---
id: framework-model-to-system-gap
title: Model-To-System Gap
slug: model-to-system-gap
type: framework
status: draft
summary: A lightweight rubric for evaluating the product system around an AI model.
agent_summary: The model-to-system gap framework evaluates context, tools, memory, controls, cost, reliability, and proof around model capability.
audiences:
  - ai-infrastructure-leaders
  - product-operators
  - founders
topics:
  - ai-systems
  - model-to-system-gap
  - product-strategy
claim_ids:
  - claim-reach-systems-around-model
proof_ids:
  - proof-context-window-research
source_ids: []
visibility_queries:
  - q-ai-infra-context-economics
risk_level: low
canonical_url: null
published_at: null
updated_at: 2026-05-22
framework_type: rubric
use_cases:
  - ai-product-review
  - infrastructure-product-strategy
inputs:
  - model-capability
  - workflow-context
  - tool-surface
  - reliability-requirements
outputs:
  - system-risk-map
  - proof-gaps
  - next-evaluation-questions
---

# Model-To-System Gap

The model-to-system gap is the distance between a capable model and a reliable product experience.

Use it when a demo works, but the production question is still unclear: what context is assembled, what tools are allowed, what state is remembered, what costs are acceptable, and what proof exists that the workflow works for the intended job?

## Rubric

| Layer | Question | Evidence to look for |
| --- | --- | --- |
| Context | What does the model see, and what is deliberately excluded? | Source policy, retrieval evals, context order tests. |
| Tools | What can the system do, and where are approvals required? | Permission map, tool logs, rollback behavior. |
| Memory | What persists across sessions, and how is it corrected? | Memory schema, user controls, audit trail. |
| Reliability | What failure modes are expected and measured? | Evals, incident notes, fallback paths. |
| Cost | What latency and spend budgets shape the design? | Budget envelope, model routing, capacity assumptions. |
| Proof | Which claims are backed by visible evidence? | Claims table, proof inventory, caveats. |

## Operator takeaway

Do not judge an AI product by model access alone. Judge the operating system around the model.