Information-only
SE OS
A solution-engineering operating pattern for governed discovery, proofs, reusable accelerators, evidence, and handoffs.
Solutions · agents · useful things
I build AI people use.
I design practical AI systems, agent teams, and business applications that move from idea to working proof fast - without giving up the human judgment that matters.
- 29 public repositories
- Minneapolis, Minnesota
- Human control by design
Independent projects. Clear boundaries. Practical possibilities.
- BUILT AROUND THE WORK
- AI & AGENTS
- DYNAMICS 365
- POWER PLATFORM
- DEVELOPER EXPERIENCE
Featured current work
Eleven projects, deliberately curated.
A focused mix of public releases and information-only private builds. Every card opens its journal entry; the full journal keeps the broader body of work.
Information-only
MCAPS OS + App Store
A modular private operating surface and curated pattern catalog with deliberate review, installation, activation, and removal.
Information-only
Portable Neuron
A provider-neutral portability concept for reusable agent knowledge and behavior, centered on human-reviewed NEURON.md and thin host adapters.
Information-only
V-Team Mesh + Hivemind
Scoped specialist roles, independent review, accountable coordination, human approval, and trusted knowledge carried forward.
Information-only
Sales Agent Extensibility Pattern
Seller and CRM context, approved tools, proposed next actions, human-gated writes, and durable receipts.
Information-only
Service Agent Extensibility Pattern
Case context, knowledge and tool assistance, evidence-backed proposals, approvals, and customer-owned execution.
Information-only
Program IQ
A program-execution view connecting milestones, ownership, evidence, risks, decisions, and next actions.
Information-only
Field Service Tech Home
A supportive mobile concept for work execution, parts, quality, productivity, and optional AI guidance.
Public release
Customer 360 for Entities
An adaptive Dynamics 365 and Dataverse web resource that brings related operational context into the form.
Public release
Freight Triage Control Tower
A sample-data browser prototype for owned freight email triage, queue visibility, aging, and resolution.
Public release
Agent Team Starter Kit
Configurable scaffolding for specialist agent roles, GitHub Issues and Actions, outcome framing, and human intervention.
No featured work matches that filter. Try another category or clear the search.
Builder profile
From rough idea to working system.
I work across the whole path: framing the outcome, shaping the architecture, building the interface, wiring the platform, and making the handoff usable.
Agents that do work, not just chat.
Orchestration, tools, grounding, MCP, evaluation, feedback loops, and explicit human gates.
signal
reason + act
review
outcome
AI inside the flow of work.
Dynamics 365, Dataverse, Power Apps, Power Automate, and Copilot Studio experiences grounded in real operational jobs.
Make the idea tangible.
Responsive prototypes, voice-first interfaces, control towers, web resources, and demo systems people can test instead of imagine.
Build the control plane around the model.
Clear ownership, evidence, observability, security boundaries, portable skills, and reviewable actions turn one-off AI moments into reliable ways of working.
Technologist. Builder. Systems thinker.
I am Bill Whalen, a Minneapolis-based technologist at Microsoft. I work at the seam between people, AI, and business systems: finding a stubborn workflow, framing the real outcome, and making the idea tangible enough to test.
The artifact might be a multi-agent team, a Dynamics 365 accelerator, a voice-first interface, an operating system for field work, or a game. The common thread is practical: working software, clear boundaries, and an adoption path.
Working principles
-
01
Start with the outcome.
Define what changes for the person doing the work before choosing the model or platform.
-
02
Build the proof.
A working prototype creates better decisions than another round of abstract architecture.
-
03
Keep humans at the consequential gates.
Automation should increase leverage without hiding uncertainty, ownership, or irreversible action.
-
04
Package what survives.
Turn validated patterns into accelerators, skills, and handoffs other builders can use responsibly.
Technologies I reach for
A working toolkit I choose from based on the workflow, platform boundary, and proof that needs to be built.
AI & agents
- Microsoft Copilot
- Copilot Studio
- Anthropic Claude
- Azure AI
- OpenAI
- GitHub Copilot
- MCP
CRM & business apps
- Dynamics 365
- Salesforce
- Pega
- Power Platform
- Dataverse
- Power Apps
- Power Automate
Cloud & integration
- Microsoft Azure
- Azure Functions
- REST APIs
- Custom connectors
- Workflow automation
Product engineering
- React
- TypeScript
- JavaScript
- Python
- PowerShell
- GitHub Actions
- Home Assistant
Foundation note. Some of my agent work builds on RAPP and RAPP/1, public projects published by Kody Wildfeuer. These foundations inform my approach to persistent agent identity, traceable memory, and reusable work.
Full solution journal
The homepage is the edit. The journal is the record.
The curated homepage highlights eleven current priorities. The journal preserves ten public releases and eleven clearly separated information-only showcases.
Public releases
Repository-grounded solution pages and companion articles, ordered by exact last public push facts.
public source → solution / article
Browse public releases
Private active work
Customer-neutral descriptions with designed value, explicit human controls, no source links, and a conspicuous public boundary.
owner-reviewed → information only
Browse info-only work
RSS + Atom
Only public-release companion articles appear in feeds. Information-only showcases are deliberately excluded.
public release → rss / atom
Choose a feed
Live now: 20 journal entries and a mode-aware manifest. Not live: email subscriptions and MCP.