1. Documentor
  2. Screenshots
Application screenshots · ZOO Plyšákov archive

What Documentor looks like.

Screenshots of the application over the fictional ZOO Plyšákov archive: invented documents of a zoo for plush animals, including a scan from 1987. The application interface is in Czech. Click a screenshot to enlarge it and use the arrow keys to browse.

Documents and processing

  • Documents of the ZOO Plyšákov archive: the Upload documents panel with the supported formats and a list of 35 documents with a first-page thumbnail, name and main heading, page count, processing state and upload date

    Archive documentsUpload by drag and drop, a list with a first-page thumbnail and the main heading of each document; Word, XPS and images are converted to PDF.

  • The Processing page while the archive is being processed: document counts by state and the job queue by phase, from conversion to PDF to QR and barcodes and document labelling, with the number of waiting and running jobs and a chart of jobs finished per hour

    Processing queueDocuments by state and jobs by phase: how many are waiting, running or failed, and how many finished in the last hour. Processing can be paused.

  • Invoice PIP-26-031 with four labels (to pay, over CZK 10,000, serial number, invoice) and the processing phases expanded from page sorting to QR and barcodes and document labelling, each with its job count, state, start, end and duration

    Document phasesFor each document you see when every phase started, how long it took and why it failed, if it did; optional phases such as reading codes and labelling are listed too. A document can be processed again.

  • Detail of the document Breeding sheet – plush brown bear: an AI annotation and abstract, the page strip, a page with marked blocks including a bar chart and a line chart, and on the right the list of blocks with an AI description of the table and the chart

    Document detailAn AI annotation and abstract, the page with marked blocks and the list of blocks; tables and charts have a description and their data so they can be searched.

  • Detail of the scan Sectoral directive 3-1987 from 1987: a typewritten page with recognised blocks, on the right the blocks with OCR confidence in percent, and an AI annotation and abstract above

    A scan from 1987A page without a text layer goes through OCR. Every block shows its recognition confidence, and uncertain text can be read again by the vision model.

  • The second page of the scan Management meeting minutes 3-2026 with stains and handwritten notes: recognised blocks on the page, on the right the blocks with OCR confidence from 80 to 95 %, including a handwritten note

    A crumpled scan with notesA skewed, crumpled page with stains goes through OCR as well. Handwritten notes are read with a lower confidence, which the block shows.

QR codes and labels

  • The QR and barcodes page of the archive ZOO – Orders and invoices: 11 documents with a code by type (EAN-13, Code 128, QR code, Data Matrix), code reading switched on, six label rules by code, and for the rule over CZK 10,000 the result of Try with three invoices

    Codes and label rulesAn overview of the codes in the archive and the rules “code pattern → label”: a QR payment gets the label to pay, an amount over CZK 10,000 another one, an order number in Code 128 its own. Try shows the matches before you save the rule.

  • Detail of the delivery note DL-2026-0113: a Code 128 barcode with the document number framed on the page and three EAN-13 codes by the items, on the right the panel Codes on the page with four codes and a copy button

    Codes on the pageThe QR and barcodes phase reads the codes on every page, scans included. The detail frames them right on the page, and the code text can be copied or searched for.

  • The document list of the archive ZOO – Orders and invoices with the Labels column (receipt, to pay, contract, overview, order, invoice, delivery note, credit note) and the All labels filter

    Labels in the listLabels from code rules and from labelling by a language model are shown with every document. Click a label, or use the filter, to see only the documents that have it.

Search

  • Search for “stuffing loss above 10 %” in all archives: an AI answer with a list of measures and numbered sources, below it 20 hits in 14 documents grouped by document with a page preview and the passage highlighted

    An answer with citationsSearch finds passages by meaning and by words, AI composes an answer from them and cites the document and page for every claim.

  • Search in the Exact text mode: the designation PZ-0001, 76 hits in 37 documents from all archives, hits from a table, a paragraph and a chart with a page preview and the term highlighted

    Exact textDesignations, clause numbers and values are found literally, regardless of case and diacritics; each hit shows the block type and the place on the page.

  • Search for “shrinkage of the cover when washing” with the block type filter Chart: an AI answer built from the values of a chart, including a table of shrinkage by material and temperature, and the list of sources

    Charts and tablesThe vision model also describes charts and tables, so you can search only in them, and an answer can be built into a clear table from their data.

Chat and research

  • Chat: saved conversations on the left, in the middle the question how to wash a mohair cover and why not in a washing machine at 60 °C and an AI answer with numbered citations, on the right the Sources panel with a cut-out of the shrinkage chart from the standard

    Chat with citationsThe answer is based only on the passages found. Clicking a source number shows a cut-out of the place on the document page in the panel.

  • Research in progress: the Research in progress panel with a time of 0:21, a live list of steps – searching and reading passages in the decree, the laundry hygiene rules, the care plan and the safety data sheet – and the answer text as it is written, with the buttons Answer now and Stop

    Research in progressThe AI goes through the archive, searches and reads documents and follows references; you watch the progress live and can answer right away or stop the research.

  • A finished research on which documents regulate the washing of plush animals and what applies today: an answer regulation by regulation – decree No. 42/2025, the standard ČPN 77 0101 and the laundry hygiene rules – with links to the sources

    A finished researchAn answer across the whole archive, regulation by regulation, every claim with a link to the page. The research found on its own that the decree repealed the sectoral directive from 1987.

  • The end of the list of sources of a research with the buttons Show in panel and the expanded Research steps: 12 steps from finding the documents on the topic through searching and reading passages and pages, with the number of model rounds, tool calls and tokens below

    Research stepsEvery research keeps its steps: what the AI looked up, searched for and read, and how many model rounds and tokens it took.

Document intake and sorting (optional plugin)

  • Sorting inboxes: the inbox Incoming documents ZOO with four target archives, the path for uploading to S3 storage, the assigned mailbox, the beginning of the API key, its state and the number of waiting documents

    Sorting inboxesAn inbox defines which archives a document may go to and where it comes from: a path in S3, an API key for another system and an e-mail mailbox.

  • The Edit inbox dialog: name, target archives, mailbox, Sort automatically and Allow external model switched off, and four rules by code – a QR payment and a Code 128 with an order or document number to the invoice archive, a Data Matrix with an animal registration number to the breeding archive

    Inbox settingsTarget archives, the mailbox and rules by code: the first matching rule from the top suggests the archive. Automatic sorting is off by default and e-mail is never sorted automatically.

  • Incoming documents awaiting triage: nine documents from S3, the API and e-mail, five with a suggested archive labelled code rule, two with an uncertain suggestion by similarity and two without a suggestion, each with the buttons Confirm or File, Elsewhere and Reject

    Triage of incoming documentsThe suggested archive comes from a rule by code, from the sender, or by similarity with a confidence label. The sorter confirms it with one click, picks another archive or rejects the document, also in bulk.

  • Detail of the incoming invoice S-26-047 from a scanner: a crumpled page with a coffee ring, the S3 source, the suggested archive ZOO – Orders and invoices labelled code rule, the QR payment code read from the page, a text excerpt and the buttons Confirm suggestion, File elsewhere and Reject

    Detail before the decisionA first-page preview, the codes from the first pages, a text excerpt and for e-mail the sender and subject. The QR payment is read even from a crumpled scan with a coffee ring.

  • The dialog Agreement of suggestions with decisions: eight documents filed, two of them with a suggestion by similarity, one went to the suggested archive, broken down by the labels certain, probable and uncertain

    Agreement of suggestionsIt shows how often sorters filed a document into the suggested archive, also by confidence; suggestions from rules and from the sender are not counted. It tells you when the suggestions can be trusted and when it pays off to switch automation on.

  • Incoming documents in the filed state: eight documents, each with its target archive and the sender for e-mails, with the processing bar of the filed documents at the top

    Filed into archivesA filed document is processed like any other: OCR, page recognition, code reading and indexing for search and chat.

  • Detail of the document Reminder for invoice 2026-118 in the archive ZOO – Orders and invoices: the labels to pay, over CZK 10,000 and reminder, the header says it was added by prijem:prichozi and shows an e-mail from Blanka Pěničková marked as unverified, on the right the QR code on the page

    A document from e-mail in the archiveThe sender and subject of the e-mail stay with the document and every reader of the archive sees them marked unverified.

Groups, usage and administration

  • Group administration: six groups with their application role, members and administrators, own archives and archive roles – the partner zoo is a reader of the regulations, the management a reader of breeding and invoices and creates archives

    GroupsA group gives its members roles in archives and its own archives, managed by its administrator. It works for Microsoft and Google accounts, so you can let an outside partner into an archive too.

  • Configuration of the group Economics: its own S3 storage, connections to the external DeepSeek model and to Ollama in the server room with their models, and the default models of the group for enrichment, annotation, embedding, chat and research

    Storage and models of a groupA group can have its own S3 storage and its own AI models, external ones or in its own server room; what it does not set, it takes from the default group. A change by the group administrator is approved by a supervisor.

  • My profile: the account and sign-in method, the application role, groups with the default group, and e-mail notifications by kind – approvals, processing errors, new documents and intake awaiting sorting

    Profile and notificationsEveryone sees their roles and groups, picks a default group and sets what the application e-mails them about and how often – right away, as a daily summary or not at all.

  • Usage for a chosen period: searches, AI questions, tokens of external and internal models for users and for processing, storage, database and index, and below the Archives tab with documents, pages, size and processing by archive and an export to Excel

    UsageHow much each person searched and asked the AI, how many tokens the models used and how much space the archives take – by user, group, archive and model, with an export to Excel as a basis for billing.

  • Administration of the archive ZOO – Orders and invoices: the processing phase graph with switches including QR and barcodes and document labelling, enrichment by the vision model with the external model allowed and a warning about what is sent to a third party, and the choice of the archive’s AI models

    Phases and external AIThe archive administrator switches on optional phases such as code reading and labelling and picks models from the group’s offer. The archive uses an external model only with the administrator’s consent.

We will show you how it works on your own documents.

Send us a few PDFs from your archive – old scans are fine. In 30 minutes you will see how searching them works and how the chat answers.

Already a customer? Sign in