Crate briefcase_ai 

Briefcase AI Python Bindings

Python FFI bindings for the Briefcase AI core library, providing high-performance AI observability, replay, and decision tracking for Python applications.

Features

• AI Decision Tracking: Capture inputs, outputs, and context for every AI decision
• Deterministic Replay: Reproduce AI decisions exactly with full context preservation
• Cost Management: Track and optimize AI model usage costs
• Drift Detection: Monitor model performance and behavior changes
• Data Sanitization: Built-in privacy controls for sensitive data
• Multiple Storage Backends: SQLite, cloud storage, and custom backends

Installation

pip install briefcase-ai

Usage

import briefcase_ai

# Initialize the library
briefcase_ai.init()

# Create a decision snapshot
decision = briefcase_ai.DecisionSnapshot("ai_function")
decision.add_input(briefcase_ai.Input("query", "Hello world", "string"))
decision.add_output(briefcase_ai.Output("response", "Hello back!", "string"))

# Save to storage
storage = briefcase_ai.SqliteBackend.in_memory()
decision_id = storage.save_decision(decision)