How it works
What 15 agents find
when they have 3 days to look.
Not an LLM with a retrieval plugin. A purpose-built research infrastructure: hierarchical query decomposition, six parallel retrieval channels, knowledge graph construction, multi-signal confidence scoring.
01 · Intake
Your question is the starting point, not the answer
You send an email. Plain language, no forms. We turn it into a structured research plan: clarifying scope, identifying depth, and surfacing implicit assumptions before a single search is run.
02 · Retrieval
Six channels searching simultaneously
Your research plan doesn't feed a single retrieval pipeline. Six independent channels search in parallel, spanning academic databases, knowledge graphs, and the open web. Results are fused and reranked in two stages.
03 · Reasoning
One question becomes hundreds
Your question isn't answered in a single pass. It's decomposed into a research tree, up to 4 levels deep, 3 branches per node. Each leaf is investigated by a specialist agent. Branches are dynamically pruned and expanded as evidence surfaces.
04 · Verification
Three independent signals, one honest score
Every finding gets a confidence score derived from three signals: the agent's own self-reflection, consistency across multiple independent answers, and formal provability via constraint solving. When these signals disagree, the report tells you.
05 · Assembly
Eight phases from findings to finished report
Eight phases from raw findings to finished report. The system plans a narrative arc, writes with inline citations, calibrates tone for the audience, and reviews its own structure for gaps. Every claim cited. Every finding scored.
01 · Intake
Your question is the starting point, not the answer
You send an email. Plain language, no forms. We turn it into a structured research plan: clarifying scope, identifying depth, and surfacing implicit assumptions before a single search is run.
02 · Retrieval
Six channels searching simultaneously
Your research plan doesn't feed a single retrieval pipeline. Six independent channels search in parallel, spanning academic databases, knowledge graphs, and the open web. Results are fused and reranked in two stages.
03 · Reasoning
One question becomes hundreds
Your question isn't answered in a single pass. It's decomposed into a research tree, up to 4 levels deep, 3 branches per node. Each leaf is investigated by a specialist agent. Branches are dynamically pruned and expanded as evidence surfaces.
04 · Verification
Three independent signals, one honest score
Every finding gets a confidence score derived from three signals: the agent's own self-reflection, consistency across multiple independent answers, and formal provability via constraint solving. When these signals disagree, the report tells you.
05 · Assembly
Eight phases from findings to finished report
Eight phases from raw findings to finished report. The system plans a narrative arc, writes with inline citations, calibrates tone for the audience, and reviews its own structure for gaps. Every claim cited. Every finding scored.
See it work on your question.
Send us an email with what you want to understand. No account needed.