Skip to content

Instantly share code, notes, and snippets.

@synchronic1
Created April 13, 2026 02:00
Show Gist options
  • Select an option

  • Save synchronic1/9321bc2ee009fab728eabab4c1f1576c to your computer and use it in GitHub Desktop.

Select an option

Save synchronic1/9321bc2ee009fab728eabab4c1f1576c to your computer and use it in GitHub Desktop.
CIG: Context Inferenced Generation - A proposed term for the context-augmented generation taxonomy

CIG: Context Inferenced Generation

Acronym Definition

CIG = Context Inferenced Generation

A generation paradigm where curated context vaults are accessed by inference engines to retrieve relevant knowledge, which then drives multimodal content generation.


Definition

CIG is the pattern of using inference to intelligently select context from structured knowledge stores (context vaults), then generating new content based on that retrieved context. The key differentiator: inference drives context selection, not just vector similarity or static caching.


Context Vault

A context vault is a curated, structured knowledge store containing:

  • Agent memory (preferences, decisions, history)
  • Skills and methods (how-to knowledge)
  • Documentation and references
  • Research and notes

CIG vs RAG vs CAG

Pattern Context Source Selection Mechanism Output
RAG Document corpus Vector similarity Text
CAG Pre-loaded cache Static Text
CIG Context vault Inference engine Multimodal

The CIG Flow

Context Vault → Inference Engine → Generator → Output

The inference engine semantically retrieves relevant context from the vault, then generators produce content in any modality.


Key Characteristics

  1. Curated context - Structured knowledge, not raw documents
  2. Inference-driven - Intelligent selection, not just similarity matching
  3. Multimodal - Generates text, images, audio, scripts, or other content
  4. Agent-centric - Designed for autonomous agent workflows

Example

When an agent receives a request:

  1. Inference engine searches the context vault
  2. Relevant memory, skills, and docs are retrieved
  3. Generator produces response using that context

This is CIG: inference determines what context matters, generation creates from it.


Proposed term for the context-augmented generation taxonomy.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment