Skip to content

suh004757/IntentGraph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

IntentGraph

IntentGraph is a model-agnostic framework for capturing, validating, and reusing human decision-making intelligence — beyond prompts, beyond any single LLM.

Prompts are consumable.
Intent, evidence, reasoning, and verification are assets.


Why IntentGraph?

Modern LLM platforms increasingly personalize and adapt to user behavior. While this improves short-term UX, the accumulated intelligence remains locked inside vendor platforms — not portable, not inspectable, not owned by the user.

IntentGraph is built on a simple premise:

If models change, prompts will break.
If reasoning is tied to language, it will expire.
Only structured intent and decisions survive.


Core Principles

1. Intent over Prompts

We treat human intent as the primary object — not chat logs or prompt text.

Intent is captured as:

  • goal
  • constraints
  • success criteria

This makes the data reusable across models, tools, and future agent architectures.


2. Language-Agnostic Reasoning

We do not store chain-of-thought or free-form reasoning text.

Instead, reasoning is abstracted into:

  • strategies
  • operations (classify, retrieve, decide, etc.)
  • decision rules
  • uncertainty registers

This abstraction survives:

  • different LLMs
  • non-language planners
  • rule engines
  • future world-model-based agents

3. Evidence as First-Class Data

Decisions are meaningless without grounds.

IntentGraph stores:

  • fact snapshots
  • official references
  • environment observations

Links alone are not enough. Key evidence fields are snapshotted for long-term validity.


4. Objective Verification Layers

Personal judgment is valuable — but insufficient.

Each decision is independently validated through:

  1. Fact Verification — Are factual claims supported?
  2. Intent Alignment — Does the output satisfy the declared goal and constraints?

Subjective evaluation sits on top of these objective layers, not instead of them.


5. Model and Vendor Independence

LLMs are treated as replaceable execution engines, not knowledge containers.

All stored assets are:

  • portable
  • inspectable
  • versioned
  • reusable

What IntentGraph Is Not

  • ❌ A prompt library
  • ❌ A chat log archive
  • ❌ A fine-tuning dataset tied to a single model
  • ❌ A chain-of-thought collector

IntentGraph is a decision intelligence ledger.


Core Data Model (Conceptual)

Intent ├─ Evidence ├─ Reasoning (abstract) ├─ Outcome ├─ Verification │ ├─ Fact Check │ └─ Intent Alignment └─ Temporal Evolution

Each layer is model-agnostic and independently testable.


Use Cases

  • Security decision tracking (e.g., CVE patch decisions)
  • LLM Ops & reliability judgment
  • Code review and risk assessment
  • Human-in-the-loop agent systems
  • Research on decision robustness beyond language models

Project Status

This repository currently focuses on:

  • Specification design
  • Data schema evolution
  • Reasoning abstraction rules
  • Verification frameworks

Implementation (agents, UI, extensions) is intentionally deferred until the core model proves stable and reusable.


Long-Term Vision

IntentGraph aims to outlive current LLM paradigms.

As AI systems move from language models to planners, tool-using agents, and world models, human intent must remain the stable interface.

This project is an experiment in building that interface — deliberately, explicitly, and portably.


License

TBD (Design-first phase; licensing will be defined once the specification stabilizes.)

About

Model-agnostic decision intelligence built from human intent.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published