AI review — page 7

claude-opus-4-8 · prompt v7 · 2026-09-04T15:09:33+00:00 · applied: yes · changed: yes

Screenshot sent to the model (reading-order tags burned on)

Instructions (system prompt)

The screenshot has annotations burned onto it that are NOT part of the document:
- a small red numbered tag at the top-left corner of each item, showing that item's position in the OCR-determined reading order (the same order the items appear in the json data);
- a red-and-white dotted outline around each item, showing the area the OCR detected for that content block.
Use the tags and outlines to see the detected reading order and item boundaries directly on the page, and judge that sequence against how a human would naturally read it. Ignore the annotations when checking text fidelity — they overlay the content, they are not content.

For the given screenshot of a PDF's page and the attached json data, I want you to perform the following tasks in order...

Review the reading order set out in the json data and compare to what a natural reading order for that of a human would be by looking at the screenshot. Decide on any changes and re-arrange the items for the most logical reading order.
Look at all text for each item and correct any extraction errors like missing words, spelling mistakes etc.
Look at each item in the JSON and ensure that the OCR process has identified the item as the correct type: text, list item etc.
Look for any text that duplicates: if two items next to each other contain the exact same text but the text only appears once on the screenshot, one of them is an extraction error — keep the item whose box matches where the text is visible and flag the other for removal.
Make amendments as you proceed through the items and list of instructions.
Reading Order Advice: If there is columns with headings and text, I wouldnt expect the reading order to jump from one heading straight to another if there is text associated with that heading.

Return format: Give me the json data back only, with the amendments you make.

Mechanical notes (so your answer can be applied automatically):
- Each item has an `id` — keep every item and its `id` exactly as given; never invent, drop or duplicate ids. Re-arranging means changing the position of items (and their nesting) in the arrays.
- Never move text (or a type) from one item to another: each item's coordinates travel with its id, so to change reading order you must move the whole item object, and text amendments must be in-place corrections of that item's own text.
- To flag a duplicate item, keep it in the array and add `"remove": "duplicate"` to it — never just delete it (deleted items are restored automatically).
- ids are opaque labels, not sequence numbers: never renumber them. After a removal or re-arrangement, every remaining item keeps the exact id it came with, even if the ids no longer look sequential.
- Text may contain `[pN.M…]` placeholders marking where an inline formula belongs — treat them as part of the text and leave them exactly where they are.
- `box` is [left, top, right, bottom] as percentages of the page from the top-left corner; return it unchanged.
- Respond with raw JSON only: no code fences, no commentary, same shape as the input (`{"items": [...]}`).

User message (json data sent)

Page 7 json data:

{"items":[{"id":"p7.1","type":"title","box":[27,5,73,7],"text":"Norwich Economic Barometer – July 2026"},{"id":"p7.2","type":"text","box":[13,9,91,12],"text":"centre unit back into use. The retailer will occupy 51-53 St Stephens Street, the former home of the YMCA store, which has stood empty since its closure last year."},{"id":"p7.3","type":"list_item","box":[9,13,91,32],"text":"Two leading Norwich-based plant science institutes, the John Innes Centre and The Sainsbury Laboratory, have secured £1.6 million in funding to support the development of a world-class research facility focused on crop resilience and sustainable agriculture at Norwich Research Park. Backed by investment from the Wolfson Foundation, the proposed 4,500sqm Technology Platform 1 will include state-of-the-art glasshouse, insectary and horticultural research facilities, enabling scientists to study crop performance under realistic growing conditions. The facility will feature advanced LED lighting, precise environmental controls capable of simulating future climate scenarios and integration with cutting-edge genomics, imaging and computational modelling technologies to accelerate innovation in agricultural research."},{"id":"p7.4","type":"heading","box":[9,33,21,35],"text":"Education"},{"id":"p7.5","type":"list","box":[8,36,91,84],"text":"","children":[{"id":"p7.5.1","type":"list_item","box":[8,36,91,55],"text":"The University of East Anglia (UEA) has opened a new anatomy suite in the Edith Cavell Building at Norwich Research Park, creating a state-of-the-art facility that will enhance healthcare education, surgical training and research across medicine, dentistry and clinical sciences. Designed as a UK exemplar facility, the suite combines traditional anatomy teaching with modern technology and features 17 dissection tables, integrated iPads at every workstation, improved audiovisual systems and high-quality anatomical models. The new space will transform anatomy learning by enabling up to 120 medical students to be taught together in a single session, while also expanding opportunities for students across graduate-entry medicine, dentistry, healthcare and clinical sciences programmes to gain valuable dissection experience and professional skills training."},{"id":"p7.5.2","type":"list_item","box":[9,55,91,65],"text":"Norwich University of the Arts and the Royal College of Art (RCA) have signed a historic agreement to establish jointly awarded undergraduate degrees, creating a new model of creative higher education collaboration in the UK. It is the only current opportunity anywhere to study undergraduate degrees validated by the Royal College of Art, the world's leading art and design university and a specialist postgraduate institution."},{"id":"p7.5.3","type":"list_item","box":[8,66,91,84],"text":"City College Norwich has been awarded £4.9m to enhance its teaching facilities which will see 12 additional classrooms added to its Ipswich Road site. The project will be funded by the Department of Education through their Post-16 Capacity Fund. The fund provides money for 16 to 19 providers, further education colleges and sixth form colleges, to create additional student places where demand for post-16 education is growing. Set to open in September 2027, the £4.9m teaching block will consist of 12 new classrooms, allowing a further 148 students to learn at the college. The classrooms will support the delivery of STEMM (science, technology, engineering, mathematics and medicine), digital, business and health-related courses, giving students access to modern learning environments and industry-standard facilities."}]},{"id":"p7.6","type":"footer","box":[90,93,91,95],"text":"6"}]}