Agentic orchestration
Typed tool use, multi-step loops, retries and fallback, failure classification, and safety gates.
Proof: agent reliability harness, LLM reliability gateway, local-model MCP bridgeDonald B. Havery
Applied AI Engineer, Forward-Deployed Focus
Donald B. Havery
APPLIED AI ENGINEER · FORWARD-DEPLOYED FOCUS
AI systems
engineered
for production.
I take vague AI asks to production: agent orchestration, RAG, eval gates, and security controls, handed off clean. Applied AI systems engineering is the layer around the models that makes them shippable.
Works across
and more
and more
Shipped & live
THREE PUBLIC BUILDS.
The strongest evidence is public and measurable: a gateway with failover, an eval gate that exits non-zero on regression, and an agent harness that records retry, fallback, and recovery paths. Inspect the repos, reports, and tests.
PUBLIC · CI GREEN
LLM GATEWAY / PLATFORM RELIABILITY
LLM reliability gateway
- Provider routing
- Cross-provider failover
- Circuit breakers
- From-scratch HNSW search
118 TESTS
An OpenAI-compatible control layer for LLM traffic: provider priorities, circuit breakers, semantic cache, and from-scratch HNSW search. The proof is deliberately inspectable: public code, MIT license, recent green CI, and cloneable tests.
OPEN REPO → MIT · github.com/dbhavery/citadel
PUBLIC · CI GREEN
RELEASE-QUALITY EVALS / RAG
Evaluation release gate for LLM & RAG
- Prompt assertions
- Retrieval precision / recall
- Citation grounding
- Non-zero exit on regression
54 TESTS
A release gate for LLM/RAG behavior: prompt assertions, retrieval metrics, citation grounding, and baseline comparison. It runs offline and deterministic, then exits non-zero when a case regresses.
OPEN REPO → MIT · github.com/dbhavery/eval-gate
PUBLIC · CI GREEN
AGENT ORCHESTRATION / RELIABILITY
Agent orchestration reliability harness
- Typed tool schemas
- Retry & fallback
- Failure classification
- Unsafe-action gate
45 TESTS
A deterministic agent loop built around production failure modes: typed tools, structured traces, bounded retries, fallback, unsafe-action blocking, and explicit failure classes for timeout, malformed output, missing context, and unsafe requests.
OPEN REPO → MIT · github.com/dbhavery/agent-harnessApplied AI engineering, end to end.
The flagship trio is the fast proof. The broader portfolio maps that proof to the capabilities senior AI teams hire for: architecture, orchestration, release quality, security posture, product surfaces, and infrastructure.
LLM platform architecture
API boundaries, model gateways, semantic cache, retrieval, ingestion, tracing, and cost control.
Proof: self-hosted LLM reliability gatewayEvaluation and reliability
Prompt assertions, RAG metrics, citation grounding, regression gates, and test reports.
Proof: LLM & RAG evaluation release gate, agent reliability harnessSecurity and governance
Control-to-evidence mapping, verdicts, audit logs, redaction, severity labels, and remediation.
Proof: policy-control evidence review, compliance gap-analysis appProduct, SaaS, and web design
Workflow design, dashboards, role-based portals, launch copy, and responsive UI.
Proof: fuel-delivery operations platform, live product sitesInfrastructure and bare metal
Docker, Linux, GPU workflows, local model bridges, IaaS choices, and systems that run without babysitting.
Proof: local-model MCP bridge, consumer-GPU fine-tuning pipeline, text-to-CAD loop
Python
TypeScript
React
FastAPI
PostgreSQL
Redis
Docker
Playwright
Next.js
Node.js
Vite
Vitest
OpenAI
Anthropic
Gemini
Google
AWS
MCP
LangGraph
Pydantic
ChromaDB
LlamaIndex
Ollama
Hugging Face
HOW I RUN A BUILD.
I am strongest where most AI prototypes fail: turning unclear scope into an architecture, product workflow, implementation plan, eval strategy, security posture, and clean ownership handoff.
ARCHITECTURE
Provider boundaries, data flow, observability, and failure modes.
ORCHESTRATION
Agents, tools, retrieval, memory, routing, and human handoffs.
QUALITY
Evals, regression tests, release checks, and measurable behavior.
SECURITY
Control evidence, audit trails, access boundaries, and review paths.
SIX MORE SHIPPED SYSTEMS.
Security and compliance review, operations tooling, live-data interfaces, local inference, and support UX, each with public code or a live surface to inspect.
PUBLIC · 23 TESTS
Self-correcting text-to-CAD loop
Plain-English part requests become OpenSCAD, render, and get inspected by a vision model that feeds failures back into repair. Local execution, no API keys, and a compact deterministic test suite.
OPEN REPO →
Public · MIT · 23 tests · github.com/dbhavery/textcad
PUBLIC · CI GREEN
Policy-control evidence review
Maps control statements to supplied evidence, returns per-control verdicts with matched excerpts, redacts secrets, and writes an append-only audit log for reviewer handoff.
OPEN REPO →
Public · 40 tests · redaction · reviewer decision aid
LIVE DEMO
Compliance gap-analysis app
Runs representative-data gap analysis against SOC 2, GDPR, and HIPAA requirement sets, then generates policy and audit-report drafts while leaving the compliance decision with a human.
TRY IT →
Live Hugging Face Space
LIVE DEMO
Role-based fuel delivery operations platform
Role-based dispatch, customer, driver, franchise, and HQ workflows for an on-site fuel delivery business, paired with a live public marketing site. Pick a role in the demo and walk the dashboards.
TRY THE DEMO →
StaFull · stafull.com is live · demo needs no account
PUBLIC · DESKTOP APP
Situational-awareness globe
Sixteen live feeds (planes, ships, satellites, weather, parcels, alerts, and events) rendered onto one operational globe for a dense desktop interface.
OPEN REPO →
Public repo · Cesium desktop app
LIVE DESIGN DEMO
Grounded support experience
A support-experience concept page: a self-playing sample transcript that cites its source doc and escalates to a human. Plainly labeled as design, not a deployed model.
OPEN →
Live page · design demo only
More systems across agents, voice, local inference, fine-tuning, and scheduled automation.
- Local-first desktop AI assistant architectureReference: Aether
- Voice assistant framework with multi-agent routingReference: Vox
- MCP bridge for local models, embeddings, vision, and memoryReference: McPlex
- Local QLoRA fine-tuning pipeline for consumer GPUsReference: FineForge
- AI pull-request review GitHub appReference: CodeRev
- AI video and research triage pipelineReference: Frontier Scout
- Scheduled AI news, system update, and social-posting automationReference: Morning Intel
- Local image generation and inpainting desktop toolReference: Image Generator
CREDENTIALS ON RECORD.
Seventeen AI certifications and thirty ACE college-credit courses. The Coursera and Credly entries verify online at the links below; the Anthropic Academy set covers Claude, Claude Code, MCP, Bedrock, and Vertex AI.
15× ANTHROPIC
Anthropic Academy certifications: Claude 101, Claude Code in Action, Claude Code Skills, Building with Claude, MCP and MCP Advanced, Claude with Bedrock, Claude on Vertex AI, Claude Cowork, AI Capabilities & Limitations, and the AI Fluency series. Mar–Apr 2026.
ABOUT THE PROGRAM →
GOOGLE
AI Fundamentals, issued by Google via Coursera, with identity-confirmed verification on record.
VERIFY ON COURSERA →
DEEPLEARNING.AI
Generative AI with Large Language Models, authorized by DeepLearning.AI and AWS, via Coursera. Mar 2026.
VERIFY ON COURSERA →
30× ACE CREDIT
Thirty ACE-recommended college-credit courses via Sophia Learning: Python, Java, web development, relational databases, networking, and statistics.
BADGES ON CREDLY →
B.S. Computer Science, AI specialization. Capella University, in progress.
AVAILABLE FOR SENIOR AI ROLES.
Roles where product judgment, hands-on implementation, quality gates, and release discipline matter. Portland, OR Metro Area. Remote or hybrid.