Two-week proof of concept · for Advanced Tech Machining

Prove it on your own sheets first. Pricing comes after.

Send 10 completed op sheets and a blank template. In two weeks, we hand back a per-dimension accuracy report on your actual handwriting — at no cost, no commitment. If the numbers earn it, we scope a paid pilot together. If they don't, you walk with the data and we go our separate ways. Same workflow at the bench either way — your inspectors keep writing on paper, the way they work fastest.

Free · 2 weeks · No commitment Runs on your own completed sheets ATM commits ~1 hour total ISO 9001 audit trail preserved
Bench: handwritten op sheet
ATM-58241 · OP 02
Advanced Tech Machining · In-Process Inspection
FORM-IPI-04 · Rev C · ISO 9001:2015
Pg 1 / 1
Job ATM-58241
Part BRKT-2045-R02
Op 02 — Mill / Finish
Date 06/05
Char.DimensionNominalTolReading
D1Bore Ø0.7500±.0002 .7501
D2Pilot Ø0.3750±.0003 .3752
L1Length overall1.250±.005 1.252
L2C'bore depth0.250±.002 .253
R1Surface finish16 Ramax 14
T1True positionØ.0010MMC .0007
Inspector A.T.
Time 10:42
Apprend: digital inspection report
awaiting capture
Capture the bench sheet
Tap Capture sheet below to run the OCR pipeline against the handwritten op sheet on the left.
Ready · paper sheet detected

The opportunity, in numbers

Now the math behind what you just watched. Every inspection report carries ~23 minutes of work that happens after the part is measured — re-keying, verifying, cross-checking, formatting. Apprend collapses that tail. The numbers below are stated per-inspector so they scale to ATM's actual headcount, whatever it turns out to be.

Time saved / report
~23 min
~45 min today → ~22 min with Apprend
Hours saved / inspector / wk
~9.6 hrs
at ~5 reports/inspector/day · 5 days/wk
Annual reclaim / inspector
~$21.6k
at ~$45/hr loaded · 50 working weeks
Transcription errors
↓ >90%
target reduction vs. hand-keyed entries
per inspector ~23 min × ~5 reports/day = ~9.6 hrs/wk reclaimed
× loaded rate ~$45/hr × 50 wks ≈ ~$21,600/yr / inspector
scale to ATM × your inspector count = your annual upside
3 inspectors ≈ ~$65k/yr · 5 ≈ ~$108k/yr · 8 ≈ ~$173k/yr — hours reclaimed go back into inspection, fixturing, CMM programming, and out-the-door velocity.

Headcount, reports/day, and loaded rate are placeholders — these get replaced with measured values from ATM's actual job mix during Phase 2. Phase 1 establishes whether the accuracy is there to make those measurements worth taking.

How the pipeline runs

Four stages. Same paper trail you already keep — a digital copy lands on top.

01 · CAPTURE
Photo at the bench
Inspector snaps the completed op sheet with the shop phone, tablet, or fixed-mount camera. No tablet entry, no new workflow.
02 · EXTRACT
Handwriting OCR
Apprend reads the form, locates each row, and extracts the handwritten reading. Numbers, units, and inspector initials.
03 · VALIDATE
Tolerance check
Each reading is compared against the part's nominal and tolerance band — pass, warn, or fail — instantly flagged for review.
04 · DELIVER
Customer report
Digital row drops into the existing inspection spreadsheet template. Export as Excel or PDF; paper still gets stapled to the job.

Where the time really goes today

From the shop walkthrough: a 30-minute inspection is the floor, but the report doesn't ship until the cross-check, re-key, verify, and format steps are done. That tail is what disappears.

Today — paper, then re-key

~45 min
per inspection report
  • Inspect & handwrite readings · ~30 min
  • Pull prior op sheets to compare trend · ~3 min
  • Walk to the computer
  • Re-key every dimension into Excel · ~10 min
  • Verify each row against the paper · ~5 min
  • Format header & export to PDF · ~2 min
  • Staple paperwork to the job · ship

With Apprend

~22 min
— more than half the report time gone
  • Inspect & handwrite — spec & prior-op reading shown inline · ~18 min
  • Snap one photo at the end of the run · ~30 sec
  • Apprend extracts, validates, and populates the Excel · ~auto
  • Inspector reviews only the flagged rows · ~2 min
  • Customer-ready report exported in one click · ~1 min
  • Staple paperwork to the job · ship

~23 minutes saved per report · ~51% reduction. Not because measurement gets faster — it doesn't — but because the four steps after measurement collapse into a photo and a glance.

The path — proof, pilot, production

Three phases. Each one earns the next. ATM can walk away at any point with everything we've built up to that moment — accuracy data, extracted reports, working capture link. Nothing is locked behind a future commitment.

Phase 1 · Proof

2 WEEKS · FREE
  • 10 of ATM's completed sheets, one part family
  • Per-dimension accuracy report on your handwriting
  • Filled customer Excel report for each sheet
  • ATM commits ~1 hour total
  • Apprend bears all engineering cost
Decision point: if the numbers earn it, scope Phase 2 together. If not, walk with the data.

Phase 2 · Paid pilot

4–6 WEEKS · FIXED FEE · SCOPED FROM PHASE 1
  • Two part families, up to 60 sheets
  • Two-week live floor trial with one inspector
  • Measured time study vs. manual baseline
  • Costed production rollout plan for Bao
  • Success guarantee: second invoice waived if we miss
Priced together with Bao after Phase 1 readout — once we both know what the work actually requires.

Phase 3 · Production

ONGOING · SCOPED FROM PHASE 2
  • All ATM part families onboarded
  • Inspector accounts & full audit log
  • Quarterly model recalibration
  • Pricing sized to your measured job mix
  • Month-to-month, no annual lock-in
Discussed only after Phase 2 shows measured results on the floor. Not committed to in this document.

What happens in the next two weeks

Phase 1 is bounded by design — five steps over two weeks, ~1 hour of ATM's time total, ending with a real accuracy report on real ATM sheets. No agreement to sign, no kickoff onsite, no inspector training. Just proof.

DAY 0

Sample handoff

One email from Bao with: the blank op-sheet template, the Excel inspection report you send the customer, and 10 completed sheets from one recent part family. We confirm receipt the same day.

~15 min of Bao's time · samples in Apprend's queue
DAY 1–3

Field mapping on your op sheet

We map every field — fixed text, machine-printed nominals, handwritten readings, signatures — and wire each row to the right cell in your Excel template. Zero ATM time required.

Working extraction template for the chosen part family
DAY 4–7

Extraction run + early numbers

All 10 sheets go through the pipeline. Every reading is compared cell-by-cell against the original handwritten value. We share an early-accuracy snapshot mid-week so Bao sees progress before Day 14.

10 filled customer reports · first-pass accuracy table
DAY 8–10

Accuracy pass + edge cases

Anything below the accuracy bar gets a tuning pass. Edge cases (smudged readings, ambiguous decimals, surface-finish-max vs. ±tol) are documented so Bao sees exactly where the model is strong and where it isn't.

Tuned pipeline · edge-case catalogue
DAY 11–14

Readout — 30 minutes with Bao

One 30-minute call. We walk through per-dimension accuracy, the filled Excel reports, projected time savings against ATM's job mix, and an honest take on whether Phase 2 is worth scoping. ATM keeps everything either way.

Readout deck · all extracted data · go/no-go on Phase 2

How we measure success

Three numbers come out of Phase 1. They're how Bao decides whether Phase 2 is worth scoping — and, in Phase 2, they become the binding success bar that triggers the guarantee.

≥ 98%
Numeric reading accuracy
Per-character accuracy on handwritten measurements vs. the original sheet. Below this, the inspector can't trust the output.
0
Silent tolerance misses
An out-of-spec reading must never be reported as in-spec. False fails (over-flagging) are acceptable; false passes are not.
≥ 50%
Projected time saved
In Phase 1, projected against ATM's job mix using measured pipeline time. In Phase 2, measured on the floor against the manual baseline.

Investment, in stages

You pay for what you've already seen work. Nothing earlier. Phase 1 is on Apprend — we cover the engineering time because if we can't read ATM's handwriting at accuracy, there's no point continuing on either side.

If Phase 1 earns it

Phase 2 · Paid pilot

Scoped
4–6 weeks · fixed-fee proposal at the Phase 1 readout
  • Two part families, up to 60 sheets
  • Two-week live floor trial with one inspector
  • Measured time study vs. manual baseline
  • Costed Phase 3 rollout plan
  • Onsite kickoff + readout in Fremont
Success guarantee. Whatever the Phase 2 fee turns out to be, it's invoiced 50/50. Miss the success bar at the readout and the second invoice is waived — worst case for ATM is half the Phase 2 fee, with accuracy + time data still in hand.
If Phase 2 earns it

Phase 3 · Production

TBD
Scoped from Phase 2's measured job-mix data
  • All ATM part families onboarded
  • Inspector accounts + audit log
  • Quarterly model recalibration
  • Same-day support for production-blocking issues
  • Month-to-month, no annual lock-in
Not priced in this document. Phase 2 pilot fee is credited against the first 12 months of Phase 3 if ATM continues.
Phase 1 cost to ATM $0 (Apprend bears it)
Phase 2 fee scoped at the Phase 1 readout (success-guarantee bounded)
Annual reclaim ~$21,600 / inspector / yr (from "The opportunity")
= No dollar commitment from ATM until Phase 1 numbers are on the table. Phase 2 is then sized to what the work actually requires — not a number invented before either side has seen the data.

Your data, your IP

ATM runs aerospace, medical, and customer-confidential parts. We treat the data like it matters.

Captured sheets only

Apprend never touches your ERP, drawings, or customer files. Only the captured op-sheet image and the resulting extraction leave your floor.

Encrypted end-to-end

TLS in flight, AES-256 at rest. Captured images are deleted on a configurable retention window — default 30 days, can be 0 days on request.

No training on your data

ATM job data is not used to train shared models. Tuning happens against a separate pilot dataset, in a tenant scoped to ATM.

Audit trail preserved

Every extracted row is linked back to the original sheet image and inspector initials — the audit trail your ISO 9001 surveillance reviews expect.

US-only processing & compliance roadmap

All capture and extraction runs on US-region infrastructure (AWS us-east / us-west). ITAR / EAR-controlled parts can be excluded from the pilot floor trial; SOC 2 Type II audit and full ITAR compliance are on the post-pilot roadmap and can be scoped if either is a gating requirement.

Data ownership

ATM owns the captured images, the extracted readings, and the resulting reports. On termination, Apprend exports everything and deletes our copies within 30 days.

The questions you'll ask next

Lifted from conversations with shop owners weighing similar engagements. If yours isn't here, ask Vidhi.

Why is Phase 1 free?

Because the bar is honest: if Apprend can't read ATM's handwriting at the accuracy your inspectors would need to trust the output, neither side should waste any more time. The free phase is how we both find out — quickly, without putting ATM on the hook financially before there's evidence.

What does ATM actually have to do in Phase 1?

One email with three attachments: the blank op-sheet template, the customer Excel report, and 10 completed sheets from a recent part family. Then a 30-minute readout call at the end of week 2. That's it — ~1 hour of Bao's time total.

What if Phase 1 results aren't strong enough?

Apprend says so honestly at the readout and there's no Phase 2. ATM keeps the accuracy report, the edge-case catalogue, and the 10 filled customer reports. Apprend deletes ATM's source data within 30 days. No invoice, no awkward follow-up, no "let's just push through anyway."

What if Phase 1 results are strong — what's Phase 2?

4–6 weeks, two part families, a live floor trial with one inspector, measured time savings against ATM's manual baseline. Fixed-fee, priced together with Bao at the readout once we both know what the work actually requires. Success-guaranteed: invoiced 50/50, second half waived if we miss the bar.

What if my inspectors won't use it?

Phase 1 doesn't touch the floor — it runs on completed sheets from your existing workflow, so adoption isn't a question yet. Phase 2 is where the live floor trial happens, and it's designed around the inspector's existing flow: keep writing on paper, snap one photo at the end. The trial is also when we'd catch resistance early, while ATM still has the off-ramp.

What if Apprend goes out of business?

Phase 1 has no recurring commitment — there's nothing to cancel. ATM keeps the filled reports and the accuracy data regardless. For Phase 2 and beyond, on termination Apprend exports everything we have for ATM in the original Excel format plus the captured images, and any production scripts we built. Your customer reports are not dependent on us being online to produce them.

Can we run this on a customer-confidential program?

Yes for non-export-controlled work. For ITAR / EAR-controlled programs, exclude those parts from the Phase 1 sample set — we'd scope a compliant path before Phase 2 if you want to extend coverage. We can sign an NDA at Phase 1 if ATM prefers; not required.

Who's actually doing the work?

Vidhi Kothari, Apprend's CEO, runs the engagement personally — she is your point of contact from sample handoff through the Phase 1 readout and into Phase 2 if it goes there. One ML engineer pairs with her on the extraction pipeline. No handoff to an account team, ever.

About Apprend

We build OCR pipelines for manufacturing shops — not generic AI.

Apprend already runs a production handwriting-extraction pipeline at a Pennsylvania injection-molding customer, reading logbook data straight off the press floor into their review queue. The same pipeline is what you'd run for ATM's op sheets. Manufacturing-specific OCR — tuned for the messy edges of bench writing, tolerance shorthand, and the smudges that come with the job.

In production at
Injection-molding shop · logbook pipeline · 2025–present
Built by
Two ex-research engineers · ML + manufacturing systems
Track record
One live deployment · one pilot in flight
Pilot mode
Hands-on, build-it-with-you · no enterprise sales theater
References
Reference call with the Pennsylvania customer's QA lead available on request
Web
apprendtechnologies.com
Start Phase 1 this week

One short email and a folder of completed sheets.

That's the entire setup for Phase 1. No agreement to sign, no kickoff onsite, no commitment until Bao has seen real numbers from his shop's sheets. Reply to Vidhi when you have the four items below ready — we run the clock from sample receipt.

Blank op-sheet template
PDF or clean scan of the form your inspectors fill in at the bench
10 completed sheets from a recent part family
Pick a job that ran in the last 30 days · variety of inspectors is better than one
The customer Excel inspection report
The template ATM hands to the customer · blank or filled, either works
A 30-minute calendar slot for the Day-14 readout
Any time during the second week works · we'll lock it on the kickoff email
Vidhi Kothari · CEO, Apprend
+1 (916) 633-4363 · vidhi@apprend.tech
Proposal #ATM-2026-001 · dated 2026-06-05
Phase 1 offer open through 2026-06-26