← Featured work

Engineering · Hybrid AI

Hermes — Hybrid AI IT Knowledge & Automation

A hybrid local/cloud platform connecting troubleshooting context, structured IT knowledge, runbooks, coding agents, and operational integrations.

Active engineering and integration work

Useful AI assistance depends on structured context, repeatable workflows, and a clear path for review.

  1. 01Operational context
  2. 02Structured knowledge
  3. 03Local inference
  4. 04Cloud escalation
  5. 05Review

An engineering platform for IT work

Hermes brings troubleshooting assistance, documentation generation, runbooks, ticket context, and automation into a hybrid local/cloud workflow. Its purpose is to make real operational knowledge usable across repeated technical tasks.

How the pieces connect

Structured project knowledge and runbooks supply context. Local inference through LM Studio supports local model workflows, while cloud AI and coding agents provide an escalation path. Git branches and worktrees isolate engineering changes for review.

What I worked on

  • Organized IT and project knowledge for troubleshooting, documentation generation, and repeatable engineering workflows.
  • Used LM Studio, OpenAI Codex, OpenCode, Git branches/worktrees, and API integrations across local and cloud tasks.
  • Developed Make.com workflows that transform RepairDesk active-ticket data and enriched context into structured JSON inputs.
  • Investigated missing or malformed API responses and retained human review around consequential operational actions.

Current scope and boundaries

The platform includes real integration development alongside experiments. This does not mean every automation is deployed in production or that generated recommendations are authorized actions. Herdr is a separate project focused on the reliability of coding-agent execution and review.

What this demonstrates

The engineering work is in the connections: shaping context, handling failed data, choosing an execution path, isolating changes, and making outputs reviewable.

Examples describe engineering methods. Client identities, endpoint identifiers, credentials, and ticket contents are omitted.

Continue exploring

01 · Professional · Endpoint security

Qualys Vulnerability Remediation & Patch Management

From vulnerable assets to verified endpoint state: patch targeting, Windows applicability analysis, deployment monitoring, failure investigation, and rescans.

Hands-on operational work

  • Qualys Patch Management
  • Vulnerability Management
  • Windows Server
  • Windows Update

02 · Professional · Observability

PRTG Infrastructure Monitoring & Remediation

Auditing ESXi and network monitoring, correcting safe configuration issues, validating discovery, and documenting the exceptions that still need investigation.

Production monitoring review

  • PRTG Network Monitor
  • VMware ESXi
  • SSL/TLS
  • Auto Discovery

From evidence to an engagement

Facing a similar technical problem?

The case study shows relevant experience—not an independent-client endorsement. Explore an independently scoped service or describe what you need.

AI & Local AI Solutions ↗Discuss a Project ↗