Home Industries Documents and archives

Documents and archives

AI document processing and search for Perth businesses

Most organisations keep their knowledge in PDFs: reports, contracts, scanned maps. We turn archives like WA's mineral exploration reports into data people can search and question, with every answer traced to its page.

Where AI helps, and where it doesn't

Workflows we often look at in a screening. Every one gets a rating and a reason; the real list comes from how your team works.

WorkflowRatingWhy
Copying figures from PDFs into spreadsheetsAutomateExtraction where every figure can be checked against the source
Finding past reports on a similar jobAutomateSearch across the archive with the source page cited
Checking tenders or contracts against a specificationAssistAI flags gaps for a person to confirm
Summarising a long reportAssistDrafted with quotes, reviewed by the reader
Signing offLeave as isStays with the responsible person

What we have already built

Your project starts from working parts, not a blank page. Try them now; each can also be installed on your own servers.

  • A pipeline that reads text, layout, tables, formulas and figures from scanned documents
  • Extracted facts stored in a structured warehouse, each linked to its page
  • Applied to the WAMEX exploration report archive
  • Automatic georeferencing of scanned maps, and places and dates from free text
  • A warehouse built from the questions experts ask, as a comparison table, knowledge graph or decision tree

How a project runs

Four steps. You can stop after any of them, and each one leaves you something to keep. More on how we work.

  1. 1

    AI workflow screening

    We review how your team actually works, task by task, and rate each workflow: automate, assist, or leave as is, with the reason, effort and risk for each.

    Typically 2 to 4 weeks, fixed price

  2. 2

    Concept design and proof of concept

    We build a working prototype on your real data. Success measures are agreed before we start, so the result is a clear go or no-go with a build cost.

    Typically 4 to 8 weeks, fixed scope and price

  3. 3

    Production development

    We turn the prototype into reliable software, connected to the systems you already use and deployed in your cloud or on your own servers.

    Typically 2 to 6 months, quoted per milestone

  4. 4

    Support and improvement

    AI systems drift as data and models change. We monitor quality, update models and add features, with a named engineer who knows your system.

    Monthly, scaled to use

Who we work with: Any business with an archive of reports, contracts or records searched by hand.

Questions

Other industries we work in:

Our documents are old scans. Will this work?

Usually yes. The pipeline was built on scanned exploration reports, including tables, figures and maps. The screening report says what is usable now.

How do we know an answer is right?

Every answer keeps its quote and its place on the page, so a person can check it in one click.

Can confidential documents stay in-house?

Yes. The whole pipeline can run on your own servers with open-weight models.

Keen to have a chat?

Schedule a coffee chat in Perth, an online meeting or an in-person meeting at your office. A rough idea of what you'd like to improve is plenty.

Coffee chatOnline meetingIn person