Building the pipeline where humans set direction and AI handles the rest.
Splunk/Cribl consultant by day. Automating myself out of a job by night.
The goal: file a GitHub Issue, grab coffee, come back to a PR that's been implemented, tested, and reviewed by multiple AI models — just waiting for a thumbs up. Not fully there yet, but close enough to be dangerous.
Humans decide what to build. AI agents handle the how. Automation runs the boring parts. A human gives the final sign-off. Claude, Gemini, Copilot, and local MLX models each do what they're best at — the right model for the right job instead of throwing everything at one.
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#4FB3A9','primaryTextColor':'#0B1D2A','primaryBorderColor':'#2F7E78','lineColor':'#E06B4A','secondaryColor':'#102937','tertiaryColor':'#0B1D2A','clusterBkg':'transparent','clusterBorder':'#4FB3A9','fontFamily':'Geist','fontSize':'16px'}}}%%
flowchart LR
subgraph Human["Human"]
direction TB
H1(["Roadmap"])
H2(["GitHub Issues"])
H3(["PR Review"])
end
subgraph AI["AI Agents"]
direction TB
A1(["Claude / Gemini / Copilot"])
A2(["Code"])
A3(["AI Code Review"])
end
subgraph Auto["Automation"]
direction TB
T1(["CI / Testing"])
T2(["Lint & Validate"])
T3(["Ship It"])
end
H1 --> H2 --> A1 --> A2 --> T1 --> T2 --> A3 --> H3 --> T3
classDef human fill:#4FB3A9,stroke:#2F7E78,stroke-width:2px,color:#0B1D2A
classDef ai fill:#E06B4A,stroke:#C25638,stroke-width:2px,color:#0B1D2A
classDef auto fill:#2F7E78,stroke:#4FB3A9,stroke-width:2px,color:#F4EFE6
class H1,H2,H3 human
class A1,A2,A3 ai
class T1,T2,T3 auto
linkStyle default stroke:#E06B4A,stroke-width:3px
On the Clock: Splunk and Cribl consultant specializing in security operations. I architect SIEM platforms, build detection pipelines, and optimize data flows. My specialty? Cutting ingest volume by 30-50% while actually improving security posture.
Outside the Terminal: When I'm not wiring up AI agents or debugging data pipelines, I'm probably over-engineering my home lab or convincing my fish that uptime matters.
Home Lab: Proxmox cluster, UniFi networking, Home Assistant, Splunk, Cribl — all managed with Terraform, Ansible, and Nix. The goal is fault-tolerant infrastructure I can rebuild from a single nix build.
Aquariums: 75-gallon saltwater reef (clownfish, corals, pistol shrimp) + freshwater tanks with custom lighting and wave-maker automations. The fish have better SLOs than most production systems.
Adventures: Scuba diving (San Pedro, Belize is my happy place), snowboarding in Michigan and Colorado, hiking, running.
AI Development Pipeline — Multi-model routing across Claude, Gemini, Copilot, and local MLX.
AI Observability — OTEL telemetry from every AI coding tool to Splunk via Cribl. If an AI touched code, there's a trace.
Nix Reproducible Everything — Four flakes (nix-darwin, nix-ai, nix-home, nix-devenv). nix build and walk away.
Home Lab IaC — Proxmox + Terraform + Ansible + Nix. Fault-tolerant infrastructure from one command.
Local LLM Inference — MLX-native models on Apple Silicon. Why pay for cloud tokens with 128GB of unified memory?
RAG & Context Engineering — Qdrant feeding context into AI workflows. AI that actually knows your codebase.
→ Full architecture across ~40 public repos: docs.jacobpevans.com
