Orientation
Purpose and audience
What is agentic visualization for?
Open this sectionDecomposed research
The actual sections, outside the omnibus pages.
Every substantive top-level section from the three visual experiences appears here exactly once. Each route renders the original content and design directly; the structured registry and audience compositions reuse the same source fragment.
33 extracted sections
No summary substitutes: each page contains the source DOM from its owning visual experience, with cross-section links rewritten to the corresponding part route.
Open the structured registry →12 extracted sections
State of the research
Twelve independently rendered sections from the research field guide.
Synthesis
Research synthesis
What does current evidence establish—and what does it not?
Open this sectionHistory
Shared research timeline
How did the evaluation surface expand from 2023 through 2026?
Open this sectionEvaluation
What the benchmarks measure
Which task-and-grader result produced each score?
Open this sectionBaseline
Moving model and harness baseline
What remains durable as models and harnesses improve?
Open this sectionForecast
Research forecast
What chain of evidence is most likely to unlock useful capability?
Open this sectionEvidence
Evidence ladder
Which meaning of works has actually been observed?
Open this sectionMechanisms
Technique map
Which recurring technique addresses the named bottleneck?
Open this sectionContext
Choose the environment first
Which controls and tests does this environment require?
Open this sectionLandscape
Research and implementation landscape
Where do the recurring mechanisms appear across systems, skills, and products?
Open this sectionResearch agenda
Research gap ledger
Which missing receipt would materially change the current answer?
Open this sectionMethod
Research method and custody
What was reviewed, retained, and not tested directly?
Open this section13 extracted sections
Practice and consequences
Thirteen independently rendered sections from the practitioner and reader experience.
Orientation
The central practice gap
When does a possible chart become finished work or useful communication?
Open this sectionPeople
Who is reaching for what
How is AI entering existing visualization work?
Open this sectionPractice
The jobs
What work is hidden inside make a chart?
Open this sectionTestimony
Listening to the field
What different experiences are practitioners reporting?
Open this sectionPerspectives
Field perspectives
What should cheaper implementation effort buy?
Open this sectionPractice
The tools and work surfaces
What can each work surface see, change, and leave behind?
Open this sectionHuman evidence
Creator experience
How does assistance change the full creator workflow?
Open this sectionEvaluation
Measured creator evidence
Which dimensions move together, and which do not?
Open this sectionLearning
Human capability
Which skill is assistance actually changing?
Open this sectionHuman evidence
Reader experience
What happens when the audience encounters the delivered claim?
Open this sectionContext
Context and lifecycle modes
How should the common evidence spine change by role and lifecycle state?
Open this sectionEvaluation
A practical evaluation
How should the complete creator-to-artifact-to-reader episode be measured?
Open this sectionMethod
How to read the evidence
What work can each source type legitimately do?
Open this section8 extracted sections
Capability and forecast
Eight independently rendered sections from the capability scorecard.
Capability model
The ideal state
What does perfect performance mean?
Open this sectionCapability model
One fixed maturity scale
What evidence moves a capability score?
Open this sectionCapability model
Current common-core scorecard
Where is the field closest to and farthest from the ideal?
Open this sectionContext
Context-specific ideals
How do release gates change while the scorecard stays fixed?
Open this sectionHistory
The same scorecard through time
How has the fixed scorecard moved?
Open this sectionForecast
Forecasts as score movements
Which score movements are plausible and resolvable?
Open this sectionEvidence
Scorecard source map
Which studies are closest to each judgment?
Open this sectionMethod
How to read and update the scorecard
What kind of judgment surface is the scorecard?
Open this section