Selected engagements.
Anonymized case studies. Client names withheld; outcomes are real.
Federal evaluators can request fuller references via [email protected].
Regional contractor. 19 dispatch users, 15-seat BI rollout.
Problem
Sales pipeline and project operations data lived in disconnected systems. No closed loop between Sales-stage activity and on-the-ground project metrics.
What we built
- Dynamics 365 Sales rebuild aligned to the actual sales process
- Power BI semantic model and dashboards across Sales + Operations
- Foundation ETL pipeline integrating CRM, project mgmt, and accounting
Outcome
Closed sales/ops data loop. The CEO, the President of Concrete and the COO are in the dashboards every business day, on a platform licensed for fifteen, alongside nineteen dispatch users on the scheduling app. Ops leadership sees pipeline-to-project-margin in one view.
Regional firm, partner-led.
Problem
Case-relevant correspondence buried in 17,000+ emails across attorneys. Finding the right thread meant searching mailboxes by hand.
What we built
- Secure M365 email pipeline with controlled retention
- RAG search layer over the email corpus with citations back to source threads
- Audit-ready access logging
Outcome
Case-relevant correspondence resolves by search rather than by manual review. Results return with thread citations attorneys can open and verify.
Startup serving regulated industries, US-based.
Problem
FinCEN BOI / RER filing required a defensible end-to-end workflow per tenant, with full audit trail and submission status tracking.
What we built
- Multi-tenant filing platform with role-based access
- Submission engine integrating with FinCEN endpoints
- Full audit trail per filing event
Outcome
End-to-end submission workflow live. Tenants file and track without leaving the platform. Every filing event carries a full audit trail, retained for review.
Owner-operated CRE practice. Built and run by HDS.
Problem
A relationship-led practice cannot run on a generic CRM. Deal tracking, market intelligence, and follow-up all wanted different tools, and every one of them expected the broker to sit at a dashboard rather than work the market.
What we built
- CRE deal platform as the system of record, on managed Postgres
- A nine-agent fleet running market intelligence and daily briefings on a schedule, not on request
- Telegram as the entire operator interface, so the practice runs from a phone
- An automated market-briefing pipeline feeding a published newsletter
Outcome
The practice runs without a dashboard. Market briefings arrive before the day starts, pipeline and follow-up live in one system of record, and the agent fleet does the research a junior analyst would otherwise be hired for. This is the reference build for the pattern we sell: agents doing standing work, and a messaging app instead of a UI.
Owner-operated, five locations, multi-year tenant base.
Problem
Rent, tenants, and late fees were tracked in a spreadsheet with twelve monthly tabs per year. Reconciling a single tenant history meant opening a dozen tabs, and nothing enforced the late-fee rules consistently.
What we built
- Tenant, unit, and payment model covering all five locations
- Rent roll and late-fee handling applied by rule instead of by hand
- Multi-year ledger with per-tenant payment history
Outcome
The spreadsheet is retired. Rent status across all five locations resolves in one view, RV parking included, and late fees apply consistently without the owner recalculating them.
Owner-operated clinical practice, two service lines.
Problem
The practice needed a clearer web presence and a practical way to manage enquiries and inspect search performance. Each service line needed its own scope and launch plan.
What we built
- Custom neurofeedback website with structured data and local search groundwork
- Dashboard with website and search reporting, lead-management tools, and manually reported revenue
- Separate chiropractic website build, currently in prelaunch review
Outcome
The neurofeedback website and dashboard are deployed. The practice has tools to inspect search performance and manage enquiries; the separate chiropractic launch is still being prepared.
Operations teams dependent on vendor platforms with difficult APIs.
Problem
Core business data was locked behind billing, telecom, and PSA platforms whose APIs paginate inconsistently, encode fields as opaque integer picklists, and return success codes on authentication failures.
What we built
- Typed async clients handling pagination, rate limits, and picklist resolution
- Model Context Protocol servers exposing those systems to AI tooling directly
- Middleware layer normalizing vendor payloads into a stable internal shape
Outcome
Operations data is queryable in one interface instead of three portals, and the same clients back both automation and assistant workflows.
The infrastructure behind the delivery.
Built and run by HDS for HDS. Listed here because it is what makes the engagement velocity above possible, not as past performance.
What we built
- Multi-agent orchestration platform with persistent memory
- Code review + verification gates as first-class agents
- Audit-grade logging of every agent action
One principal runs several workstreams in parallel, because review and verification are automated rather than queued behind a person. The agents that built this site are the same ones used in client work.
Your problem is probably a variation on one of these.
Start with a free scoping conversation with Mike Hyams, the person who builds and supports the work.