Structure claims. Gather evidence. Present with confidence.
Inference Explorer listens to a live discussion, turns speech into revisioned claims, gathers provenance-aware evidence, and helps you publish a clean audience view—without treating AI output as unverified truth.
What it is
A research control room—not a chat window
The source of truth is a structured, revisioned claim-and-evidence graph. Models emit typed domain commands; they never generate arbitrary executable UI at runtime.
Listen live
Explicit microphone control, partial transcript deltas, and durable finalized segments.
Inspect evidence
Supporting, qualifying, challenging, or absent—never confuse silence with falsehood.
Publish carefully
Compose cards in the control room, then project a recording-friendly presentation route.
How it works
Four steps from speech to slide
Built for a single presenter operating one session—with a clear path to richer collaboration later.
01
Listen
Capture live transcription with explicit start/stop control. Partial text appears quickly; finalized segments drive analysis.
02
Structure
Convert speech into revisioned claims, topics, and entities—typed domain objects, not freeform chat blobs.
03
Research
Run seeded and public research in parallel. Classify evidence as supporting, qualifying, challenging, or absent.
04
Present
Compose cards in the control room, then publish a clean audience view suitable for recording.
Features
Capability highlights
Concise building blocks for live inference, research, and presentation.
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.
Research
Research capabilities
Seeded corpora, public web, and specialized providers—routed by claim, not by guesswork.
Seeded corpora
Search uploaded Markdown and PDF material with hybrid full-text and vector retrieval.
Public web
Plan queries that seek both support and challenge, then extract citable passages.
Specialized providers
Route to archives, scholarly indexes, and ancient-text corpora when the claim warrants it.
AI providers
Provider interfaces first
OpenAI is the first implementation for listening and research planning. The architecture stays behind interfaces so models can change without rewriting the product.
- OpenAI
- Provider interfaces
- Transcription APIs
- Embedding models
Task-appropriate models
Transcription, claim structuring, embeddings, and research planning can use different providers. Secrets stay on the server.
Typed outputs only
Models produce validated domain commands and component specifications—not executable HTML, templates, or SQL.
Evidence & citations
Provenance from card to source
Every factual item should remain inspectable. Citation metadata travels with the evidence.
Evidence passages keep source URL, title, publisher or author when available, retrieval time, and content type. Stance labels help you see support and challenge side by side.
- SupportingPassages that corroborate the claim
- QualifyingNuance that narrows or conditions the claim
- ChallengingMaterial that conflicts or complicates
Live inference
Keep pace with the conversation
As claims revise, obsolete research is superseded so stale results do not overwrite newer understanding.
Partial transcript text appears quickly for awareness. Finalized segments drive semantic listening: topics, entities, claims, comparisons, questions, and presentation commands.
Learn about live inferenceArchives
Declassified archives when the claim warrants it
Specialized providers can reach FOI and diplomatic primary records—without putting archive credentials in the browser.
History Lab and beyond
Declassified archive research is available through dedicated integrations. Enable or disable them per environment; the product remains useful without them.
Ancient texts, scholarly indexes, and library catalogs follow the same pattern: provider behind an interface, provenance on the result.
Product
Screenshots
A look at the control room in action.
Pricing
Simple plans for early access
Start free, then scale to multi-session research and archive access as you need it.
free
For individual presenters validating the workflow.
$0during early access
- 50 monthly request credits
- Core research workflow
- Private presentation sharing
- Public presentation sharing
hobbyist
You like to research a bit.
$19.99/ month
- Deep Research
- Archive Research
- Knowledge Graph
- Video Upload
- Public Sharing
pro
+30% CREDITSYou like to dig. Deep.
$49.99/ month
- Everything in hobbyist, plus:
- Live Research Workflow
- Premium Research
- Premium Models
- Priority Queue
- Deep Research
Enterprise
For teams that need controls, review, and deployment options.
Custom
- 5,000 monthly request credits
- Core research workflow
- Premium research providers
- Deep scour escalated research
- Public presentation sharing
- Private presentation sharing
- Programmatic API access
- Multi-seat organization workspaces
- Priority processing for research jobs
- Archive and declassified sources
- Access to premium AI models
- Larger export packs with attribution
- Research workspace and evidence graph
Ready to explore with evidence?
Join the waitlist for early access. Authentication and billing arrive in later phases—this site is here to explain the product clearly.