← Back

AI-Native Development Criteria

Purpose

A structured diagnostic to score your development environment's AI-Native readiness on a 100-point scale across four perspectives.

How to Use

  1. Read each perspective and its sub-items
  2. Score each item based on the criteria provided
  3. Sum scores to determine your level

Score Summary

LevelScoreState
Excellent90–100Fully structured AI-Native workflow with high-quality context
Good70–89Workflow established with conscious quality practices
Fair50–69Core workflows in place, but operations and autonomy are immature
Poor30–49Initial efforts underway, but workflows are fragmented and unintegrated
Critical0–29Not started or early stage

Evaluation Scope and Premises

Scope: Evaluate against the product's primary working repository (or single monorepo).

Context fragmentation: If core context is distributed across multiple repositories, and cross-repository search, reference, and update do not complete within a single workflow, context closure scores low.

External sources of truth: If the SSoT (Single Source of Truth) for PRDs, design documents, or tasks resides in an external tool, that item scores 0.

Why "Updatable" Is Non-Negotiable

Read-only documents are not true context. Context is something you grow, not something you write once and reference forever.

As LLMs execute development work, they need to:

  • Record design decisions discovered during implementation
  • Add constraints that emerge from technical investigation
  • Update specifications that prove incomplete or incorrect

Context that cannot be updated drifts from reality. "Readable but not updatable" context becomes stale and misleading as the codebase evolves. Misleading context is worse than no context, because the LLM trusts it.

Allowing external SSoTs would mean tolerating this drift. This criteria does not. Search, reference, and update must all complete within the LLM's workflow. Without this, LLMs cannot operate autonomously.

Point Allocation Rationale

PerspectivePointsRationale
Context Closure15Necessary foundation, but a prerequisite, not a differentiator
Codified Principles30Highest leverage: determines every LLM decision's quality
Workflow and Guardrails25Operationalizes principles into enforced practice
Context Quality30Existence of principles is meaningless if poorly expressed

Principles and Quality together account for 60 out of 100 points. This reflects a core belief: an LLM with well-written, project-specific principles in a messy repository will outperform an LLM in a perfectly organized repository with no principles.

Scoring Rules

  • Perspectives 1–3 are evaluated cumulatively. If foundational items are not met, dependent items score 0 (no renormalization).
  • Perspective 4 (Context Quality) is evaluated across all artifacts, independent of Perspectives 1–3.
  • Qualitative evaluation requires actual file content review.
  • Evaluate the essence of "providing appropriate context to LLMs": avoid tool-specific assessments.
  • Evidence-based scoring: Score based on what you can verify in the repository, not what you believe to be true.
    • "We have documentation" is not evidence: open the files and evaluate their content
    • "We do reviews" is not evidence: check whether review integration is defined in the workflow

Perspective 1: Context Closure (15 points)

Whether all product context is in a state where search, reference, and update complete within the LLM's workflow.

All three capabilities must complete within the workflow:

CapabilityMeaningMetNot Met
SearchableDiscoverable without knowing exact pathsFiles in repo (grep/glob), semantically searchable docsSingle file reference in external tool
ReadableLoadable into LLM contextFile read, API retrievalDocuments behind authentication walls
UpdatableLLM or workflow can maintain contentMarkdown in repo (edit/write)Read-only external tool integration

A. Product-Level Closure (9 points)

ItemPointsCriteria
Design documents3PRDs, Design Docs, ADRs, and similar artifacts are searchable, readable, and updatable within the workflow
Task management3Tasks (issues/tickets) are searchable, readable, and updatable within the workflow
Infrastructure/platform definitions3Terraform, k8s manifests, CI definitions, and similar configurations are searchable, readable, and updatable within the workflow

Scoring per item:

ConditionPoints
Search, reference, and update complete within primary repository3
Separate repository, but cross-repository workflow completes all three2
Search and reference possible, but update not possible1
Reference only, or external SSoT0

B. Application-Level Closure (6 points)

ItemPointsCriteria
Feature-based directory structure4Core services, modules, contract definitions (API, SDK, Proto), and infrastructure definitions are organized by feature/domain within the same repository
Colocation2Tests, type definitions, and styles colocated within corresponding features (holds for most core features)

Scoring:

  • Feature-based: Same repo + all core domains = 4, partial = 2, layer-based = 0
  • Colocation: Most core features = 2, some = 1, separated = 0

When scoring: Feature-based structure with bloated files undermines closure effectiveness. Complexity concentrated in specific directories indicates insufficient separation of concerns.


Perspective 2: Codified Principles (30 points)

Whether project-specific principles are documented in a form LLMs can reference. Not generic rules, but judgment criteria specific to this project.

Foundation (5 points)

ItemPointsCriteria
Principle document exists5AGENTS.md (or equivalent) functions as entry point with universal principles stated concisely, routing to skills/references for details

Scoring:

  • 5: Entry point contains minimal universal principles + routing only (no task procedures)
  • 3: Entry point mixes task procedures or multi-domain details
  • 0: No principle document, or external links only

Coverage (25 points)

DomainPointsCriteria
Coding standards & design principles5Project-specific coding rules, design patterns, naming conventions documented
Domain-specific knowledge5Business logic, domain terminology, business workflows documented
Architecture decision criteria5ADRs exist with current decision criteria summarized separately
Done definitions5Mechanical completion criteria (tests, verification, acceptance) documented so LLM can judge autonomously
Structured review perspectives5Project-specific review criteria structured, not reliant on generic templates alone

Scoring notes:

  • Done definitions: PR template only = 1, per-task mechanical criteria = 5
  • Review perspectives: Generic-dominant = 1, project-specific-dominant = 5

When scoring: Abundant technical debt markers (TODO/FIXME/HACK) without codified principles are evidence of subjective frustration accumulation, not healthy management. Debt markers grounded in principles are evidence of conscious debt tracking.


Perspective 3: Workflow and Guardrails (25 points)

Whether operational mechanisms exist to translate principles into execution.

Foundation (2 points)

ItemPointsCriteria
Commands/agents/skills exist2Some form of task execution definition exists

Task Execution Environment (6 points)

ItemPointsCriteria
Navigation design (entry point → skills → references)3Progressive context loading from entry point: minimal context acquired at each stage
Context reference2Skills/commands specify reference targets and purposes, loading only when needed
Specialized agent definitions1Single-responsibility agents defined for context control and bias elimination

Scoring:

  • Navigation: Entry point is minimal principles + routing = 3, entry point is overloaded / commands carry excessive context = 1, no navigation = 0

Review Workflow (7 points)

ItemPointsCriteria
Review integration point3Review occurs during implementation, not dependent on PR/CI post-stage
Design/test priority2Design doc review and test review are built in as highest priority
Review perspective reference2Structured review perspectives are referenced

Scoring:

  • Integration point: During implementation = 3, PR/CI only = 1, none = 0
  • Design/test priority: Documented + prioritized in workflow = 2, documented only = 1, none = 0

Test Verification & Quality Assurance (6 points)

ItemPointsCriteria
Test generation/verification commands2Commands or skills for testing are defined
Test guidelines reference2Testing guidelines are referenced
Quality assurance guardrails2Pre-commit, local verification, or AI auto-checks run during implementation

Scoring:

  • Guardrails: CI only = 1, automated verification during implementation = 2

Value Stream Integration (4 points)

ItemPointsCriteria
Integrated review mechanism2A mechanism to synthesize multiple review results is defined
Conflict resolution rules2Priority and adjudication rules for conflicting perspectives are documented

Scoring:

  • Integrated review: Explicit integration output format = 2, partial = 1, none = 0
  • Conflict resolution: Documented priority/adjudication rules = 2, implicit/ad-hoc = 0

When scoring: Test verification workflows with low-quality tests (low behavioral coverage, high mock density) indicate the workflow is ineffective regardless of its existence. High test quality maintained through workflows is evidence that guardrails are functioning.


Perspective 4: Context Quality (30 points)

Quality criteria for all context artifacts: AGENTS.md, commands, agents, skills, rules, and design templates.

4-1. Single Responsibility (5 points)

Each context artifact serves one purpose/domain.

PointsCriteria
0Multiple unrelated responsibilities mixed in a single file
3Generally separated, but some responsibility mixing remains
5Each artifact clearly serves a single purpose

Detection indicators:

  • Single command/skill handles multiple unrelated tasks
  • AGENTS.md contains detailed procedures beyond entry-point role
  • Agents split by review perspective, not by context-control purpose

4-2. Consistency (5 points)

No contradictions between artifacts; all references match the current codebase.

PointsCriteria
0Contradictory instructions between files, or stale descriptions remain
3Main artifacts are consistent, but some inconsistencies exist
5All artifacts are coherent and match the current codebase state

Detection indicators:

  • AGENTS.md instructions contradict command procedures
  • References to deleted files or APIs remain
  • Conflicting rules between rule files

4-3. Explicitness (5 points)

No ambiguity; LLM can judge and execute without hesitation. Stated in positive form.

PointsCriteria
0Many ambiguous instructions; relies on negative-form instructions
3Main instructions are clear, but some ambiguity or negative forms remain
5All instructions are specific, positive-form, with no room for LLM hesitation

Detection indicators:

  • Vague instructions like "write good code"
  • Negative-form instructions like "don't do X"
  • Success criteria or output formats undefined
  • Skills/commands with ambiguous purpose, usage conditions, or I/O

4-4. Target Clarity (5 points)

Written for LLMs. No human-oriented preambles, decoration, or explanatory prose.

PointsCriteria
0Human-oriented documentation repurposed as LLM context
3Generally LLM-targeted, but human-oriented decorative text remains
5All artifacts designed with LLMs as the target audience

Detection indicators:

  • Preambles like "This document aims to..."
  • Decorative headings or emoji
  • Verbose explanations assuming human readers
  • README content copied verbatim

4-5. Project Specificity (5 points)

Focused on project-specific judgment, not generic advice. Not verbose.

PointsCriteria
0Mostly transcribed generic best practices or copied from other projects
3Contains project-specific content, but generic advice is mixed in
5All statements are project-specific judgments; nothing that should be handled by tooling

Detection indicators:

  • Content like "use camelCase for variables" that linters/formatters should handle
  • Transcribed generic coding principles
  • Settings copied from another project without understanding

4-6. Quality Assurance Mechanisms (5 points)

Each task/principle has clear purpose and criteria, with verification mechanisms.

PointsCriteria
0Procedures only; no purpose, criteria, or verification steps
3Purpose is clear, but verification means (checklists and similar) are partial
5Each task/principle has purpose, criteria, and quality checklists enabling artifact verification

Detection indicators:

  • Lists of procedures without stated purpose
  • Execution instructions without verification steps
  • Undefined behavior for uncertain situations

© 2026 Norsica. All rights reserved.