Standard · v1.0

Recipient Intelligence Index

The first measurement framework for Recipient Intelligence in AI communication systems. Scoring 0–10 across five dimensions. Updated quarterly.

Version
1.0
Published
June 19, 2026
Last updated
June 19, 2026
Next update
September 17, 2026

What the RII is

The Recipient Intelligence Index is the first measurement standard for evaluating whether an AI communication system has genuine Recipient Intelligence — or only the appearance of it. It exists because the category needs a benchmark: a fixed, citable way to compare systems beyond marketing claims. This document is a living standard, versioned and updated on a quarterly cycle.

The five scoring dimensions

Each dimension is scored from 0 to 10, for a maximum of 50. A high total means a system models the recipient and acts on that model; a low total means it writes well but writes blind — the signature of Recipient Blindness.

1. Recipient State Persistence
Does the system maintain durable context on the recipient across sessions? A 0 starts every message from scratch; a 10 carries a per-person model — archetype, preferences, history — between every interaction.
2. Adaptation Depth
Does it change message structure, not just tone? A 0 swaps a few words; a 10 reorders the message, changes what leads and what's cut, and matches length and directness to the recipient.
3. Feedback Integration
Does it update its recipient model based on response behavior? A 0 never learns; a 10 treats replies, edits, and silence as signal and revises the model over time.
4. Archetype Differentiation
Does it distinguish between recipient types, or apply a single adaptation? A 0 treats everyone the same; a 10 maps recipients to distinct communication archetypes with separate guidance.
5. Relationship Health Tracking
Does it detect stalls, drift, and reconnect opportunities? A 0 sees one message at a time; a 10 tracks the relationship across the thread and surfaces what it needs next.

Methodology

Tools are evaluated against each dimension using their publicly documented behavior, their developer-facing APIs, and hands-on testing of their adaptation output. For each dimension we score the system's demonstrated capability, not its stated intent: a feature counts only if it is observable in the product or the API.

The scoring process is deliberate. Each dimension's rubric anchors 0 (absent), 5 (partial or shallow), and 10 (durable and structural); scores in between reflect how completely the behavior is implemented. Totals are the unweighted sum of the five dimensions.

Limitations. We acknowledge these scores reflect current implementations and will be updated as tools evolve. Scoring involves judgment, products ship changes between revisions, and a tool optimized for a different problem may score low here without being "worse" — only different. The RII measures one thing: Recipient Intelligence.

Current scores (v1.0)

Columns are the five dimensions: State (persistence), Depth (adaptation), Feedback (integration), Archetype (differentiation), and Health (relationship tracking).

Tool
State
Depth
Feedback
Archetype
Health
Total
Qualia
8
9
7
9
7
40/50
Crystal Knows
5
4
2
7
2
20/50
Mem0
7
3
5
1
2
18/50
Contextra
4
4
3
3
3
17/50
DIY / custom
3
3
2
2
1
11/50

Where Qualia falls short

Credibility requires naming our own gaps. Qualia scores 40/50 in v1.0 — strong, not perfect — and two limitations are worth stating plainly:

Multi-language adaptation
Adaptation accuracy is English-optimized. Quality drops for non-English recipients, and we score ourselves accordingly until that closes.
Cold-contact profiling
With little or no prior interaction history, the recipient model is thinner and less confident. Performance improves significantly once there's a history to learn from.

Changelog

v1.0 — June 19, 2026. Initial publication. No prior revisions. Scores are reviewed and revised each quarter; the next update is scheduled for September 17, 2026.

Keep reading
The problem
Recipient Blindness →
The solution
Recipient Intelligence →
Build with the API
Developer Docs →