feat: rebuild evidence-first application workflow

knowledge_base/extractions/thiessen_cv_master_profile.md

@@ -62,7 +62,7 @@
 
 ---
 
-### 2. BOSCH Semiconductor Manufacturing — Dresden, Germany | Feb 2020 – Jan 2023
+### 2. BOSCH Semiconductor Manufacturing — Dresden, Germany | Feb 2020 – Dec 2022
 **Title (CV-1):** (Senior) Data Analysis Engineer
 **Title (CV-2):** (Senior) Engineer Data Analysis
 
@@ -76,7 +76,7 @@
 
 ---
 
-### 3. Fraunhofer CML — Hamburg, Germany | Sep 2018 – Jan 2020
+### 3. Fraunhofer CML — Hamburg, Germany | Sep 2018 – Oct 2019
 **Title:** Research Software Engineer
 
 **Bullets (combined):**
@@ -89,7 +89,7 @@
 
 ---
 
-### 4. Vizrt — Bergen, Norway | Jul 2017 – Aug 2018
+### 4. Vizrt — Bergen, Norway | Jul 2017 – May 2018
 **Title:** DevOps Engineer
 
 **Bullets (combined):**
@@ -104,10 +104,9 @@
 **Title:** Software Engineer
 
 **Bullets:**
-- CV-1: Python/C++ development for distributed backend components; implemented test automation and long-term maintainability practices
 - CV-2: Software Engineering for a process-oriented workflow web-portal using Java/J2EE, JavaScript and Oracle DB
 
-**Key tech stack:** Python, C++, Java, J2EE, JavaScript, Oracle DB
+**Key tech stack:** Java, J2EE, JavaScript, Oracle DB, BDD/Selenium/JBehave, Jenkins, UIPath
 
 ---
 
@@ -123,26 +122,30 @@
 
 ## Skills Inventory
 
-### Programming Languages
-Python, SQL (Postgres, MySQL, Oracle, Impala/Hadoop), Java, C#, TypeScript, C++, JavaScript
+This inventory is descriptive evidence, not resume-ready output. The canonical
+output policy in `resume_builder/canonical/claims.json` controls every use.
 
-### Frameworks & APIs
-Flask, FastAPI, Django, Swagger/OpenAPI, Express.js, J2EE, .NET, Entity Framework, SQLAlchemy
+### Production-current
+Python, SQL, AWS (S3, Glue, Athena/Iceberg, Redshift), Airflow, Kafka, Oracle,
+Teradata, Kubernetes, Docker, GitLab CI/CD, CloudFormation, data products,
+metadata/governance and on-call production operation.
 
-### Data & Pipelines
-ETL/ELT design, data modeling, Airflow, Kafka, SAP BODS, Hadoop/Impala, Teradata DWH, SQL performance tuning (explain plans, indexes, partitions)
+### Production-historical
+Java, C#, Jenkins, Ansible, Hadoop/Impala, ELK Stack and TIBCO Spotfire.
+C++ and JavaScript/Express.js were used in bounded historical roles.
 
-### Cloud & Infra
-AWS (S3, Glue, Athena, Redshift, Lambda, Step Functions), Docker, Kubernetes, Ansible, CI/CD, IaC
+### Hands-on-current or proof-of-concept
+LiteLLM, custom GPTs, Kiro and VS Code/Copilot are hands-on current evidence.
+Grafana, Prometheus and Loki are supported as Bosch proof-of-concept work, not
+as current platform ownership.
 
-### ML & AI
-PyTorch, SciKit-Learn, Pandas, NumPy, Matplotlib, Plotly, Mockito, ML inference deployment (Docker/K8s)
+### Certification/coursework context only
+TensorFlow/Keras and PyTorch are not professional production claims. Use only
+with explicit certification or coursework context.
 
-### Observability / DevOps
-ELK Stack, Grafana, Prometheus, Loki, Jenkins, Git, pytest
-
-### Blockchain (bonus)
-RPC APIs, public node operation, on-chain data via RPC/REST, basic Solidity, Kraken client since 2017
+### Unverified or forbidden in generated documents
+TypeScript, FastAPI, Flask, Django, LangChain/LangGraph/LlamaIndex, Terraform,
+Azure, GCP, formal model evaluation and LLM fine-tuning remain unsupported.
 
 ### Legacy / Enterprise
 Oracle, Teradata, SAP BODS
@@ -178,8 +181,8 @@ Oracle, Teradata, SAP BODS
 
 ## Provenance Notes
 
-- **Safe to claim (full ownership):** All items listed under each position — solo developer work clearly attributed
-- **Shared/team work:** Bosch ML pipeline integration — context suggests team effort; hedge as "led" or "owned end-to-end" only if confirmed
+- **Safe to claim:** Only facts that also appear in `resume_builder/canonical/claims.json`; this older CV synthesis is not authoritative.
+- **Shared/team work:** Apply the canonical claim's ownership scope and allowed verbs. Never infer solo ownership from a CV bullet.
 - **Do NOT claim:** Any results from collaborators at Fraunhofer research projects (NLP, Digital Twins) unless specific contribution confirmed
 - **RiskAhead:** Personal project framing only — not a commercial product, not peer-reviewed