Frequently Asked Questions (FAQ)

​

General

What is Future AGI?

• Future AGI is an AI lifecycle platform designed to support enterprises throughout their AI journey. It combines rapid prototyping, rigorous evaluation, continuous observability, and reliable deployment to help build, monitor, optimize, and secure generative AI applications.

How do I get started?

• You can get started by following our Quickstart Guide.

​

Evaluation

What types of evaluations can I perform?

• Future AGI supports a wide range of evaluations including Hallucination, Guardrails, RAG, etc. See the Evaluation Overview for more details.

How do I evaluate RAG applications?

• Refer to the guide on Evaluating RAG Applications.

​

Knowledge Base

How do I add documents to a Knowledge Base?

• You can add documents via the UI or using the SDK. See Create KB using UI and Create KB using SDK.

What file types are supported?

• PDF, DOCX, TXT, RTF, CSV, JSON, and more. Refer to the Knowledge Base Concepts.

​

Dataset

How can I import data?

• Data can be added manually, via file upload, SDK, or imported from Hugging Face. See the Adding Dataset section.

What are dynamic columns?

• Dynamic columns allow you to generate new data based on existing columns using prompts, API calls, code execution, etc. Learn more in Create Dynamic Column.

​

Experimentation

What is an Experiment in Future AGI?

• Experiments allow you to systematically compare different prompts, models, or parameters. See the Experimentation Overview.

How do I compare different models or prompts?

• You can set up experiments to run different configurations against your datasets and compare results using evaluations. See How To Experiment.

​

Prototype

What is the purpose of the Prototype section?

• Prototyping helps you iterate quickly on different versions of your AI application or prompt. See the Prototype Overview.

How do I choose a winning prototype?

• You can compare prototypes based on evaluations and select the best performing one. See Choose Winner.

​

Observe

What can I monitor with Observe?

• Observe helps monitor key metrics like latency, cost, token usage, and evaluation results over time. See the Observe Overview.

How do I set up alerts?

• Alerts can be configured to notify you about anomalies or issues based on defined thresholds. See Alerts and Monitors.

​

Tracing (Observability)

What is tracing used for?

• Tracing provides detailed visibility into the execution flow of your AI applications, helping debug issues and understand performance. See the Tracing Overview.

Which frameworks support auto-instrumentation?

• We support auto-instrumentation for frameworks like OpenAI, Langchain, LlamaIndex, and more. See Auto Instrumentation.

​

Optimization

How does Future AGI help optimize prompts or models?

• Optimization provides a structured, iterative approach to refining AI-generated outputs by systematically improving prompts. Unlike experimentation, which focuses on testing multiple prompt variations, optimization enhances prompt by adjusting its structure based on evaluation-driven feedback. See the Optimization Overview.

​

Prompt Workbench

How can the Prompt Workbench help me engineer prompts?

• The workbench provides tools to write, generate, and improve prompts. See the Prompt Workbench Overview.

​

Protect

What does the Protect feature guard against?

• Protect helps enforce safety rules like toxicity, PII detection, prompt injection, etc., in real-time. See the Protect Overview.