Skip to content

Product Requirements Document

Jump to bottom
Chris Booth edited this page Feb 20, 2024 · 43 revisions

Product Requirement Document for InferGPT

1. Purpose

The purpose of this document is to outline the product requirements for InferGPT, a personalized AI agent designed to understand and predict users' needs effectively, facilitating deep personal interactions, goal setting, task execution, and personalized recommendations.

2. Product Overview

InferGPT aims to be an AI that personalizes interactions based on the user's specific data, facilitating a seamless and intuitive experience. See repo readme and home wiki for more details.

3. Target Demographic & Sector

Initially start as a Financial assistant to keep the scope narrow, but keep in mind our approach should then work for any direction the user wishes to send InferGPT and therefore be general.

See graph ontology example: {Example} and especially voyager paper for how InferGPT can learn new skills in unfamiliar domains.

4. Onboarding

Get up to speed with current research and agent designs:

5. Features and User Stories

a. Data Ingestion

User Story: As a user, I want the AI to access my data from various sources so that it can understand me better.

Task: Enable InferGPT to pull data from local folders

Inspiration: AutoGen

Task: Create an onboarding conversation flow that gathers some high-level info about the user. e.g "What would you like me to know about you first, or I can help you set a goal and go from there?"

Task: Develop a secure API integration framework to pull data from designated data sources.

Task: Implement user permission protocols for data access.

b. Conversational Inference

User Story: As a user, I want to be able to easily from various sources so that they can understand me better. Task: Create front end

Inspiration:

Task: Front end should have the ability to type messages & select model usage.

Task: The front end should display what it's thinking, what phase of action it's at, and how many questions it needs to ask before it's confident in its response/task and source of information.

Inspiration::

Task: Create a feedback loop to refine AI's understanding based on user interactions.

c. Multi-Agents & architecture

User Story: As a user, I want the AI to perform complex tasks on my behalf and be personalised to my situation.

Task: Explore and decide on agent frameworks:

Inspiration

Task stream chain of thought to terminal

Task: Create Director Agent

Inspiration

Tools

  • Automatic Curriculum
  • Canvas

Task: Create Planner Agent

Tools

  • Next best question

Task: Create Memory Agent

Inspiration Text to Cypher

d. Neo4j Knowledge graph

User Story: As an AI, to be able to infer the next best question, personalise, and remember conversations and other functions, I'll need a memory.

Task: Create a knowledge graph that stores and processes personal user data. Task: Support text to cypher llm that can manage ontology, database and read/write to store. Task: Support goal setting with tracking and reminders. Task: Support next best question inference

Task: Create Data Agent

Task: Create Synthiser Agent

Inspiration Evo Ninja AutoGen

Task: Create Skill library & self verify AI User Story: As an AI, I need to be able to adapt to unseen situations. This will require creating a new custom agent, tool or skill to achieve my task. Voyager

Task: Create Automatic Curriculum AI User Story: As an AI, I need a progressive increase in difficulty to enable a manageable learning process, so I should provide myself with a steady stream of new tasks and challenges to achieve a given task or goal. Voyager

e. Task Execution

User Story: As a user, I want the AI to perform tasks on my behalf.

Task: Build a task management Canvas that the AI can use to execute user commands.

Inspiration:

  • Evo Ninja
  • AutoGen
  • CrewAI

Task: Create a reporting system for task outcomes.

f. Next Best Question

User Story: As a user, I want the AI to be very clear on my intent and if in doubt, ask questions to check understanding before responding with an answer or carrying out a task.

Task: Design an inference engine that utilizes the knowledge graph for deep understanding.

6. Acceptance Criteria

The AI should be able to:

  • have a JSON list of agents that can be switched on and off (fed into director agent)
  • clarify intent or task within a reasonable amount of questions (# to be defined - estimated 3 to 10)
  • ingest data from approved sources with user consent.
  • Maintain a conversational context and recall previous interactions.
  • perform designated tasks as instructed by the user.
  • create new agents and skills if tasked to action in an area it's unfamiliar with
  • Use APIs or local LLMs
  • The AI should be able to compete and be benched on public AI agent benchmarks

7. Benchmarking

Other benchmarks to consider: GAIA

8. Dependencies

  • Data Privacy Laws and Regulations
  • Third-Party Data Source APIs
  • Open AI / Hardware / Cloud requirements for running LLMs
  • Neo4j Desktop or cloud

9. Out of Scope

  • Any data source integrations without user consent****
  • Actions beyond the agreed-upon user permissions****

10. Risks

  • Data breaches and privacy concerns
  • User reliance on AI for decision-making
  • It becomes ASI /s

11. Future Enhancements

  • Local models / Ollama
  • Expansion of data sources
  • Predictive Needs / Forecast intent
  • Recommend Actions
  • Security: Ensure all data is encrypted and handled according to privacy laws.
  • Scalability: Design the system to handle an increasing amount of user data and interactions.
  • Performance: Optimize response times for real-time interaction.
  • Self Rewarding Language Models
  • Multi-agent performance AI Agents is all you need
Clone this wiki locally