How the record was read
This site reads a single database built by the insight-bridge pipeline from the inquiry’s page on aph.gov.au: 547 submitters, 647 evidence documents, 9,235 passages, 1,646 submitter–topic memberships, 1,646 submitter-level stances, 169 sector perspectives and 4,879 answers to 14 questions.
Everything on every page is a live query against Cloudflare D1 (the run's own tables, copied whole) and Vectorize (the embeddings), through fully-typed Drizzle. The same data is exposed to agents over an MCP server at /mcp.
What was done, in order
Each step below is a stage this run actually executed, read from the run's own record of itself; a stage the run was configured to skip is not listed.
- Collecting the evidence from the Parliament’s site
The collection was updated on 13 October 2026: 590 written documents and 57 source-attributed extracts from five published hearings, across 547 source records. Each document retains its Parliament source link. Six superseded documents remain in the run history but are excluded from this current reading and search. Text extraction combines native PDF text and local OCR. All 305 new written PDFs were audited against the pipeline’s additional image-page OCR pass; 76 flagged pages received visual review and a second local recognizer, with rotation and region crops where needed. No generative transcription replacements were used. The September analysis was extended through append, followed by an Update of the topics and synthesis. Hearing extracts contain the source’s witness turns; consult the full Hansard for questions and context. Housing Industry Association’s submission 146 retains its confirmed black-page source defect. OCR can still misread small raster text. The record is a snapshot of published evidence, not everything the inquiry eventually received.
- Reading in the evidence documents
Every evidence document was stored whole under its submitter, its text cut into passages small enough to compare — 9,235 of them across 647 evidence documents from 547 submitters — and each passage embedded with text-embedding-3-large, which is what makes a search by meaning, and the grouping below, possible at all. Each submitter carries what the inquiry records about it (its submission number, what it lodged) and each document its type, the Parliament’s descriptor and the link to the original file.
- Reading each evidence document end to end
A language model read every evidence document in full against this run's profile and recorded what it found as key points, each with the verbatim quotes that support it: 7,986 key points and 25,769 quotes. Every quotation is verbatim from the source evidence document: each is verified against the evidence document's text before it is stored, and one that cannot be found there is never presented as verified. 100% verify, and a quote that does not is never shown here. The same reading classified each submitter's sector from what it wrote. The same reading put the committee's 14 terms of reference to every evidence document: 4,879 answers were found, each with a position, key points and quotes. A question left unanswered means no answer was located in the available text, never that a submitter has no view.
- Settling what counts as one submitter
The names the model inferred were put to a person beside the names the record carries, before anything was counted, so that one submitter appearing under two spellings is counted once in every figure on this site. The record's name stands; the model's reading is kept beside it.
- Grouping the passages into topics
Topics are found from the passages themselves, bottom-up, by grouping the passages across the corpus that say the same thing; nothing supplies a list of themes beforehand. A topic has to be raised by more than one submitter to form: one submitter's volume cannot make a topic on its own, and the rare topic that only one submitter carries is flagged as such. A group had to hold at least 3 passages to count as a topic. Where those settings found nothing, they were relaxed a step at a time until they did. Each passage, and each submitter, is then placed against every topic at a graded strength (exemplar, high-value, member), so a submitter that touches a topic in passing is recorded as well as the submitters that define it, and a passage can belong to more than one topic. 39 topics resulted, over 9,235 passages.
- Writing each topic up and reading positions against it
Each topic is written up as a proposition with key points, and every exemplar and high-value submitter's position is recorded against that proposition, on this run's own scale, Supports, Builds on, Mixed, Redirects, Opposes and Unclear. Positions are relative to the topic's own framing, never absolute agreement, and every submitter is measured against the same proposition. 1,646 positions were written, and the same was done for each value of source sector: 169 perspectives. A position here records how a submitter stands against one topic's particular framing, and is never a verdict on the subject in general.
- Removing the groups that carry nothing
A model flagged topics whose synthesis reported no substantive shared content, and a person confirmed or rejected each flag — and could confirm a topic the model had not flagged. 2 topics were confirmed and are excluded from every figure on this site. The flag alone never removes anything.
- Offering the topics upward into themes
The topics were grouped again, generation by generation, each generation clustering the one below it until it stopped merging. A topic with no theme above the attachment threshold stands on its own. This site reads the tree as the run left it, however many generations that turned out to be — here, 4 families above the topics, each named by the model from its members.
- Placing the topics in a sky
Each topic's place in the galaxy was computed once and stored with the run, seeded so it is the same sky every time. That is what lets these pages draw the constellation as plain graphics, with no WebGPU and nothing solved in your browser.
- Loading this site
Outside the pipeline, before loading: the run database was copied whole to the cloud — every table as the pipeline wrote it, with the passage embeddings moved to a vector index — and two facts were derived from it for these pages, each document’s and each passage’s dominant topic. Nothing was flattened, re-verified or re-classified here; every figure on every page is a live query over the run’s own tables.
What each submitter was classified by
Every facet the run's profile declares. A facet marked compared is one the analysis wrote a perspective for, value by value — the lens you can read a topic through. Facets that are not compared ride beside it as facets of the record.
What a position means here
Read weakest claim first. Supports, Builds on agree with a topic's proposition; Mixed, Redirects, Opposes push back against it; Unclear reads as neither.
Position is relative to the cluster proposition, not the source's tone. Nuance alone is not Mixed, and constructive engagement alone is not Builds on.
How to read the output
These rules apply to every Insight Bridge corpus. They are properties of the method, not caveats about a particular run.
- Positions are relative to a proposition. A source’s position records how it stands against that cluster’s particular framing — not whether it agrees with some absolute claim. The same source can support one cluster and redirect a neighbouring one that covers similar ground differently.
- Propositions are written from the cluster’s own members. Because the argument is built from the sources that were grouped together, and positions are read relative to it, a degree of agreement is built into the method. Comparisons between groups carry weight; a corpus-wide agreement rate does not.
- Counts describe the corpus, not the world. Every corpus here is curated. “N sources say X” measures what was collected and is never a measure of how common X is in the field.
- Clusters differ in how many distinct sources back them. A long document can fragment across many clusters, so weight a theme by the distinct sources beneath it rather than by how many clusters it contains.
- Every extraction and position is a model judgement. Key points, stances, propositions and syntheses are produced by a language model reading the source. They inherit its calibration and are not determinations of fact.
In this run
Removed after review. “Workplace Algorithms: Require continuous workplace risk management” — confirmed by the reviewer without a model flag. “AI Adoption: Link assurance with national capability” — confirmed by the reviewer without a model flag. They are excluded from every figure on this site, including the 37 topics counted above.
Not analysed. . Step 1 produced no key points for this document; it keeps its topic memberships.
Questions are answered per document. A submitter with more than one document may answer a question twice; a question's page counts a submitter once. An unanswered question means no answer was located in the available text, never that a submitter has no view.
Partly unreadable in the published original. (Housing Industry Association (HIA) — Submission — User manually confirmed the black pages in the original HIA submission and could not locate another published copy, including on the HIA website. This is a confirmed source defect, not a pipeline extraction failure.). What is here is that submitter's available text, not its complete evidence; do not infer absent views from it.
Witnesses without a numbered submission. ; ; ; ; ; ; .
Written and hearing evidence. Five published hearings contribute witness extracts alongside submissions and attachments. A source may appear in either or both forms; repeated appearances do not represent additional independent sources.
What else was asked of every evidence document
Beyond the standard reading, this run declared its own questions and put each of them to every evidence document.
Which model did what
Named because it matters: the reading, the writing-up and the grouping were done by these, and a different model would have produced a different record.