Features
Capabilities for live research and presentation
Concise building blocks. Each capability preserves provenance and keeps the presenter in control of what reaches the audience.
Live inference
Turn finalized transcript segments into structured topics, claims, and research commands as the conversation unfolds.
Multi-model AI
Route listening, planning, and research through provider interfaces so models can specialize by task.
Evidence gathering
Retrieve passages—not just summaries—from seeded documents and the public web, with clear stance labels.
Research routing
Generate support- and challenge-oriented queries, then send work to the right source families.
Government archives
Reach declassified FOI and diplomatic records through specialized archive providers when relevant.
Academic sources
Connect scholarly indexes and library catalogs so claims can be grounded in peer-reviewed material.
Primary documents
Surface ancient texts, manuscripts, and other primary sources with citation metadata preserved.
Sharing
Publish selected cards to a presentation route suited for a second display or OBS Browser Source.
Exporting
Package claims, evidence, and attribution for later review—without losing the source trail.
Source attribution
Keep provenance attached from card to passage to source so audiences and reviewers can verify.
See Delveira in context
The homepage walks through the full presenter workflow—from transcript to published card.