Enterprise SaaS · implementation & AI workflow engineering

Complex
systems.
Clear outcomes.

Des Moines, Iowa
Available for an AI-forward role

I lead enterprise financial reporting implementations and build the AI workflow layer around them — MCP integrations, multi-agent orchestration, and verification tooling that makes automated changes traceable before sign-off.

Explore selected work Download résumé
Dave Bettner smiling in a gray suit
Dave BettnerProfessional portfolio · 2026
12+ yearsEnterprise delivery6–12Concurrent implementations · 2022–2435+ sheetsLive ACFR workbook scope29 testsIndependent deployment lab
01 / What I build

Selected technical work.

01 · Multi-agent deliveryBuzz, Hermes & agent-stackA governed operating layer for coordinating Claude, Codex, Cursor, and specialist agents on real client work—with proof before sign-off.Orchestration · memory · proof gates02 · Workiva MCP & API layerWorkiva MCP ServerAuthenticated API tools so AI workflows read and update Workiva spreadsheets and documents—without manual browser work.MCP · REST · exports · Wdata03 · Quality & deliveryWingman & evidence-backed reportingDetect spreadsheet defects, propose fixes for approval, and reconcile sources before anything is called done.Chrome extension · validators · signoff
02 / Delivery leadership

Proposals, scope, and agent-assisted project management.

Implementation proposals & discovery

ERP/GL → reporting scoping: what integrates cleanly, what needs configuration, what stays human. Pre-sale technical discovery, tailored demos, and integration checklists at Workiva. At Citrin: Kaiser Permanente certification workflow with bidirectional API to an internal archival system.

Workiva SA
Citrin

Bounded agent execution

Live engagements run on task packets — partition, allowed paths, stop condition, prestate/poststate. Coordinator routes work across specialist agents; independent readback on live Workiva before customer-impacting changes ship.

Buzz · Hermes
agent lanes

Wave-based reporting delivery

Complex ACFR remediations decomposed by defect class: sweep → scoped write → tie-out verify → human sign-off. 35+ sheet workbook scope; handoff runbooks for team adoption.

Public sector
ACFR
03 / Career story

12+ years of staying with the work from discovery to adoption.

Senior Manager · LSL, LLP

Governmental ACFR delivery; agent-assisted workbook sweeps with journaled changesets and tie-outs.

Des Moines, IA
(Remote US)

Manager - Digital Services · Citrin Cooperman

Five-person Workiva team; finance and regulatory reporting implementations.

Chicago, IL
(Remote US)

Solutions Architect · Workiva

6–12 concurrent GRC and financial reporting implementations; ERP/GL integration scoping.

Denver, CO

Professional Services Consultant · Ambra Health

Healthcare imaging startup; continued through acquisition by Intelerad Medical Systems. HIPAA implementations and API integrations.

Denver, CO

Professional Services Manager · Workiva

Owned enterprise implementations from kickoff through production; trained client teams on GAAP/IFRS/XBRL reporting.


Financial Reporting Manager · Workiva

SEC reporting for public companies — statements, disclosures, and quarterly review cycles.


Data Research Analyst Intern · Kingland Systems

Financial reference data research and quality analysis.

Ames, IA

AI should make the work more accountable, not less.

I use AI where it can reduce coordination drag, surface exceptions, and accelerate the next safe action—scoped credentials, readback checks, and explicit approval gates so automated work stays traceable and reversible.

01

Start with the real workflow

Understand the source, permissions, decisions, and failure modes before automating anything.

02

Keep consequential decisions human

Let automation reduce coordination drag while accountable people retain judgment and approval.

03

Evidence before confidence

Use tests, native readback, and observable poststate instead of activity or plausible output.

Résumé.

12+ years in customer-facing implementation across enterprise SaaS, financial reporting, GRC, healthcare, and public-sector workflows.

Download PDF Get in touch
Selected case study

Buzz, Hermes & agent-stack

A governed operating layer for coordinating Claude, Codex, Cursor, and specialist agents on real client work—with proof before sign-off.

View full case study

Constraint
Multiple AI runtimes can generate activity faster than a team can prove state, ownership, or what actually shipped.
Built
Buzz (Nostr team messaging) for channel coordination; Hermes as coordinator across bounded worker lanes; agent-stack as git-backed shared memory with reversibility tiers, completion contracts, and route-specific proof gates. Capability routing sends each task to the cheapest lane that can verify its own output.
Role
Designed and operates the stack on live ACFR and enterprise reporting engagements—scoped write packets, adopt-gates before production workbook changes, and durable session logs.
Human boundary
Humans retain approval for publication, destructive actions, credentials, spend, and consequential judgment. Automation proposes and routes; people decide.
Evidence
Worktree-isolated edits, native Workiva readbacks, and explicit completion contracts before sign-off.
Scope
Practical implementation infrastructure for regulated delivery—not foundation-model or ML-research work.
Selected case study

Workiva MCP Server

Authenticated API tools so AI workflows read and update Workiva spreadsheets and documents—without manual browser work.

View full case study

Constraint
Browser-only automation breaks on canvas grids, iframe boundaries, and session expiry; regulated reporting needs structured reads, writes, and readback.
Built
MCP server exposing 20+ Workiva REST tools—values, formulas, formats, destination links, Wdata queries, file exports, and async job polling—with engagement-scoped credentials and production error handling. Paired with a containerized deployment lab (29 automated tests, nine acceptance areas) that proves clean-clone deploy, auth, and failure recovery.
Role
Built and maintain the integration; designed the deployment shape, service harness, and operating runbooks.
Human boundary
API-first for structured data; browser capture only for UI-only proof. The lab proves reproducibility—it is not represented as a live client production tenant.
Evidence
29 automated tests across nine acceptance areas; live readback after scoped writes; binary-safe export verification.
Scope
Architecture, tests, and operating discipline are public; client data and credentials are not.
Selected case study

Wingman & evidence-backed reporting

Detect spreadsheet defects, propose fixes for approval, and reconcile sources before anything is called done.

View full case study

Constraint
Complex reporting can look complete while mappings, formulas, links, or presentation remain wrong—and manual review does not scale.
Built
Wingman: Chrome extension + Python service that scans live Workiva sheets via API, flags defects (formula hygiene, broken refs, linked blanks), explains each issue, and applies narrow safe fixes only after confirm-before-write. Alongside: source-first reconciliation, controlled write batches, deterministic validators, and human signoff on customer-impacting changes—used across financial reporting and public-sector implementations.
Role
Designed and built Wingman; designed and operated the delivery workflow across enterprise SaaS implementations for 12+ years.
Human boundary
Automation detects, classifies, and routes exceptions; accountable owners resolve classified differences and approve consequential changes.
Evidence
Logged fix outcomes improving detection over time; formula/formatting gates; prestate/poststate diffs; native source verification.
Scope
Examples are sanitized. Client data and non-public implementation details are not exposed.