Skip to main content

Reading Your Analysis Results

When Quick or Full Analysis finishes, the output appears on the dossier's AI Analysis panel. Full Analysis produces up to nine distinct block types, organised under a table of contents. Quick Analysis produces a subset of the same blocks — typically Narrative, top themes, and one or two highlight quotes.

The block types​

1. Narrative​

An essay-style summary of what the dossier contains. Reads like the introduction of an archivist's report. Length varies with dossier size — typically 500–1,500 words for Full, 200–400 for Quick.

2. Timeline​

Chronological events extracted from the dossier with item citations. Each event has a date, a one-line summary, and a "see also" list of items where it appears.

3. Quote​

Verbatim passages from the underlying material — letters, transcripts, captions — that capture key moments. Quotes are always cited back to the source item.

4. Entity Card​

Profile-style cards for the most prominent people, organisations, and places in the dossier. Each card pulls together:

  • Authority-resolved identity (with LCSH / VIAF / GeoNames URI)
  • Dates of mention in the dossier
  • Items where this entity appears
  • A short biographical or descriptive note synthesised from the dossier itself

5. Connection​

Relationships between entities that emerge from the material — "A worked with B at C from 1956 to 1962". Each connection links the entities involved and cites the supporting evidence.

6. Finding​

A discrete, surprising claim the analysis can support from the underlying material. Findings always include a confidence indicator and the items that ground the claim. These are the bits worth quoting in your own work.

7. Comparison​

Where the dossier contains contrasting positions or events — "the 1962 minutes describe X positively; the 1965 minutes describe it as a failure". Useful for thematic essays.

8. Gap​

What's missing — runs of years where the record is silent, expected items that aren't present, named people who appear once and never again. Useful for collection development and for being honest about the limits of an enquiry.

9. Research Question​

Open questions the dossier raises but doesn't answer. Phrased as researchable prompts — "What is the relationship between X's tenure and the disposal of the Y collection?"

A Table of Contents on the left lets you jump between block types. Within each block, individual items (e.g. Timeline rows, Entity Cards) have permalinks — useful for sharing a specific finding.

Most blocks include "View source items" links that take you to the underlying item in its accession.

Interrogating further​

At the bottom of every analysis is a Continue in Explore button — start a Research & Explore session pre-loaded with the dossier's contents. Useful when the analysis raises questions you want to dig into.

Exporting the analysis​

The analysis panel has an Export button with these options:

  • PDF Report — formatted for distribution; cover page, table of contents, full output
  • Word document — for editing in Word or Google Docs
  • Markdown — for further publication workflows
  • JSON — structured output, useful for embedding in a content platform

Citations and provenance​

Every claim in the analysis is cited back to source items. Click any citation to jump to the item; hover for a preview. This is non-negotiable in the platform — there's no claim in an analysis that isn't traceable back to material you uploaded.

If you spot a claim that doesn't fit the cited evidence, the Flag button on each block reports it for review. Patterns of flagged claims feed back into how we tune the models.

What the analysis is good at, and not​

Good at:

  • Summarising what's in a body of material
  • Spotting themes and recurring entities
  • Producing a timeline from heterogeneous dates
  • Finding gaps and silences

Less good at:

  • Causal claims ("X happened because Y")
  • Statements about the wider historical period (it knows your dossier, not the world)
  • Long-form prose that reads exactly like your own — use Profile → AI & Defaults to tune the writing style, but plan to edit final output for tone