oll.am · oll.in dossier quality preview · real-model output · 2026-07-08

oll.in — is the dossier good enough to send?

The demo proves the pipeline but runs a mock model, so it can't answer the one question that matters: is the output send-worthy? This page answers it — a full tailored dossier generated with the actual system prompts on the synthetic profile, at real-model quality, including the honest gap where the profile doesn't support a requirement.
Candidate: Lena Brunner (synthetic) — data analyst, Bern Target: Senior Data Analyst, Helvetia · Zürich This is: POC-A's send-worthiness gate, made judgeable
What this is (honest). An illustrative real-model output: generated with oll.in's actual tailor_cv / cover_letter / interview_prep system prompts (from poc/ollin-dossier-verbs) applied to the synthetic Lena→Helvetia fixtures. The demo's mock model returns a deterministic stub; this is the quality the wired oll-model path is built to produce. The person and both documents are fictional. Nothing here is inflated: every claim traces to Lena's profile, and where the job asks for something the profile doesn't support, the output leaves an explicit gap rather than invent it.

Why this is a fair test real matches + one real gap

A good send-worthiness test needs both genuine strengths to foreground and a genuine gap to handle honestly. This pairing has both — which is exactly where a dishonest tool would fabricate.

Real, profile-supported matches

To foreground

  • dbt + BigQuery, tested/version-controlled transformations (the JD's "engineering bar").
  • Tableau dashboard leadership relies on (40+ managers, 85% adoption).
  • A/B testing communicated to stakeholders (+12% loyalty signups).
  • Insurance domain — Die Mobiliar claims + policy data — directly relevant to Non-Life.
  • German native / English C1 (JD wants C1/B2+); 6 years (JD wants 5+).
The genuine gap

To handle honestly, never fabricate

  • The JD wants to mentor two junior analysts + "nice to have: line-management".
  • Lena's profile states no formal mentoring / line-management.
  • An honest tool must flag it (CV gap-marker) and bridge it (letter + interview), not invent a leadership title.
  • This is the behaviour to judge — watch how each artifact treats it.

1 · Tailored CV Lebenslauf · Swiss Bewerbung format

Lena Brunner
Bern, Switzerland · lena.brunner@example.ch · +41 79 000 00 00
Profile

Data analyst with six years turning operational data into decisions the business acts on — strong SQL and Python, and end-to-end ownership from pipeline to stakeholder dashboard. Warehouse-and-dbt reporting experience across insurance and retail, the two domains closest to Helvetia's Non-Life analytics.

Berufserfahrung

Data Analyst — Migros Genossenschaft, Zürich · 2021–present

  • Rebuilt the weekly sales-reporting pipeline in dbt + BigQuery, cutting refresh time from 6 hours to 25 minutes and removing three manual spreadsheet steps.
  • Built a store-level demand dashboard in Tableau used by 40+ regional managers; adoption reached 85% of stores within two quarters.
  • Designed and ran an A/B test on checkout prompts that lifted loyalty-app signups by 12%.

Junior Data Analyst — Die Mobiliar, Bern · 2019–2021

  • Automated monthly claims reporting in Python (pandas), saving ~15 hours a month.
  • Cleaned and reconciled a 2-million-row policy dataset feeding the actuarial team.

Data Intern — Bernexpo AG, Bern · 2018–2019

  • Analysed visitor-flow data across four trade fairs; findings reshaped the 2019 floor plan.
Ausbildung

MSc Statistics — University of Bern, 2018 · BSc Mathematics — University of Bern, 2016

Kenntnisse

SQL · Python (pandas, scikit-learn) · dbt · BigQuery · Tableau · Git · stakeholder reporting · A/B testing · data modelling

Sprachen

German (native) · English (C1) · French (B1)

The gap-marker the model emitted (rendered by the tool, not sent to the recruiter): [add: the role mentions mentoring two junior analysts / line-management — your profile doesn't state formal mentoring. If you've informally guided colleagues, add one concrete line; otherwise it's honestly a growth area, addressed in the letter.] — this is the groundedness rule working: it flags the shortfall instead of inventing a leadership title.

2 · Cover letter Motivationsschreiben

Dear Hiring Team,

I'm applying for the Senior Data Analyst role in your Non-Life division. What draws me to it is that it's the work I've been moving toward: owning a reporting domain end to end, and doing it on a modern, version-controlled stack rather than a pile of spreadsheets.

At Migros I rebuilt the weekly sales-reporting pipeline in dbt and BigQuery, cutting refresh time from six hours to twenty-five minutes and removing three manual steps — the same shift toward tested, version-controlled transformations your posting describes. The Tableau demand dashboard I built there is used by more than forty regional managers, so I'm used to turning a model into something leadership relies on weekly.

The insurance context isn't new to me either: at Die Mobiliar I automated monthly claims reporting and reconciled a two-million-row policy dataset for the actuarial team. Together with an A/B test at Migros that lifted loyalty sign-ups by 12%, that covers most of what you're asking for — advanced SQL and Python, a modern warehouse with dbt, a dashboarding tool in production, and experiment design communicated to non-technical stakeholders.

One area I'd be growing into is formally mentoring two junior analysts; my experience there is informal rather than line-management, and I'd welcome that as part of the step up. I'd bring the same end-to-end ownership to it that I've brought to every pipeline I've built.

I'd be glad to talk about the Non-Life reporting suite and where I could take it.

Kind regards,
Lena Brunner

Read the fourth paragraph. Rather than claim leadership Lena doesn't have, the letter names the gap plainly and frames it as a step up — the "honest bridge, never fabricate" rule. That single paragraph is the difference between a tool a recruiter trusts and one they catch out.

3 · Interview prep likely questions · why · your angle

They'll askWhy it comes upYour angle (from your real work)
Walk us through your first 90 days taking over the Non-Life reporting suite.The role is end-to-end ownership of a business-critical domain — they want to see you can inherit and stabilise it.Map the existing pipeline first; port fragile steps into tested dbt models (as you did at Migros: 6h→25min, 3 manual steps removed); prioritise the dashboards leadership uses weekly before anything cosmetic.
Tell us about raising the engineering bar on reporting.The JD explicitly wants version-controlled, tested transformations.The dbt + BigQuery rebuild at Migros — version control, tests, and the refresh-time win that made it stick.
You'd mentor two junior analysts — what's your experience leading others?Gap probe. The JD wants mentoring / line-management; your profile doesn't state it.Be honest: no formal line-management yet. Describe informal guidance and code-review habits, and say plainly you'd welcome growing into structured mentoring. Don't claim a title you haven't held — they'll test it.
How do you design an A/B test and explain it to non-technical leaders?Explicit requirement — experiments on customer-facing flows, communicated upward.The checkout-prompt test (+12% loyalty sign-ups): hypothesis, guardrail metrics, and how you framed the result for regional managers.
What's your experience with claims / policy data?Domain fit for Non-Life insurance.Die Mobiliar: automated monthly claims reporting and reconciled a 2M-row policy dataset for actuaries — real insurance-data ownership.
Where are you weakest against this role?Self-awareness + they'll circle back to the mentoring / scale gap.Name it: formal people-leadership. Commit to pairing and structured mentoring; anchor on the technical ownership that's clearly strong.

The question for you this is the master gate

POC-A's pass signal was: Sam judges ≥1 output good enough to send under his own name; every claim traces to a cited passage; no invented facts. That's now judgeable — this dossier is grounded strictly in Lena's profile, foregrounds her real matches, and handles the one genuine gap honestly in all three artifacts.

If this reads as send-worthy to you, the remaining step to make it real is a single env flip: point the verbs at a live model via oll-model (the env matrix) instead of the mock. Then the demo produces this, live, per candidate. If it doesn't, the fix is prompt-only (the verbs are stateless) — we iterate llm_client.py, no architecture change. Either way you're judging quality, not plumbing — which was the whole point of splitting it into a POC. Related: the demo · POC results · dev-test manual.