AI review — page 10

claude-opus-4-8 · prompt v7 · 2026-09-04T15:08:30+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 10 json data:

{"items":[{"id":"p10.1","type":"heading","box":[12,11,70,14],"text":"3. Local Area Profile – Norwich 2026"},{"id":"p10.2","type":"heading","box":[12,15,57,17],"text":"3.1 Location and Administrative Context"},{"id":"p10.3","type":"text","box":[12,18,87,29],"text":"Norwich is a city and non-metropolitan district in Norfolk and the county town of Norfolk, situated around 100 miles northeast of London. Built along the River Wensum, the city has a compact urban form with a well-preserved medieval centre, extensive green spaces, and limited suburban sprawl. Surrounded by a predominantly rural county, Norwich plays a crucial role as the main service, employment, and cultural hub for the wider region."},{"id":"p10.4","type":"text","box":[12,30,88,47],"text":"Economically, Norwich is the principal economic centre of Norfolk with a predominantly service-based economy. Major employment sectors include health and social care, education, public administration, finance and insurance, retail, and the digital and creative industries. The University of East Anglia and Norwich University of the Arts contribute significantly to the city's economic activity, skills base and innovation. While Norwich has experienced strong population and employment growth, average wages remain below national levels, and a sizeable proportion of residents work in lower-paid or insecure employment. The city also has a high proportion of social housing, reflecting its long history of council house provision."},{"id":"p10.5","type":"text","box":[12,48,88,63],"text":"Socially, Norwich has a relatively young population, with one of the highest proportions of working-age residents in Norfolk, partly driven by its student population. This supports a vibrant cultural scene and active voluntary and community sector. However, the city experiences significant inequality, with deprivation and poverty concentrated in specific wards. Child poverty rates are high, and many households face cost-of-living pressures, fuel poverty, and issues linked to older or poorly insulated housing stock. These conditions contribute to persistent health and wellbeing inequalities across the city."},{"id":"p10.6","type":"text","box":[12,64,83,70],"text":"Overall, Norwich is a dynamic regional centre combining economic and cultural strengths with enduring social and economic challenges, particularly relating to deprivation, housing quality and affordability."},{"id":"p10.7","type":"footer","box":[49,93,51,94],"text":"9"}]}