What Lumiere is
Lumiere is an automated research system. Reports are produced by coordinated AI agents rather than human researchers — so instead of asking for your trust, we attach the evidence. Every figure links back to the source it came from, and every report publishes the verification checks it passed, along with the ones it didn't.
How a report is made
Lumiere is not a single model writing an essay. An orchestrator delegates each phase to a specialist agent — retrieval, outlining, writing, verification, review — and holds the boundary between them. The critical rule is that evidence is gathered and frozen before any writing begins: nothing downstream can cite outside that pool, which is what makes every sentence traceable.
Targeted searches run against each question. Candidate sources are read, screened for relevance and authority, and reduced to the facts, claims, and quotes worth keeping. What survives becomes the evidence pool — frozen, with provenance attached.
The report is framed around decision questions — "when is X worth it?" — rather than a fixed template. Major clusters found in research must be covered, or explicitly scoped out with a reason.
One controlling verdict, argued section by section, citing only the frozen pool. Evidence is graded and the language must match its grade: a controlled comparison may "establish"; a result that doesn't isolate the variable, or a vendor-authored figure, may only "suggest" — and vendor studies are named as vendor studies.
Deterministic checks that can block publication: every [N] resolves to a real source, every cited URL exists in the evidence store, every figure traces to a source extract, named systems appear in the evidence, and quotation marks are reserved for verbatim source language.
An independent pass re-examines the draft and applies minimal, audited edits. It sees the report, not the reasoning that produced it — then the gate runs once more.
The report ships with its receipts: per-claim source statements, the source list with authority labels, the retrieval funnel, and the audit ledger.
What the checks do — and do not — guarantee
- Traceability — every figure links to the source it came from
- Internal consistency — markers, sources, and figures reconcile
- That a third-party figure is correct, or that an experiment reproduces
- That a volatile value — a price, a model version, a benchmark — hasn't changed since we retrieved it
A report is anchored in time: it reflects its sources as of its publication date. We say this plainly rather than implying permanence.
Code and data
We publish verification datasets and artifacts as we build them — the underlying claim-checks behind our reports, released for anyone to scrutinize. The research system itself is not open source yet; when parts of it are, we'll say so here.