Learn how ABV's prompt management helps you build effective LLM applications.  Discover tools for tracking metrics, linking prompts to traces, and improving prompt quality over time.

Prompt Management Overview

Learn to manage, version, and track your LLM prompts with ABV.  Follow our getting-started guide for the Python SDK, TypeScript SDK, and API integration.

Get Started with Prompt Management

Learn about the ABV Prompts data model and how to effectively manage your prompts.  This document explains prompt objects, text and chat prompts, versioning, and the use of labels for seamless deployment and management.

ABV Prompts Data Model

 Role-Based Access Controls in ABV In ABV, version control & deployment of prompts is managed via versions and labels .  Each prompt version is automatically assigned a version ID .

Prompt Version Control

 As you create more prompts, you will often find yourself using the same snippets of text or instructions in multiple prompts.  To avoid duplication, you can compose prompts by referencing other prompts .

Prompt Composability

 Message Placeholders allow you to insert a list of chat messages ( \[{role "... ", content "...

Message Placeholders in Chat Prompts

 Get Started with Prompt Management enables A/B testing by allowing you to label different versions of a prompt (e. g.

A/B Testing of LLM Prompts

 ABV prompts are cached client-side in the SDKs, so there's no latency impact after the first use and no availability risk.  You can also pre-fetch prompts on startup to populate the cache or provide a fallback prompt.

Caching of Prompts in Client SDKs

 The prompt config in ABV is an optional arbitrary JSON object attached to each prompt that stores structured data such as model parameters (like model name, temperature), function/tool parameters, or JSON schemas.  This config is versioned together with the prompt and allows you to manage all parameters associated with a prompt in one place, making it easier to deploy, update, and track prompt behavior and performance across different versions and environments.

Prompt Config

 Prompts can be organized into virtual folders to group prompts with similar purposes.  To create a folder, add slashes ( / ) to a prompt name.

Prompt Folders

 The ABV API has high uptime and prompts are Caching of Prompts in Client SDKs in the SDKs to prevent network issues from affecting your application.  However, get prompt() / getPrompt() will throw an exception if No local (fresh or stale) cached prompt is available -> new application instance fetching prompt for the first time and network request fails -> networking or ABV API issue (after retries) To guarantee 100% availability, there are two options Pre-fetch prompts on application startup and exit the application if the prompt is not available.

Guaranteed Availability

 Linking prompts to Observability & Tracing enables tracking of metrics and evaluations per prompt version.  It's the foundation of improving prompt quality over time.

Link Prompts to Traces

Trace URLs

Prompt Management

Trace

ABV Developer Docs

Quickstart (Python SDK)

Quickstart (JS/TS SDK)

Observability & Tracing

Sessions

User Tracking

Environments

ABV Prompt Playground

Metadata

Trace IDs & Distributed Tracing

Log Levels

Comments on Objects

Masking of Sensitive LLM Data

Multi-Modality and Attachments

Event Queuing/Batching

Releases & Versioning

Sampling

Model Usage & Cost Tracking

Query Data

API & Data Platform (cloned)

Metrics API

Metrics API (cloned with children)

Custom Dashboards

Basic Features

Evaluation Overview

Scores Data Model

LLM-as-a-Judge

Human Annotation

Custom Scores

Dataset Runs Data Model

Datasets

Prompt Experiments

Remote Dataset Runs

Evaluations

Overview of ABV SDKs

Python SDK - Overview

Python SDK - Setup

Python SDK - Instrumentation

Python SDK - Evaluations

Python SDK - Advanced Usage

Python SDK - Troubleshooting

Python SDK

TypeScript SDK - Overview

TypeScript SDK - Setup

TypeScript SDK - Instrumentation

TypeScript SDK - Advanced Configuration

TypeScript SDK - Troubleshooting and FAQ

Cookbook: ABV JS/TS SDK

JS/TS SDK

SDKs

Metrics overview

Metrics

API & Data Platform overview

Export Data from UI

Export via Blob Storage Integration

Export for Fine-Tuning

Public API

Query Data via SDKs

API & Data Platform

Role-Based Access Controls in ABV

Audit Logs

Data Deletion

Data Retention

LLM Connections

SCIM & Organization-Key Scoped API Routes

Usage Alerts

Administration

Platform

API Reference

References

Python SDK (v3)

JS SDK

Security & Compliance Overview

More