← All Patterns

Pattern

Crystallization

Encode human judgment into configurable constraints. AI executes within those constraints. One expert's judgment scales through AI execution.

Published January 8, 2025

“Your judgment, crystallized.”

Definition

Crystallizationis the process of encoding human judgment—taste, philosophy, domain expertise—into configurable constraints that AI agents can execute. The expert doesn’t disappear; they become infrastructure.

This iscurated autonomy: the human decides the boundaries, the AI works within them. Unlike “autonomous organizations without humans in the loop,” crystallization keeps human judgment central—it just doesn’t require human presence for every decision.

A legal expert crystallizes contract review criteria. A finance expert crystallizes audit trail requirements. A designer crystallizes aesthetic principles. The AI executes these judgments at scale.

“The question is not ‘can AI do this?’ but ‘what judgment should guide how AI does this?‘”

“The question is not ‘can AI do this?’ but ‘what judgment should guide how AI does this?‘”

Curated Autonomy vs. Full Autonomy

Human judgment crystallized into constraints. AI executes within boundaries.

“No humans in the loop.” AI makes all decisions.

  • • Expert encodes quality criteria

  • • AI executes at scale

  • • Judgment persists across sessions

  • • One human serves many

  • • Constraints evolve with learning

  • • No quality criteria encoding

  • • AI decides what “good” means

  • • No domain expertise transfer

  • • Humans are replaced, not scaled

  • • Black box decision-making

What Gets Crystallized

Which AI model handles which task. Cost optimization meets capability matching.

modelRouting:

patterns:

haiku: [rename, typo, format]

opus: [architect, design, refactor]

sonnet: [add, update, fix]

What must pass before work is considered complete. Domain-specific criteria.

Legal domain example

qualityGates:

custom:

  • name: contract-validation

command: pnpm run validate:contracts

canBlock: true

What reviewers look for. Security, architecture, quality—with custom prompts.

reviewers:

reviewers:

  • id: compliance

type: custom

prompt: ./reviewers/compliance.md

canBlock: true

How work is categorized. Reflects organizational structure and priorities.

labels:

scope: [agency, io, space, ltd]

type: [feature, bug, refactor, research]

Domain Examples

Contract review, compliance checking, redaction validation.

✓ contract-validation: Check clause requirements

✓ redaction-check: Verify PII removal

✓ compliance-review: Regulatory requirements

Audit trails, calculation verification, regulatory compliance.

✓ audit-trail: Ensure transaction logging

✓ calculation-verify: Validate financial math

✓ sox-compliance: SOX requirement checks

Tolerance verification, BOM validation, quality control.

✓ tolerance-check: Verify specifications

✓ bom-validation: Bill of materials accuracy

✓ qc-inspection: Quality control criteria

Canon compliance, accessibility, animation auditing.

✓ canon-audit: Design token compliance

✓ a11y-check: WCAG requirements

✓ motion-review: Animation purposefulness

Implementation

Auto-discovers config

harness work cs-xyz

Explicit config

harness start spec.yaml —config custom.yaml

Philosophy

Crystallization is the Subtractive Triad applied to human judgment itself:

DRY (Implementation):Encode judgment once, execute many times. Don’t repeat the same quality decision for every task.

Rams (Artifact):Only crystallize judgment that earns its existence. Not every preference needs to be a constraint.

Heidegger (System):Crystallized judgment should serve the whole. Constraints that don’t serve users get removed.

The hermeneutic circle applies: the crystallized config informs AI execution, AI execution reveals what needs crystallizing, which refines the config. Understanding deepens through the cycle.

“The goal is not to remove humans from the loop, but to make human judgment scale without requiring human presence for every decision.”

DRY (Implementation):Encode judgment once, execute many times. Don’t repeat the same quality decision for every task.

Rams (Artifact):Only crystallize judgment that earns its existence. Not every preference needs to be a constraint.

Heidegger (System):Crystallized judgment should serve the whole. Constraints that don’t serve users get removed.

“The goal is not to remove humans from the loop, but to make human judgment scale without requiring human presence for every decision.”

When to Apply

  • • Expert judgment should scale

  • • Quality criteria are domain-specific

  • • AI is executing, not deciding strategy

  • • Consistency matters across executions

  • • You want to serve many without being present

  • • Novel situations need fresh judgment

  • • Over-constraint kills exploration

  • • Some decisions should remain human

  • • Crystallized != frozen (evolve the config)

Related Patterns

Every value traces to a principle. Crystallized judgment is principled by definition.

Crystallized constraints free AI to work without constant guidance.

Crystallized judgment enables tools to recede. The harness disappears; work remains.

Crystallized configs evolve. Each execution informs the next refinement.