Work
This is a curated set of customer-readable engineering evidence: research projects, prototypes, architecture examples, selected applications, and technical experiments. Each item is labeled so a prototype is not mistaken for paid client work and a test is not mistaken for a production result.
Featured Case Studies
Engineering Research Project
A multi-device computer-vision platform exploring capture, analysis, annotation, datasets, evaluation, security, recovery, and reproducible research.
Evidence state: Implemented research workflows; deterministic tests; physical validation remains explicitly not passed.
Read the case study
Engineering Prototype
A native iOS and Android field workflow for image capture, local analysis, project history, issue documentation, and PDF reporting.
Evidence state: Implemented prototype and current project screens; no customer deployment or ROI claim.
Read the case study
Architecture Example
A human-reviewed claims architecture with routing, policy and repair context, confidence handling, validation, and audit records.
Evidence state: Workflow design evidence; not represented as an implemented client system.
Read the case study
Architecture Example
A route-aware rescheduling design that connects customer matching, feasible appointment choices, proposals, and operations approval.
Evidence state: Workflow design evidence; no deployment or operational-outcome claim.
Read the case studySelected Projects & Products
Mobile product work, safety-bounded companion architecture, movement-analysis concepts, and engineering experiments provide breadth without competing with the strongest featured evidence.
Detailed Evidence
Some projects include architecture documentation, experiment methodology, test plans, validation reports, datasets, and research notes. That material stays beneath project context instead of becoming a global directory.
Customer-readable problem, constraints, evidence, and limitations.
Implementation scope, product context, and project-local navigation.
Methods, experiments, reports, datasets, and known limitations.
Work → OrganicVision case study → OrganicVision project → detailed research.
Describe the software, operating constraints, and decision you need to make. HerbDev can identify the closest evidence and the gaps that still need validation.
Discuss Your Project“Remove my test data” clears all AI 101 and ML 101 scores, reviews, project checklists and rating selections, plus saved vocabulary and recent history in this browser. Test entries cannot be separated from other learning progress. Cookie preferences, security protections, submitted feedback, contact emails and past analytics are kept.