Home · Business · Operations & Logistics · Quality control

PARTLY

As of 13 August 2026, AI can only partly identify snagging issues from building photos.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ita colleague

What the alternative costsNo comparable alternative price is provided in the supplied tool data.

If this goes wrong, a missed or misclassified defect can remain in the works, create rework and complicate responsibility for the finished building.

What to actually do

  1. Hand it to a person

    The route this page recommends

    A person who owns the outcome does this end to end, worth it when the failure is dear.

  2. Use a tool built for this

    Second choice

  3. Do it yourself

    The distant third

    A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open the project drawings, specification, room schedule and any inspection checklist that define the required finish or installation standard.
    2. Gather original, full-resolution photos with room or plot references, including wider context views and close-ups of each suspected defect.
    3. Upload the documents and photos to a multimodal chatbot and paste the prompt, replacing the bracketed project context with the information available.
    4. Ask the chatbot to keep each observation tied to a photo reference and to mark uncertain, obstructed or poorly lit views instead of filling in missing details.
    5. Visit the relevant locations and compare every drafted snag against the physical work, using a tape measure, level or manufacturer instructions where the issue concerns dimensions, alignment or installation.
    6. Record confirmed items in the project snagging system with the exact location, responsible contractor, required remedy, evidence photo and status, and send the list to the accountable site reviewer.

    Prompt

    Review the attached building photos for visible snagging issues. Treat each photo as evidence, not proof of compliance. For every possible issue, provide: photo reference, room or location if inferable, precise description of what is visible, likely category such as finish, alignment, damage, sealing, fitting or cleanliness, confidence level, and a practical on-site check. Do not diagnose hidden defects, structural problems or regulatory non-compliance from photographs. Do not invent dimensions, materials, tolerances, locations or project requirements. Separate clear observations from possible interpretations, flag poor lighting, blocked views and missing context, and identify photos that need retaking. Produce a numbered snag list followed by a short list of items that must be checked against the drawings, specification or manufacturer instructions. Project context: [building type, floor or phase, room references, relevant specification or drawings].

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

  • AI cannot see defects hidden behind finishes, inside assemblies or outside the photographed area.
  • AI cannot reliably judge whether a gap, variation or alignment issue is outside the project tolerance without the correct drawings and specification.
  • AI cannot distinguish a harmless visual variation from a defect requiring specialist investigation in every ambiguous photo.
  • AI cannot take responsibility for accepting the work, instructing remedial action or confirming that a snag has been closed.
  • AI cannot replace a physical inspection when lighting, scale, access or the viewing angle affects the result.

What caps this at PARTLY: verification cost, judgement under ambiguity and stakes of error.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs1
Verification1
Liability1
Effort delta1
Total6 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT spot snags in building photos?
Yes, it can identify many visible issues and turn them into a provisional snag list. It cannot confirm hidden defects, project tolerances or compliance from photos alone, so a site inspection still has to confirm each item.
Can AI replace a snagging inspection?
No. AI can sort and describe photographic evidence, but it cannot inspect inaccessible areas, take measurements reliably in every image or accept responsibility for the finished work.
What photos should I take for AI snagging?
Take a wider view showing the room or location, then clear close-ups of the suspected issue, with good lighting and an object or reference for scale where useful. Keep the original files and label each image with its location so the result can be checked on site.
Can AI tell me if a building defect breaches regulations?
Not reliably from photos alone. Ask it to describe what is visible and list the checks needed against the drawings, specification or relevant guidance, then have the accountable site professional decide whether specialist advice is required.

Nearby answers

All Quality control rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.