search form icon

I gave Claude for Manufacturing an 8D case with 7 hidden traps

Claude for Manufacturing vs. an 8D case with 7 hidden traps: 7 of 7 caught, plus 3 unplanted issues Claude for Manufacturing gegen einen 8D-Fall mit 7 versteckten

The biggest value of AI in quality management may not be writing reports faster. It may be finding the flaws in our own analysis.

That is the main lesson from my test: what convinced me were not the finished drafts, but the moments when the AI exposed a gap, a contradiction or a conclusion drawn too quickly.

I ran Anthropic's new Claude for Manufacturing plugin through a full 8D case with seven hidden traps. It caught all seven and found three more problems I had not planted as traps. The quality logic is stricter than many 8D reports I have reviewed in supplier quality. Customer-specific 8D formats, FMEA feedback and approval packages are not covered out of the box.

The case ran in a fictional plant with fictional data. Claude generated the data set and ran the chain in one session. That makes it a function test, not a blind test.

7 of 7hidden traps caught
3more findings, not planted
0invented proofs of effectiveness

What Claude for Manufacturing is

A plugin for Claude, released by Anthropic on 12 November 2026. It is not a separate product and needs a Team or Enterprise plan.

PartWhat it contains
Skills17, across sales, quality, operations, supply chain, design and setup; 4 of them for quality
ConnectorsMicrosoft 365, Oracle NetSuite, Infor M3, Autodesk Fusion; other systems through a custom-connector skill or scheduled file exports
Approval gatesNothing is sent, applied or written to a system without an explicit yes from a named person
StatusA reference implementation, “not actively maintained” according to its README

What a skill is: a written work instruction for Claude, much like a standard operating procedure. It defines the sequence, the rules, the edge cases and the approvals. The model brings the intelligence; the skill decides how it works.

Claude chat with the slash menu open, listing the Claude for Manufacturing skills such as breakdown-diagnosis, inspection-to-capa and ncr-writeup
This is where it starts: type “/” in Claude and the installed plugin lists its skills, each with a short description. (Screenshot from a German-language Claude interface.)

The four quality skills

Two skills do the work, two chain them together. All four share two rules: compute, don't eyeball and rank, don't conclude.

SkillWhat it doesRule that stood out
ncr-writeupWrites the nonconformance: what was found, against which requirement, how many parts, where they areNo cited requirement, no NCR. “Not checked” is never written as zero
root-cause-capaPuts measurements, sensor and maintenance data on one verified timeline, ranks causal chains, drafts the 8DEvidence for and against every link; D6 and D8 stay empty
inspection-to-capaChains the two, up to a redacted customer versionTwo approval gates; a recurrence is never redacted
supplier-escape-to-alternate-sourceFrom a supplier-caused defect to an RFQ for an alternate sourceBlaming a supplier needs its own approval; a tie means no blame

The test setup

A classic customer escape: a bore undersize on a critical characteristic, with parts already at the customer.

ElementTest data (all fictional)
PlantMusterwerk GmbH, a fictional pump-component supplier; one site, three shifts
Part and characteristicValve housing 4711-200 rev C, bore Ø 12.000 +0.050/0, critical characteristic (CC)
ProductionThree work orders on one machining centre; two from raw-material lot CH-2311, one from CH-2310
Inspection data57 sampled measurements; the CH-2311 runs drift into undersize
Material certificatesCH-2311 at 103 HB against a spec of 75–95 HB
Where the parts are500 at the customer, 120 in transit, 280 in stock, 40 at the machine
Customer agreementNotification within 24 hours; 8D within 10 working days for critical characteristics
HistoryA closed 8D on the same defect from March, plus a mislabelled old NCR

Results: seven traps, seven caught

TrapWhat a weak investigation doesWhat the plugin did
Recurrence after a closed 8DTreats it as a new caseFlagged “recurrence, previous fix failed”; D7 explains why the old fix did not hold
Parts at the customerNotifies when the 8D is doneDrafted the notification immediately, deadline taken from the quality agreement
Unknown whether parts are installedLeaves the location outListed it as “not checked”, never as zero
Material lot above hardness specBlames tool wear againFound it through lot clustering: 10 of 37 samples out on CH-2311, 0 of 20 on CH-2310
Clocks that do not line upMatches events by eyeRefused to correlate across the unverified clock and said what still holds
Night shift looks guiltyPoints at the operatorCalled it small numbers at the end of each run, not a people problem
Mislabelled old NCRCounts it as historyExcluded it: the work order belongs to a different part

Every figure came from code over the data, with a figures block showing the filter behind each number.

Three findings I had not planted as traps

  1. A detection gap. Four readings below tolerance were recorded on 11 and 12 November, and the work order still shipped on 13 November. The 8D therefore splits D4 into occurrence and non-detection, and D5 adds a control chart with a stop rule.
  2. A hard stop in the supplier chain. There was no drawing and no revision for the raw part, and the supplier specification carried no index. The plugin refused to build an RFQ on an unverified revision and flagged the real risk first: the supplier who caused the defect is the only approved one.
  3. A control chart set too tight. In the simulated follow-up production, the new stop rule fired five times with zero bad parts. The limits had been computed from one short run; they were checked statistically and recalculated from 60 values.

Nobody set these up as traps; Claude spotted them on its own from the data and the rules in the skills. That is what makes the test interesting.

The 8D, the gates and the customer version

The chain stops at three gates and says where it stopped. In the test it paused twice for my confirmation and once at a hard stop.

The AI drafts every step; people approve at every gateNCRrequirement citedGate 1owner confirms NCRHistory + timelinedid the old fix hold?Ranked causesfor and against8D draftD6 and D8 left emptyCustomer versionredaction as a diffGate 2owner approves diffTo customersent by a personSupplier flagwith counter-evidenceSupplier gatecommercial claimRFQ packagealternate sourceHard stop in testno raw-part revisionmaterial lot implicated
On a phone, swipe sideways to see the whole flow.

The 8D followed the plant's own template. D1 to D5 and D7 were drafted from the evidence. Every D5 action names the link in the causal chain it breaks; 100% inspection was moved out of D5 and labelled “improvement, not corrective action”. D7 explained why the March fix failed: the earlier lot was also above hardness spec, and nobody looked.

The customer version was produced as a redaction diff: supplier name, operator IDs and maintenance orders out; the recurrence stays in. The quality owner approves the diff, not just the clean document.

Limits

  • Function test, not blind test. Claude built the data and ran the chain in the same session. A real test needs a case whose answer the system does not know.
  • Not ready for customer-specific quality rules out of the box. Customer 8D formats, FMEA and control-plan feedback, approval packages and customer portal formats are not included. The plant's own template can be loaded, and the skills can be adapted.
  • Data quality decides. Old 8Ds that sit in no connected system are not found. The recurrence check is a search, not learning.
  • Cloud and licence. It runs on Anthropic's cloud and needs a Team or Enterprise plan. Commercial plans are not used for model training by default; retention controls are an Enterprise feature.
  • Reference version. Anthropic does not promise maintenance. Skills may change; this report reflects the state of 15 November 2026.
  • Competence. If the AI always ranks the causes, teams may stop practising problem solving.

Who it is for

FitWhoWhy
Good fitMid-sized manufacturers without deep CAQ or an AI team, running Microsoft 365, NetSuite or InforFast start into clean NCR and 8D practice; the gates enforce human sign-off
With adaptationSuppliers with customer-specific quality rulesAdd skills for their 8D format, FMEA and control-plan feedback, approval packages
Not yetMulti-tier supply-chain steering; plants with a no-cloud policyNo n-tier view; cloud only

For managing directors, three questions decide whether to start: which data classes may go to the cloud, which systems you are willing to connect, and who in your quality team owns the approvals. Start with one product line and one recent, closed 8D you know well. Run it again with the plugin and compare.

My verdict

Not a substitute for problem-solving skills, but a serious sparring partner.

For years we have asked how AI can help quality engineers write reports faster. Perhaps that is the wrong question. What the test showed above all is what a team easily overlooks: a detection gap, a missing revision, a control chart set too tight.

The AI drafts. People check the evidence, decide and prove effectiveness.

In pizza terms: Claude puts on the toppings. Whether the base is done is the pizzaiolo's call.

Get the test package — free

Fictional data set, NCR, internal 8D, customer 8D and redaction diff — everything from this test, in English (translated from the German original run). Unlock once with your email and you also get access to all ZeroDefectPizza Excel templates.

Unlock with email & download

Sources

ZeroDefectPizza is not affiliated with Anthropic. All plant, part, supplier and customer names in the test are fictional.

Martin Schneider, founder of Zero Defect Pizza and supplier quality expert
Written by Martin Schneider — a decade on the customer side of supplier quality, founder of Zero Defect Pizza. More about Martin →
Table of Contents
    Add a header to begin generating the table of contents
    Newsletter
    Social Media
    Related Posts

    Short answer The cost of poor quality is everything you pay because something was not right the first time: scrap,......

    Short answer Cost of quality reporting means giving failure costs a line of their own: a booking code for rework,......

    Have you ever wondered why some problem-solving efforts succeed while others fail? I have seen thousands of 8D reports and......

    Next step

    What are quality problems really costing you?

    Most of it is in your P&L — just not labelled as quality. The free Cost of Quality calculator gives you a first order of magnitude in 10 minutes. If you would rather talk it through: 30 minutes, no slides, no sales pitch.

    Newsletter Sign-Up
    Name

    Contact Form

    Name
    Newsletter