Skip to content
View dynamic-dome's full-sized avatar
🌅
🌅

Highlights

  • Pro

Block or report dynamic-dome

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dynamic-dome/README.md

Dominic Meiser

M.Sc. Mechatronics → measurement systems, sensor data, and applied research → observable, human-governed AI agent systems.

I transfer the discipline of measurement — traceability, validation, and explicit limits — into agent-assisted Python and FastAPI workflows. My work focuses on explicit state, persistent knowledge, traceable tool use, verification, and human approval.

Public repositories and case studies show architecture, tests, limits, and failure paths. Operational cores and confidential data remain private.

Selected work

Project What it demonstrates Status Limits
DCO Reference Queue, worker, verification, and an explicit human approval gate Reference implementation Synthetic examples; not an export of the private operational system
Orchestrated Bridge Separated roles, persistent state, trace files, validation, workspace-scoped builds, and an explicit acceptance boundary Working public reference Deterministic public demo; operational deployments remain private
Agent Skill Index Capability discovery, governance metadata, and privacy-aware indexing Public tool Demonstrates the indexing layer, not a complete agent platform
Dynamic Workshop Structured modules, demos, exercises, mentor resources, and a testable playground Curriculum Educational material; not a production service

Methodological foundation

My path from measurement engineering to AI agent engineering explains how work with sensor data shaped the way I build software systems. The Master's thesis case study shows feature selection, leakage control, sample-level validation, and held-out testing. The reported 98.8% refers only to test balanced accuracy for material discrimination.

What I work on

  • Agent-assisted Python and FastAPI workflows
  • Explicit state, memory, and retrieval
  • Traceable tool calls, tests, and verification
  • Human approval and operational boundaries
  • Sensor-data analysis and evaluation methodology

Selected case studies

Role focus

I am looking for an early-career role as an Agentic AI Engineer, Applied AI or Machine Learning Engineer, or Data Engineer, in applied research or industry. My background in measurement engineering is most useful where machine learning meets sensor and industrial data, such as predictive maintenance or industrial AI.

Portfolio · Profile and CV · LinkedIn

Pinned Loading

  1. dco-reference dco-reference Public

    Minimal runnable reference for queued agent work, verification, and explicit human approval.

    Python

  2. orchestrated-bridge orchestrated-bridge Public

    Public reference for separated agent roles, persistent state, trace files, validation, workspace-scoped builds, and an explicit acceptance boundary.

    Python

  3. agent-skill-index agent-skill-index Public

    Privacy-aware capability index for discovering and governing reusable agent skills.

    Python

  4. dynamic-workshop dynamic-workshop Public

    Structured AI-engineering curriculum with demos, exercises, and testable labs.

    HTML

  5. agentic-os-plugin agentic-os-plugin Public

    Persistent per-project memory for Claude Code (public export of agentic-os)

    Python