TagAndReport · for inspectors

Same report. Faster. Without the busywork.

A field tool that removes the low-value work from inspection reporting
01 · Where the hours actually go

Most of the inspection
is copy, paste, and rename.

Whether it's five photos or five hundred, most of the time isn't spent on engineering judgement. It's spent on file management, photo numbering, code lookup, and Word formatting — work that adds nothing to the deliverable, regardless of how big the job is.

  • ~75% of post-site time is spent on tasks a tool can do
  • ~25% is the actual engineering: tagging findings, naming areas, writing notes
  • The deliverable doesn't get better when an engineer renames IMG_4837.jpg to 03-north-ladder.jpg — it just gets done
02 · Old vs new

Same inspection.
Quarter the time.

Today's workflow

1
Photos on phone — 50–500 shots
site
2
iCloud sync, copy to firm server
15–30 min
3
Sort folders in Explorer by hand
30–45 min
4
Rename + renumber every photo
30–60 min
5
Insert into Word, type captions, cross-ref codes
2–4 hrs
6
Format to template, re-flow, print PDF
30–60 min

With TagAndReport

1
Photos on phone — exactly like today
site
2
Drop the folder in — auto-cluster, AI describe, OCR
~1 min
3
Press a letter, draw a box — codes attach
30–60 min
4
Name areas, propagate titles in one click
~10 min
5
Click Export — branded PDF or Word, auto-numbered
~10 sec
No tagging. No traceability. 4–7 hrs
Tagged. Traceable. ~1 hr
03 · Head to head

Where it actually
helps and hurts.

Today's workflow
With TagAndReport
Photos manually copied from iCloud, often duplicated or missed
Drop the folder; the app reads it in place — no copy step
Folder organization done by hand in Explorer
Auto-clusters by time + GPS, then you tweak — never start from zero
Photo numbering done manually, breaks if anything shifts
Numbering auto-generated at export — always in sync with the report
No tagging — findings live only in your head and the Word caption
Every photo carries a code, region, severity, and regulation reference
Cross-referencing codes from a printed standard, every time
Codes loaded once per project; press a letter, done
Inconsistent deliverables across staff and across inspections
Same template, same structure, every inspector, every time
If a photo is lost or misfiled, the finding is lost with it
Tags ride along inside the photo (EXIF + XMP) — survives any mishap
04 · Any size project

Five photos or five thousand.
Same tool. Same flow.

TAR isn't a "big project" tool — it's a workflow. Setup overhead is zero, so it's worth using on the five-photo retainer check, and it scales without effort to the five-thousand-photo portfolio survey.

5–20 photos

Quick check

Single elevator inspection. Courtesy site visit. Retainer photo log.
~5 min total
Drag, tag, export — faster than emailing the photos. Same firm-branded PDF as your biggest job.
50–200 photos

Routine inspection

Annual building check. Single-site walkthrough. Periodic compliance review.
~30 min vs ~3 hrs
The sweet spot — auto-grouping handles the area structure, tag mode finds its rhythm, every photo carries its code.
500+ photos

Full survey or portfolio

Major building survey. Multi-site campaign. Annual portfolio inspection.
days → afternoon
Manual workflow becomes impossible. AI describe, OCR, auto-clustering aren't optional — they're the only way the report ships.

Same drag-and-drop. Same keyboard. Same firm-branded PDF. No matter the size.

05 · Vocabulary per inspection type

One vocabulary per
inspection type.

Every kind of inspection has its own language. TAR carries a tag set per project — pick the right one when you create the project and the codes for this inspection light up on the keyboard.

Example tag sets

  • Ladder safety — rung damage, rail integrity, anti-slip, signage, anchor points
  • Building envelope — sealant failure, cladding, flashing, water staining, parapet
  • Electrical — panel labelling, conduit, GFCI, bonding, clearance
  • Drainage / site civil — ponding, cover damage, scour, erosion, grading
  • Structural — cracking, deflection, corrosion, connection slip, displacement

What that means in practice

  • Switch from a ladder inspection to an envelope inspection by picking a different set
  • Codes, severities, colours, and regulation references all update together
  • Same field workflow, different vocabulary — no re-training
  • Build your own set for the inspections your firm actually does
06 · Auto-grouping at scale

Turn 1,847 unsorted photos
into 38 named areas.

3-day building envelope survey

1,847 iPhone photos dropped onto TAR. In ~90 seconds: clustered into 38 GPS-bounded areas, each with a centroid for the cover map, an AI-drafted caption per photo, and visible-text OCR (panel labels, addresses, drawing numbers) captured. You then tag with one keystroke per finding instead of building the report scaffold by hand.

500-photo retainer walkthrough

Hybrid clustering produces 12 areas. You re-name 4, merge 2, split 1 at a gap badge — done in 8 minutes. Same scaffold, scaled down. No setup overhead.

North elevation
East roof
Mech room
Parapet — SW
Folder of unsorted photos · clustered · named
Timestamp gap
Photos within N minutes belong to the same area; longer gaps start a new one. Best for sequential walks where you stop, document, then move on.
GPS radius
Photos within N metres cluster regardless of time. Best for walks that revisit areas or inspections where you backtrack between zones.
Hybrid
Timestamp first, then GPS-merges nearby clusters and GPS-splits distant ones inside the same time window. The most robust for mixed indoor/outdoor sites where some photos lack GPS.
Folder structure
Respects subfolders if you've already organised photos that way — honours what you've done instead of overriding it.

All four preserve manually-grouped areas. Re-cluster as many times as you want — your hand-grouping is never destroyed.

07 · The whole flow

Four steps.
One screen.

Opendrop a folder in
Groupauto-cluster + name
TagA–Z, draw a box
Reportpick template, export
1

Open

Point at the photo folder. TAR reads images in place — no copy, no upload. The project remembers where you left off the next time you open it.

2

Group

Auto-cluster runs on import. Drag thumbnails between areas, click a gap badge to split, click between areas to merge. Propagate Names copies area labels down to photo titles in one click.

3

Tag

Press a letter, draw a box. Codes, severities, regulation references attach automatically. Shift+letter for a whole-image tag. Hands never leave the keyboard.

4

Report

Pick the template (PDF or Word). Click export. Image numbers, captions, map page, tag legend — all generated, all numbered, all in firm style.

No mode-switching paperwork. Move between Group, Tag, and Report from a single header tab.

08 · Outdoor — GPS basemaps

Every outdoor photo,
already on the map.

Photos with GPS auto-pin on an OpenStreetMap basemap rendered locally — no API key, no cloud, no tracking. Pins use the firm colour and stack when locations overlap so the map stays readable on a 500-photo inspection. Tile fetching falls back to a clean schematic if you're offline.

The map page goes straight into the report as a navigation overview. Pin numbers cross-reference the image pages so the reviewer can jump from a finding on the map to the photo that documents it.

40-acre industrial site

320 photos pinned on the basemap; the cover map shows 14 area centroids with colour-coded severity, cross-referenced by pin number to image pages.

Linear bridge inspection

Pins trace your walking path along the deck and underside; the basemap proves coverage to the client without a separate site-walk diagram.

1 2 3 4 5 COVER MAP — 320 PHOTOS
Pinned cover map · severity-coloured · numbered
09 · Indoor — plans & pins

Indoor photos
land on a plan you upload.

Photos without GPS — interiors, basements, roof voids, mech rooms — get pinned on whatever plan you load: a PDF floorplan, a scanned sketch, even a hand-drawn schematic. Click on the plan to drop a pin for the active photo.

Same pin style as the GPS basemap, same cross-references into the report. One consistent visual language across outdoor and indoor sections of the same deliverable.

3-storey commercial fit-out

220 interior photos pinned on per-floor PDF plans. The report renders one plan per area with the area's photos numbered around it — reviewers walk the building on paper.

Roof void inspection

Hand-drawn schematic loaded; pins mark each access hatch and noted defect. No GPS, no problem — the report still has a navigable visual index.

OFFICE A MECH CORE OFFICE B OPEN AREA 1 2 3 4 5 LEVEL 02 — 47 PHOTOS
Floorplan · click-to-pin · same numbering scheme
10 · AI features & project context

The things you'd type
are already typed.

AI Describe

A vision model drafts a caption for each photo on import — what's in it, the apparent condition, anything notable. You edit instead of drafting.

Text recognition

OCR reads visible text out of every photo: serial numbers, panel labels, address signs, equipment tags, drawing numbers. Captured automatically.

Semantic search

Find photos by what's in them, not just by tag. "Panel 3B", "rusted railing", "exposed conduit" — query in plain English, jump to the matching photo.

Object suggestions

A local model flags likely objects of interest — ladders, panels, structural members — and proposes the matching tag for you to confirm.

Why these features know what to say — Project context

Every project carries its own context, so AI suggestions and the report itself are scoped to this inspection — not your whole laptop.

Per-project tag set — a different vocabulary per inspection type, switched per project

Per-project branding — firm name, colours, logo, organization carry through to the report cover

Multi-user awareness — others can't stomp your write while you're editing the same project

Resume where you left off — captions, titles, areas all scoped to the project; reopen and pick up exactly there

AI features run locally on your laptop. No upload, no cloud, no privilege concerns. Photos and analysis stay on the same machine.

11 · Report generation

Templated. Branded. Auto-generated.

What the report contains

  • Title page — project info, organization, date, inspector
  • Map page — pinned photo locations with deduplicated overlap
  • Tag legend — every code with regulation reference and severity
  • Image pages — bounding regions overlaid, captions auto-generated
  • Per-area sections — primary image + rolled-up tags + detail photos

How it's controlled

  • Templates drive layout, typography, branding
  • PDF + Word output, both auto-numbered
  • Portable file links survive folder moves between machines
Title
Map
Tag legend
Area · 01
Area · 02
Skeleton preview · 5 pages of a 38-area report · all auto-laid-out
12 · What you actually get

The whole tool,
on one page.

Drag-drop import

Point at a folder. TAR reads it in place. No copy step.

Auto-cluster

Time, GPS, hybrid, or folder. Hundreds of photos → named areas.

Keyboard tagging

Press a letter, draw a box. Codes, severities, regulation refs attach.

Area naming

Drag, split, merge, propagate names to titles in one click.

GPS basemap

Outdoor pins on OpenStreetMap, severity-coloured, numbered.

Indoor plan pins

Floorplans, sketches, schematics — same pin language.

AI describe + OCR

Captions drafted, visible text extracted, all on your laptop.

Branded PDF / Word

One click. Title, map, legend, area sections. Auto-numbered.

Same drag-and-drop, same keyboard, same firm-branded output — whether it's a 5-photo retainer or a 5,000-photo survey.

13 · Report generation — roadmap

Where the report engine
is going next.

Near-term

  • Live in-browser preview — render pages to PNG inline as you tag; no export step needed to see how it'll look
  • WYSIWYG layout editor — drag page elements; layout overrides write back to the project's TOML template
  • Per-area GPS centroids — one map pin per area, not per photo, so the map stays readable on large inspections
  • Severity-first ordering — high-severity findings render before cosmetic ones in the report body

Mid-term

  • Multi-site reports — combine areas from multiple folders into a single deliverable for portfolio inspections
  • Inline annotations — arrows, callouts, and text overlays on report images, drawn in the browser
  • Conditional sections — pages auto-hide if no relevant codes were used (skip the "electrical" page if no E-tags)
  • Custom page types via ReportFactory designer — new page templates without touching code

Vision

  • AI-drafted executive summaries — front-page narrative generated from the tag set, written in firm voice
  • Comparison reports — diff two inspections of the same site; automatically flag changes and resolved items
  • Embedded FieldLog signatures — signed-on-site PDFs pull straight into the report cover
  • One-click brand swap — re-render the same data as a different firm's branded report with one TOML change
14 · Your data, your control

It runs on your laptop.
Nothing leaves.

No cloud

No upload. No login. No internet required after install. AI features run locally.

📁

Your folders

The photos stay where you put them. The app reads them in place.

Survives the tool

Tags ride along in the photos themselves (EXIF + XMP). If TAR vanished tomorrow, the work is still there.

15 · What's coming next

The report writes itself,
before you leave site.

TAR's sister app FieldLog already runs on your phone for field forms and signatures. The next phase wires them together — a photo taken on site is auto-uploaded, AI-tagged, GPS-grouped, and queued for the report without ever touching a laptop.

FieldLogphoto + form on phone
Auto-uploadno iCloud step
TARAI tags + group
Draft reportin your inbox

You walk back to the truck. The draft report is already on your screen — codes filled in, areas grouped, photos placed, plan-pinned. You review for 15 minutes instead of building for 4 hours.

16 · No pressure

Don't want to use it?
Don't have to.

The current workflow stays exactly as it is

TAR doesn't replace anything. The iCloud-to-server flow, the Explorer folders, the Word templates — all still work, untouched. Nothing about how the firm operates today depends on TAR being adopted.

Use it on the inspection where the time savings matter. Skip it on the one where they don't. Try it once. If it doesn't fit how you work, the old workflow is right there waiting.

17 · The result
~75%
less time per inspection report

Same deliverable. Faster turnaround.
Consistent output across every inspector.
Findings traceable to the regulation, every time.

18 · Sound interesting?

Sound interesting?

It's already set up and waiting on your laptop. No install, no logins, no cloud accounts — just a folder of photos and a keyboard.

Pick the next inspection on your desk — a five-photo retainer check is the fastest way to feel the difference. We can sit down together and walk through it the first time, then it's yours.

The current workflow stays exactly where it is. If the new one fits better, you'll know inside an inspection or two.

Questions, feedback, or want a walkthrough? Talk to Elliott.