new TokenFlowModelClient("gpt-4o-mini");
var context = new PromptContextManager();

var service = new PromptStreamService(tokenProvider, context, modelClient);

// Define a shared Core template
var template = new PromptTemplate
{
    Id = "summarize-v1",
    Template = "Summarize the following:\n\n{{input}}\n\nBe concise.",
    RequiredVariables = new() { "input" }
};

// Variables to inject
var variables = new Dictionary<string, string>
{
    ["input"] = "Flow.AI enables composable AI workflows for .NET developers."
};

// Build and validate
var (instance, validation) = service.BuildAndValidate(template, variables);

if (validation.IsValid)
{
    Console.WriteLine($"✅ Valid prompt ({validation.TokenCount} tokens)");
    Console.WriteLine(instance.RenderedText);
}
else
{
    Console.WriteLine($"❌ Invalid: {string.Join(", ", validation.Errors)}");
}

// Add a user message to the context
context.AddMessage(new PromptMessage { Role = "user", Content = instance.RenderedText });

---

💻 CLI Usage (PromptStream.AI.CLI)

PromptStream.AI includes a full command-line interface for developers to build, validate, analyze, and generate prompts directly from the terminal.

🧩 Build a prompt

dotnet run --project src/PromptStream.AI.CLI/PromptStream.AI.CLI.csproj -- build --template "Hello {{name}}" --var name=Andrew

✅ Validate a prompt

dotnet run --project src/PromptStream.AI.CLI/PromptStream.AI.CLI.csproj -- validate --template "Summarize {{topic}}" --var topic="AI in .NET"

🤖 Generate a model response

dotnet run --project src/PromptStream.AI.CLI/PromptStream.AI.CLI.csproj -- generate --template "Explain {{concept}}" --var concept="tokenization" --save context.json

🧠 Manage conversation context

dotnet run --project src/PromptStream.AI.CLI/PromptStream.AI.CLI.csproj -- context --load context.json --summarize

📊 Analyze prompt usage

dotnet run --project src/PromptStream.AI.CLI/PromptStream.AI.CLI.csproj -- analyze --template "Summarize {{topic}}" --var topic="AI" --model gpt-4o-mini

Available commands:

Command	Description
build	Render a prompt with variable substitution
validate	Validate prompt completeness and token limits
generate	Build, validate, and produce a model-like response
context	Load, save, summarize, or clear conversation context
analyze	Estimate token usage and cost for prompts

---

🌟 Supporting the Project

If you find PromptStream.AI helpful, please consider
⭐ starring the repository and ☕ supporting my work.
Your support helps keep the Flow.AI ecosystem growing.

---

Part of the Flow.AI Ecosystem
© 2025 Andrew Clements