Dave Fels, PMP
Signal over noise
A Portfolio of AI-Driven Project Management Strategy in Three Case Studies
About
Dave Fels, PMP
I believe AI shouldn't just make project management faster; it should make it smarter. Welcome to my portfolio, where I demo how I bridge that gap to deliver real results.I don’t treat AI as an autopilot; I treat it as a precision instrument. I’m here to demo how I cut through administrative noise to isolate the data that actually moves the needle, using a rigorous framework for every project.Take a look at how I turn AI from a simple tool into a competitive advantage.
Contact
Dave Fels, PMP
I’m always looking to connect with fellow leaders who are navigating the intersection of project management and AI. Whether you’re looking to optimize your own operational workflows or just want to swap notes on how we can cut through the noise, I’d love to hear from you. Let’s start a conversation.
PMP-Certified Project & Implementation Leader | AI-Certified Professional | UX-Certified | SaaS & GovTech Delivery | Open to New Opportunities
[email protected]
AI-Assisted "Pre-Mortem" Risk Analysis
An Exercise in Prompt Engineering Toward Strategy
The Context
Managing the lifecycle of 400+ websites annually generates a vast ocean of data, often masking critical insights. By leveraging AI to filter this noise, I don't just achieve operational velocity—I gain the clarity to inject high-level strategy into every launch, turning raw data into a decisive competitive advantage.
The Challenge (The "Why")
Traditional risk registers frequently fail to account for late-stage project volatility. To stabilize an 8-to-24-week project lifecycle, I can use AI to evolve our risk management approach to better anticipate and mitigate the specific triggers that cause delays.
The AI-Augmented Workflow (The "How")
Prompt Evolution Toward Strategy
Initial Prompt + attaching a spreadsheet of project data
This Basic Prompt is direct, but lacks context, methodology, and formatting constraints. The AI does not know its role, the specific analytical lens to use, or how to structure the output. It will likely produce generic, surface-level observations.
Version 2 Prompt
This one adds analytical depth and specific data-processing instructions. By defining a Role and a Methodology (Pattern Recognition), I force the AI to move beyond general knowledge and perform actual data correlation.
Version 3 Prompt
This eliminates the fluff and ensures actionable, high-quality output. The addition of Constraints acts as a filter, removing the AI's tendency to fill gaps with generic advice, ensuring the response remains grounded in your specific data.
My Value Add (The "So What?")
I leveraged the AI report to identify the ten high-impact failure modes, which I then synthesized into the top three risks specifically affecting late-stage project delivery. I validated these findings against my own expertise, refining the timeline mapping for greater accuracy.
| Failure Mode | Avg. Impact | Mitigation Strategy |
|---|---|---|
| Dependency Delay | 9.0 Days | Mandatory validation of all third-party deliverables must occur 4 weeks prior to launch |
| Resource Constraint | 6.0 Days | Project Lead must secure written capacity commitments from functional managers at the project kickoff |
| Scope Creep | 5.0 Days | A "Scope Freeze" is implemented 14 days before final delivery |
The Impact/Outcome: 20 Day Reduction
Prioritizing these three high-impact late-stage risks allowed us to streamline our process, resulting in a 20-day reduction in our average delivery timeline.
The following section is designed to be copy-pasted directly into the Project Charter. It focuses on high-impact proactive management rather than passive status reporting.
PROJECT CHARTER AMENDMENT
Section: Risk & Stabilization Framework
Objective: To ensure predictable launch dates and minimize operational noise, the following risk mitigation strategies are mandatory for this project. These protocols are derived from historical project performance data and must be audited by the Project Lead at the stated intervals.1. Proactive Risk Mitigation Protocols
| Risk Area | Trigger | Mitigation Strategy |
|---|---|---|
| Dependency Delays | External integration latency / Missed milestone | Mandatory Handshake: External dependencies must be validated via a formal "Readiness Confirmation" document 4 weeks prior to launch. |
| Resource Contention | Functional lead reassigning staff / Capacity gaps | Binding Commitments: Formal capacity commitments must be secured at project kickoff. Any mid-cycle changes require an executive impact assessment. |
| Scope Creep | Unplanned feature requests in UAT | 14-Day Scope Freeze: All requirements are frozen 14 days before delivery; new items are automatically diverted to a "Phase 2" backlog. |
2. Governance & Escalation
Audit Interval: The Project Lead will review these three indicators during the bi-weekly status meeting once the project enters the final 6-week window.Escalation Trigger: If any of the above "Leading Indicators" are detected, the project will immediately move to "Yellow" status, triggering a formal mitigation review with the project team and relevant stakeholders within 48 hours.
The Wrap Up
Ultimately, this exercise demonstrates how AI can transform a reactive risk register into a proactive stabilization strategy. While iterative prompt engineering allowed me to cut through the noise of hundreds of past projects, it was the human-in-the-loop validation that translated those AI-generated patterns into actionable governance. By isolating and targeting the three most disruptive late-stage failure modes, the result wasn't just a smarter document—it was an enforceable framework that permanently improved operational velocity and shaved 20 days off the average delivery cycle.
Stakeholder Communication Tailoring
Communication is where projects succeed or fail
The Context
At a scale of 400+ websites a year, conventional project management isn't enough. Each client brings a unique stack of third-party integrations and preferences that require more than a 'one-size-fits-all' approach. To bridge this gap, I engineered a web app that transforms complex project data into a roadmap for authentic connection, proving that technical efficiency and a personal touch are not mutually exclusive.
Web App Demo
Customize the client intake form below to reflect the project scope, then click the "Generate Custom Kick-Off Email" button
The Wrap Up
In the end, this web app didn't just automate communication; it elevated it. By processing complex integration data and client preferences into tailored engagement strategies, I eliminate the generic 'project kick-off email.' The result is a scalable framework that maintains a high-touch client experience across all projects, proving that with the right technical leverage, operational volume doesn't have to compromise bespoke service.
Automated Meeting Synthesis & Action Tracking
Turning "noise" into "signal"
The Context: From Meeting "Noise" to Strategic "Signal"
The Problem: Project meetings often result in long, unstructured transcripts that obscure key decisions and accountability.The Goal: I'll Demo how I transform raw conversation into an execution-ready artifact.
The Workflow: Raw Data Processing
The Scenario:In this sample Sprint Planning session, I encountered a common project management hurdle: high cognitive load and conversational drift. The meeting environment was fragmented by 'Zoom fatigue' from back-to-back calls, and the transcript was cluttered with non-linear dialogue—mixing critical project status updates with personal anecdotes. This chaotic flow made it difficult to extract clear decision points and accountability.
Meeting Transcript Snippet: Before
The AI Task: Structuring the Chaos with an AI Agent
The Logic: To scale consistent communication across my projects, I can develop and deploy a custom AI agent to process our meeting transcripts. By anchoring the agent's prompt with rich contextual guardrails and strict formatting instructions, we achieve a highly structured, reliable output every time. Sharing this tool team-wide eliminates administrative overhead, standardized our project documentation, and ensured all stakeholders receive uniform, actionable updates.
AI Agent Instructions
My Value Add: The Human in the Loop
The "Missed" Moment: This is the most important part the meeting wrap up. We need to scan for missed or incorrect informationExample: The AI extracted the clear action items but missed a subtle, conditional commitment made by the Sarah regarding server access in week 4.The Correction: Make the "Human Edit." I reviewed the transcript against the AI output, identified the missing stakeholder commitment, and manually inserted it as a high-priority risk item in the final tracker."The Lesson: AI is a powerful summarizer, but as the Project Manager, I am the final auditor. My expertise ensures that subtle verbal commitments—which often carry the highest risk—are never lost.
Meeting Transcript Snippet: After
The Result
This cleaned, AI-supported tracker can be distributed to all stakeholders within 15 minutes of the meeting's conclusion, reducing 'wait time' for project updates by 90% and ensuring total alignment on ownership.