Second-pass review of this session's work by another agent. It corrected several
real mistakes of mine and finished F06 gaps I had left open. Reviewed, verified
and committed as-is.
THE MISS THAT MATTERS
`job_scout/state/applications.json` — the authoritative application registry
introduced by F02 — was never actually tracked. `job_scout/state/*` in
.gitignore silently excluded it, so my checkpoint commit afdef7e claimed to add
it and did not. Only `application_cohort.json`, the GENERATED projection, was
version-controlled; the source of truth and the migration history backup were
not. .gitignore now carries explicit negations for both.
MY ERRORS, CORRECTED
- "kastellaun" was in CH_LOCATION_KEYWORDS. Kastellaun is in Rhineland-Palatinate.
I took it from a Bundeswehr reserve listing and filed it under Switzerland -
precisely the class of bug F12 existed to fix.
- The F12 fix only widened the keyword list; SmartRecruiters still discarded the
structured country, which was the concrete case the review named
(city=Baar, country=CH). The adapter now preserves it, and a COUNTRY_NAMES
mapping gives country precedence over a bare town name.
- F15 was applied to Taleo and Prospective only. Greenhouse still wrote
`updated_at` into `posted`; it now uses `published_at` and carries provenance.
- My negation guard `\b(no|not|...)\b[^.;]{0,60}$` was too loose - an unrelated
"not" within 60 characters could mask a real claim. Tightened to require the
negation to govern the term.
- F18's retirement of the macro-count rule missed "Four to six compact skills
lines" in the workflow; removed now.
F06 GAPS I LEFT OPEN, NOW CLOSED
Date-format validation on education/employment periods (the 2035-99 case named
in the review), evidence-structure validation, referential integrity on evidence
source files, and the missing-identity KeyError.
F10 TAKEN FURTHER, AND RIGHTLY
I demoted the US-GPA fields to *_orientation_only. They are now removed
entirely, with grade_output_rule saying what to do instead: use the German grade
and scale, and if a recipient requires a US GPA, use THEIR method and record it.
Keeping a number derived by a non-recognised method invites its use.
Also: the Capgemini omit-preference now sits in experience_capgemini.md itself,
alongside the instruction not to fill or explain the intentional gap.
BIS BASEL - REJECTED 2026-09-11
jr100429, applied 2026-07-10, no interview, no reason given. Recorded in the
registry with a dated event and in the decision log; the "prep interview brief
when screening lands" next action is cleared. This also settles the 2026-09-04
observation that the req had vanished from the BIS board - it was a real
rejection, not just a closed posting.
VERIFICATION I RAN MYSELF BEFORE COMMITTING
49/49 tests. Validator PASS with 0 advisory warnings. Package manifest and
registry views current. All 12 F12 location cases still correct, including
Kastellaun now rejecting. The F05 counter-proof still catches all 9 violations.
SBB, NVIDIA, RUAG and Kdo Cy resumes still scan clean. Diffs are net-additive
across every reference file - the deletions are replacements, not losses.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qej5SBvhcbGXHwLqNWiskM
User-confirmed 2026-09-11, extending the Arbeitszeugnis line about supervising
students and their theses.
Zweitpruefer (second examiner) is a FORMAL role carrying assessment
responsibility, not informal mentoring. That matters because "developing other
engineers" keeps appearing as a JD requirement and the profile has otherwise
only team-role evidence to offer - Security Champion, the Generali Java
community, Application Owner training. SBB asked for it explicitly and the
prepared answer had to fall back on exactly those.
Limits recorded with it: exactly ONE thesis is confirmed as second-examiner
work, so it must not be pluralised; the wider number of students supervised is
not recorded; and none of it is people management. `forbidden` now blocks
"supervised multiple theses", "lecturer", "taught a course" and an academic
appointment reading.
Carried into both data bundles so it can actually be selected - the BS-6 lesson
from the same week: evidence that reaches no bundle cannot be chosen.
Validator PASS, 37/37 tests.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qej5SBvhcbGXHwLqNWiskM
D1/D2 - Bosch title and promotion: CONFIRMED by the user. The promotion and its
timing are correct and came from a re-grading (Neueinstufung). The Zeugnis does
not contradict it - it names DEPARTMENTS ("Ingenieur" in Fertigungstechnologie
1/2/3) rather than job titles. Separately corrected a false provenance note that
claimed official_title was "the formal combined string on the Zeugnis"; it never
came from that document, it comes from the user and LinkedIn.
D3 - part-time from 2021-09: NOT recorded, by the user's decision. Noted for
completeness that tenure wording such as "over ten years" measures elapsed time
and is unaffected; it would only matter if a document claimed FTE years, and
none does.
D4 - French and Italian: the Swisscom Zwischenzeugnis says he uses both
professionally on a regular basis. The user reviewed the sentence and confirmed
it is an ERROR IN THE DOCUMENT. DE/EN only stands. Recorded in
identity.language_note so nobody rediscovers the line and acts on it, with the
practical warning that a reader of that Zeugnis may take it at face value.
D5 - the RUAG MSSQL rule-out: the DECISION stands (user does not want it
revisited), the REASONING is corrected. Two of its four premises were wrong:
MSSQL is not 0 (Fraunhofer SCEDAS ran on Microsoft SQL Server), and "his stack
is AWS cloud-native" was too narrow - the Swisscom Zeugnis documents component
ownership for ETL into the Teradata DWH. Talend and SAP S/4HANA remain genuinely
0, and the required line reads "Aufbau UND Betrieb" while he has documented
Betrieb only - so the skip is still defensible, it was just better than its
written justification. Both RUAG decision rows now carry the correction and a
standing rule for future DWH postings.
D6 - Vizrt end date: 2018-05 stands by the user's decision.
And the follow-through that matters: the data-warehouse, MSSQL and mentoring
evidence is now IN THE BUNDLES, not only in claims.json. BS-6 showed last week
that evidence which reaches no bundle cannot be selected - this is the same
failure mode, caught the same week. The DWH entry carries its scope limit
explicitly: documented Betrieb, not Aufbau.
Validator PASS, 37/37 tests.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qej5SBvhcbGXHwLqNWiskM
The review's key point is that the error ran BOTH ways.
Overstatement, narrowed to canonical scope:
- BS-1 variants claimed "eliminated manual wafer inspection", "no manual
intervention" and "unattended quality monitoring". Canonical BS-1 supports a
qualitative reduction whose size is unverified. Reworded; the scope limit is
now stated inline where the variants are written.
- bundle_data_platform called BS-1 a "zero-downtime constrained deployment".
Integration into a fab that runs continuously is not a measured zero-downtime
property.
- experience_swisscom carried "grounded retrieval" as a skill and ATS keyword
while SW-8 records retrieval implementation as explicitly unknown, and its
reframing note invited "evaluation discipline" although formal model
evaluation is a globally forbidden pattern. Both removed.
- PyTorch sat in bundle_ml_ai_engineer as a bold tool and an ATS must-include
with no certification context - the exact way the context gets lost.
Undervaluation, the half that quietly costs him roles:
- BS-6 (Linux administration, intensive Ansible incl. self-written extensions)
has been canonical since 2026-08-27 but appeared in NO bundle, so the normal
selection paths could not see it. Added to the data-platform and data-engineer
bundles with its currency limit (employer-side ended Dec 2022; PP-3 is
personal) and the standing GitOps prohibition.
- Linux, Ansible and Bash were missing from skills_taxonomy entirely.
- skills_taxonomy still said the IBM certification year was "not recorded" and
that PyTorch needed verification; both were settled on 2026-08-27.
Not rewritten, deliberately: the NVIDIA and RUAG cover letters state the
production line could not be stopped. That exceeds the canonical record but is
plausible and both are already submitted. Recorded as an OPEN ITEM in
experience_bosch.md to be confirmed with the user before any reuse.
Validator PASS, 31/31 tests.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qej5SBvhcbGXHwLqNWiskM
Scout run 2026-09-04 (36 companies, 778 eligible) plus the NVIDIA package it
surfaced, and the tooling and policy fixes found along the way.
Application
- NVIDIA Senior DevOps Engineer, Zurich (JR2024256): submitted 2026-09-05.
Evidence Fit 64/100 Stretch, hard gate FAIL x2, channel Weak. Sent on an
explicit user override with the working model unresolved, so hybrid-vs-onsite
is a live screening topic. 2pp resume + 1pp cover letter, both validators
PASS, 0 boxes, 0 Tier 1 findings open.
Policy
- Drop the 7 Core / 2 Adjacent / 1 Stretch cohort caps. They had no derivation
and were overridden whenever they bound, and the cohort was confounded: it
tested fit class while holding channel constant at Weak across all six
applications. Keep the recording, drop the rationing.
- Channel replaces the slot budget as the rationed variable: no application
goes out cold when a named contact is published and reachable.
- Propagated through shared_ops, session_file_template, cohort_tracker
(counts, never counts-against-a-target) and application_cohort.json.
Tool fixes
- fetch_workday emitted 404 URLs for every Workday company (NVIDIA, Novartis,
Equinor): externalPath is site-relative and needs the locale + site prefix.
6/6 short-form 404, 3/3 long-form 200. 773 dead links repaired across 42
archived reports.
- find_decision_url silently de-linked decisions on two boards, which is why
ruled-out roles kept resurfacing as undecided. RUAG rotates its UUID on
repost; BIS migrated its vacancy URL scheme, orphaning 5 decisions including
a live application. Fixed as a two-tier match, not a slug key -- slugs
collide (two live RUAG reqs shared one).
Knowledge base
- claims.json: add Bash / shell scripting, the third canonical gap of this
shape after Ansible and Linux administration.
- bundle_data_platform: BS-4 was framed as a delivered observability stack over
what claims.json calls a proof of concept -- the defect the 2026-08-21 sweep
was told to look for.
- CLAUDE.md and AGENTS.md: correct the RUAG Data Lakehouse shortlist claim,
which the JD does not support and which both files still asserted.
- resume_template: comment-guard the missing babel/ngerman language block.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QFb8tTCig5r1KzkQiNXcYt
Cover letter: 1 page, 270 words, 3 paragraphs, validator PASS. Carries
the one thing the resume structurally cannot - why a Swisscom data
engineer credibly wants a research-platform seat at a market maker,
which against an ex-FAANG field is the main differentiator.
Deliberately uses no external hooks. cl_reference.md says to omit an
unnecessary hook rather than spend words proving company familiarity, so
the only hook is the JD's own language, scraped verbatim and first-party.
No named executives: nothing to verify, and nothing that reads as
name-dropping. The letter also states the R1 gap plainly rather than
hiding it, because a technical reviewer will find it in the first
question anyway and owning it is stronger than being caught by it.
PP-1 appears with its personal-project label and an explicit "I make no
claims for its results".
Separately, loading the bundles for this letter surfaced two live scope
traps. The 2026-08-21 correction that fixed the SW-1 violation in
bundle_data_engineer.md ended with "check the other four bundles for the
same pattern". That sweep was never done, and two of them carried it:
bundle_data_platform.md - the S5 cover-letter hook read "migrating
Swisscom's legacy ETL stack to a cloud-native AWS platform", and its
narrative thread said "migrating an entire ETL infrastructure". Both
pair a full-ownership framing with a company-scale object, which
claims.json SW-1 forbids outright.
bundle_ml_ai_engineer.md - the SW-1 reframing row read "Built
cloud-native data infrastructure on AWS ... the scalable data layer",
which is both a full-ownership verb on an org-scale object and an
unverified scale claim.
Both rewritten to the scoped form with inline scope warnings, matching
the data_engineer fix. bundle_analytics_engineer.md and
bundle_semiconductor.md were checked and are clean.
These were loaded traps: any future cover letter built from either
bundle would have started from a sentence claims.json forbids.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MHtzyTKBcg6BWhD5qFegtK
13 bullets, 6 skills lines, International Tech profile in English with an
explicit Languages line naming German as mother tongue (user instruction).
Framing leads on operate-and-own — Component Ownership with on-call and
governance answers the JD's "Betrieb" and "Verantwortung für Qualität und
Nachhaltigkeit" — and carries the Bosch industrial sensor-data thread
(defect records, wafer inspection images, PCM parameters) against the
role's vorausschauende-Wartung purpose. GenAI/LLM material dropped.
Two deviations from the approved 11-bullet plan, both deliberate:
Fraunhofer keeps one combined bullet rather than zero, because dropping the
role opens an unexplained 21-month gap between Vizrt and Bosch; and BS-1 is
added as a fifth Bosch bullet, HIGH priority in the bundle and directly
relevant to an employer running a 24/7 network.
Kept the guarded page break after testing the natural flow: without it page 1
fills, but two Bosch bullets land on page 2 with no visible employer header.
Hierarchy beats page-fill, and page-fill quotas were removed on 2026-07-27.
Gates: canonical validator PASS (0 warnings), forbidden-token scan PASS (none
of the seven non-canonical JD tools present), scope-discipline scan PASS,
compile PASS at exactly 2 pages, both pages visually inspected. SW-1 and SW-7
bullets also read by eye against their claims.json forbidden lists.
Not submitted — held pending the Anforderungsniveau K comp answer.
Also fixes a KB defect found during generation: bundle_data_engineer.md §S5's
cover-letter hook read "leading the migration of our legacy stack", a
full-ownership verb on a company-scale object that contradicts claims.json
SW-1 and its own narrative thread. Rewritten, warned inline, and recorded in
the CLAUDE.md corrections log. The other four bundles are unchecked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WpMtWFtYkGkjSMShuTgXiB
dennisthiessenandClaude Opus 5