Follow the evidence by subject, not file type.

Designed experience

The state of AI-assisted data visualization research

An explanatory field guide to goals, use contexts, techniques, convergence, disagreement, failure evidence, benchmarks, baseline readiness, and the 36-month capability timeline.

Extracted sections

• Purpose and audienceWhat is agentic visualization for?
• Research synthesisWhat does current evidence establish—and what does it not?
• Shared research timelineHow did the evaluation surface expand from 2023 through 2026?
• What the benchmarks measureWhich task-and-grader result produced each score?
• Moving model and harness baselineWhat remains durable as models and harnesses improve?
• Research forecastWhat chain of evidence is most likely to unlock useful capability?
• Evidence ladderWhich meaning of works has actually been observed?
• Technique mapWhich recurring technique addresses the named bottleneck?
• Choose the environment firstWhich controls and tests does this environment require?
• Research and implementation landscapeWhere do the recurring mechanisms appear across systems, skills, and products?
• Research gap ledgerWhich missing receipt would materially change the current answer?
• Research method and custodyWhat was reviewed, retained, and not tested directly?

Designed experience

The practitioner and reader experience

What people are trying to accomplish, which tools they reach for, what feels newly possible, and where correction, prepared change, maintenance, trust, and reader experience still break down.

Extracted sections

• The central practice gapWhen does a possible chart become finished work or useful communication?
• Who is reaching for whatHow is AI entering existing visualization work?
• The jobsWhat work is hidden inside make a chart?
• Listening to the fieldWhat different experiences are practitioners reporting?
• Field perspectivesWhat should cheaper implementation effort buy?
• The tools and work surfacesWhat can each work surface see, change, and leave behind?
• Creator experienceHow does assistance change the full creator workflow?
• Measured creator evidenceWhich dimensions move together, and which do not?
• Human capabilityWhich skill is assistance actually changing?
• Reader experienceWhat happens when the audience encounters the delivered claim?
• Context and lifecycle modesHow should the common evidence spine change by role and lifecycle state?
• A practical evaluationHow should the complete creator-to-artifact-to-reader episode be measured?
• How to read the evidenceWhat work can each source type legitimately do?

Designed experience

How close are we to the ideal?

Context-specific scorecards for generation and understanding, reconstructed backward through time and connected to explicit forecasts.

Extracted sections

• The ideal stateWhat does perfect performance mean?
• One fixed maturity scaleWhat evidence moves a capability score?
• Current common-core scorecardWhere is the field closest to and farthest from the ideal?
• Context-specific idealsHow do release gates change while the scorecard stays fixed?
• The same scorecard through timeHow has the fixed scorecard moved?
• Forecasts as score movementsWhich score movements are plausible and resolvable?
• Scorecard source mapWhich studies are closest to each judgment?
• How to read and update the scorecardWhat kind of judgment surface is the scorecard?