From AI Ambition
To
Production Reality

Delivering practical AI engineering for businesses that need it to actually work — designed, built, and operated end-to-end.

$270M+
adjustments processed
2.9M
claim lines triaged
48
practices served
100%
appeal coverage
Start a conversation See the work ↓
Denials automation engine — nightly production run
$ engine.run --nightly --practices 48
✓ 2.9M lines classified
✓ 135,970 letters drafted
✓ invoices posted to QBO

What we build for clients

Every engagement ships as a working system in production — not a slide deck. Four core capabilities, each proven with paying clients.

01 / PLATFORMS

AI & LLM Platform Engineering

Production agent platforms: runtimes, MCP services on Kubernetes, evaluation pipelines (MLflow/LangSmith), observability, and Terraform-managed infrastructure.

02 / AUTOMATION

Billing & RCM Automation

Denials engines, appeal-letter generation, month-end pipelines, EHR/PM integrations (ModMed, AdvancedMD), and QuickBooks Online invoicing — deterministic Python pipelines replacing manual cycles.

03 / DATA

Data Pipelines & Integration

API extraction, normalization, reconciliation at penny-exact accuracy, and reporting workbooks — connecting vendor portals, clearinghouses, and accounting systems.

04 / APPLIED AI

Custom AI Agents & Fine-Tuning

Autonomous agent harnesses with permission gating, RAG systems, LoRA/QLoRA fine-tuning, evaluation harnesses that prove quality before deployment — and PHI-redaction gateways for regulated data.

2.9M
claim lines triaged
$270M
adjustments processed
48
dermatology practices
136K+
appeal letters auto-drafted
100%
appeal coverage, same-day

Business products, shipped and running

Typical client engagements: full products delivered to production with real users. These are the systems businesses hire us to build.

Month-end bucket to invoice engine dashboard
58 CLIENTS AUTOMATED · 392 CLIENT-MONTHS · $0.00 VARIANCE
BILLING OPERATIONS

Month-End Bucket → Invoice Engine

Nightly extraction from the practice-management exports feeds a bucket-classification engine (14 revenue buckets), applies each client's contracted rates, assembles the month-end review workbook, and posts draft invoices to QuickBooks Online with the invoice dated to period close and payment due on the 10th. The whole run reconciles penny-exact against the source invoices.

58 clients automated 392 client-months 14 buckets $0.00 variance
Python · ModMed & Clinix exports · bucket classification · QuickBooks Online
Denials automation engine dashboard
NIGHTLY AUTOMATED RUN · 48 PRACTICES · JAN–JUL 2026
MEDICAL BILLING & RCM

Denials-Automation Engine

End-to-end revenue-cycle automation for a medical billing company: nightly claim extraction from ModMed and AdvancedMD, adjustment classification into contractual / patient-share / actionable-denial buckets, same-day appeal and deficiency letter drafting, month-end bucket reporting, and QuickBooks Online invoice posting.

2.9M lines triaged $270M adjustments 136K letters 100% appeal coverage 6-fig impact in 60 days
Python · ModMed & AdvancedMD exports · CPT/CARC denial classification · automated appeal + deficiency letters
Dilbert-Bot assistant in the team chat
ASKED IN CHAT · ANSWERED WITH THE REPORT IN MINUTES
AI ASSISTANT IN PRODUCTION

Dilbert-Bot — Billing Assistant in the Team Channel

A RingCentral assistant the billing team uses daily. It pulls production, A/R and denial reporting on request, answers questions about the numbers in plain language, and returns analyses that previously took several people the better part of a week — delivered in minutes. Behind it runs the scheduled extraction/reconciliation fleet, with patient data protected by the PHI gateway.

Used daily by the billing team Multi-day reports in minutes PHI-protected
Hermes agent framework · RingCentral adapter · Python · scheduled automation
Client portal sign-in for billing practices
PER-PRACTICE ACCOUNTS · DAILY REFRESH · REPORTS + DOCUMENT REQUESTS
CLIENT-FACING PORTAL

Client Portal for Billing Practices

A self-service portal where each practice signs in to its own dashboard — charges, payments and collections performance, refreshed daily — alongside document requests and downloadable reports. It replaces the status-check email chain with data clients can pull themselves.

Per-practice access Daily data refresh Reports & document requests
Python · FastAPI · role-scoped access · daily pipeline
Pet-sitting booking calendar on mobile — client view
PRODUCTION APP · 30+ ACTIVE CLIENTS · INSTALLABLE PWA (IOS/ANDROID)
CONSUMER PLATFORM

Booking Platform for a Pet-Sitting Business

A live scheduling and client-management platform: customer accounts, service catalog, calendar booking with date-range selection, visit management, payments and rate configuration, plus an owner console. Delivered as an installable web app so it runs like a native mobile app with no app-store approval cycle.

30+ live clients Installable PWA Owner + client views
Python · FastAPI · SQLite/Litestream · Railway
The Pet Whisper client portal — live production app
LIVE CLIENT PORTAL · INVITE-ONLY ACCOUNTS
Round-robin standings
Score entry and rounds
LIVE STANDINGS · ROUNDS & SCORE ENTRY · SHAREABLE PLAYER LINKS
SPORTS TECH · IN PITCH WITH PICKLR

Pickleball Round-Robin & Rating System

Round-robin tournament app that assigns courts and partners round by round, tracks live standings with point differential, and takes score entry with real rules validation. Paired with a DUPR-style rating engine using a chess-ELO equivalent, and an onboarding flow that mirrors a player's verified DUPR rating.

Live standings ELO rating engine Shareable player links
Python · Django · PWA · Third-party rating API integration
PHI redaction gateway — executive summary dashboard
EVERY OUTBOUND LLM CALL PASSES THROUGH THE GATEWAY · 0 KNOWN LEAKS
HEALTHCARE AI · COMPLIANCE

PHI-Redaction Gateway for Cloud AI

An OpenAI-compatible proxy that sits in front of every outbound LLM call, so patient data never reaches a third-party model. It detects PHI locally (rules plus NLP models), swaps each value for a deterministic reversible token, re-scans to catch misses, adds an independent second-opinion model pass, then forwards tokens only — restoring real values in the response. Token mappings are encrypted at rest and never leave the machine, and every leak signal is audited.

46K+ calls/day routed 552K values swapped 0 known leaks <2% added latency
Python · FastAPI · Presidio/spaCy · GLiNER · AES-encrypted token store

What clients say

Direct feedback from the businesses running systems built here.

"I brought Dylan in to automate high-labor internal operations at my billing company. He spent time on-site observing our workflows and talking with my staff about what kept them away from revenue-generating work — then built sustainable systems around what he learned. The results: our team saves roughly 200 labor hours annually, and within the first 60 days the financial impact had already reached six figures. Just as important, Dylan built these systems with our long-term mission in mind — we've been able to extend the foundations he laid rather than rebuild them. I'd recommend Dylan to any company looking for similar results."
— Rob Manjura · CEO, Inga Ellzey Billing Companies

Special projects & research systems

The weirder stuff — custom software, drivers, game-playing AI, and community platforms. Where new capabilities get proven before they become client work.

VENUE PHOTO PENDING
Arduino-free custom CV build · live at a commercial venue
CUSTOM SOFTWARE + DRIVERS

Interactive Projection Wall

Camera-tracked interactive wall running live at a commercial venue: real-time computer-vision ball tracking, OS-level input drivers that translate physical ball hits into arcade-game input, calibration tooling, and kiosk deployment.

Riftbound replay viewer showing a recorded match
GAME AI

Game-Playing AI + Replay Viewer

Trained game-playing AI for a third-party trading-card game: live client data capture, training-data pipelines, on-device LoRA fine-tuning, and a control harness that lets the model drive the game — plus a replay viewer that rebuilds any recorded match checkpoint-by-checkpoint with a full action log.

$ rift.game sim --deck blue --opponent red
✓ 291 checkpoints captured
✓ match logged to replay store
$ rating.update --player @member
✓ ladder standings posted to #riftbound
COMMUNITY PLATFORM

Community Game Bot & Ecosystem

A fully functional Discord bot running a local gaming community: match simulation, competitive rating, leaderboards and challenge flows — plus tooling used by developers working on the game's competitive scene.

agent run --pipeline billing-month-end
gate write reports/ : allowed
gate delete client data : BLOCKED
gate payer API calls : allowlisted
audit 1,284 actions logged
AGENT SAFETY

Autonomous Agent Harness

An agent harness with granular permission gating — scoped filesystem writes, destructive-action blocks, and a full audit trail — making unattended LLM coding agents safe to run on production-adjacent machines.

Built by a practicing engineer

Rund Consulting Inc. is the AI & automation consultancy of Dylan Rund — a working engineer, not an agency. His career was built inside three of the largest professional-services firms in the world — Accenture, Deloitte and PwC — delivering AI platforms and automation for regulated, data-heavy operations. The systems he builds for clients are the same class of system he ships professionally: production AI, automation and data pipelines, backed by 10+ years across platform engineering, cloud infrastructure and enterprise delivery.

16+ AWS CERTIFICATIONS AZURE FUNDAMENTALS KCNA · KUBERNETES OCI MULTI-CLOUD ARCHITECT GCP CLOUD ENGINEER COMPTIA A+ / NET+ / SEC+ / CASP+
Dylan Rund
FOUNDING ENGINEER · RUND CONSULTING INC.
Engineering experience10+ years
Cloud certifications20+ across 5 platforms
Based inCasselberry, FL
REMOTE & ON-SITE · dylan.rund@rundconsulting.com

Let us solve the complicated, tedious problems

Most businesses aren't short on AI ideas — they're short on time. Somewhere in your operation there's a process that eats hours every week: pulling data out of portals, reconciling spreadsheets, chasing rejections, re-keying the same information twice. That's exactly the work modern AI and automation is good at, and it's the work we take off your plate.

DATA CHASING

Information trapped in portals

Claims, reports, and statements that only exist behind logins get extracted, normalized, and delivered on a schedule — no one logging in at 6am to download files.

REPETITIVE RECONCILIATION

Month-end that takes days

Reconciliation, summarization, and invoice preparation become one deterministic run that finishes in minutes and is penny-exact by construction.

VOLUME WORK

Backlogs that grow faster than staff

Denials, appeals, review queues, and ticket triage get classified, prioritized, and drafted automatically — your team reviews and approves instead of starting from blank.

JUDGEMENT AT SCALE

Decisions nobody has time to make consistently

LLM systems with evaluation harnesses that measure quality before deployment, so automated decisions stay explainable, auditable, and improvable.

Tell us what's eating your team's time
dylan.rund@rundconsulting.com
Responses within one business day · Casselberry, FL — remote & on-site