×
Molly Shove

Molly Shove

Senior AI Product Manager, Regulated Agentic Systems

Portland, Oregon, US
541-690-7158

Background


About

About

Product leader specializing in agentic AI systems and regulated environments. Track record shipping LLM-powered products, agent infrastructure, and developer platforms. Additionally, sole PM in high-stakes constrained environments where compliance is a design input, not a review step. Hands-on with prompt architecture, token optimization, and agentic pipeline design.

Work Experience

Work Experience

  • Senior AI Product Manager, Regulated Agentic Systems, Ascendion

    Mar, 2026 - Present

    Embedded as sole PM on an internal agentic product being piloted with a regulated banking client. The product auto-generates epics, features, and user stories end-to-end from a high-level initiative brief, targeting production-ready output including code and tests.

    • Translated 15 UK banking regulations including FCA Principles, BCOBS, PSR 2017, and the Data Protection Act; into structured story templates that encode compliance requirements as a first-class input to AI-generated artifacts, replacing human-dependent recall with systematic coverage across all future projects.

    • Designed and implemented a 9-point rubric-based evaluation system for scoring agentic output quality across PRDs, features, stories, and tasks enabling comparative measurement across prompt sets and establishing a repeatable standard for production readiness.

    • Reduced token costs and improved agent focus through context partitioning: splitting instructions across role-specific files so each agent receives only relevant context, replacing prompt verbosity with targeted retrieval.

    • Designed tiered model routing across the agentic pipeline, matching task complexity to model capability to reduce inference cost without sacrificing output quality.

    • Designed and implemented pre/post execution hooks within the agentic pipeline including linting, validation gates, and output checks; both independently and in collaboration with engineers on a custom framework.

    • Each initiative generates 40–50 stories; the system reduces PM delivery time by approximately 10x, enabling a single person to cover both PM and TPM scope.

  • Senior Product Manager, Moodys Northwest Consulting

    Apr, 2025 - Feb, 202610 months

    Embedded PM on a T-Mobile engagement, leading product strategy across web, iOS, and Android experiences serving millions of customers.

    • Shipped a redesigned military suspend flow that eliminated the requirement to call customer support or visit a store: fully digitizing a process previously unavailable in self-service for T-Mobile's military customer base.

    • Led product development for T-Mobile's troubleshooting experience across web, iOS, and Android.

    • Shipped an LLM-powered troubleshooting assistant using knowledge-base retrieval to guide users through support workflows; the business case projected $1.2M in savings over five years through reduced support calls and office visits.

  • Generative AI Product Manager, Microsoft

    Apr, 2020 - Sep, 20244 years 5 months

    Led product initiatives across generative AI systems, developer platforms, and APIs powering Microsoft 365 and Copilot experiences.

    • Led development of a C# validation framework enabling Microsoft 365 Copilot agents to safely connect to any OpenAPI-compliant REST API, defining which endpoints agents could access via plugin manifests and JSON schema validation, preventing unsafe tool execution.

    • Partnered with the Copilot orchestration team to define structured tool schemas enabling AI agents to discover and invoke approved APIs.

    • Built automated testing infrastructure validating SDKs and documentation by compiling and executing code examples against thousands of Microsoft Graph API endpoints, with zero-permission security testing to detect privilege escalation risks.

    • Improved developer experience by introducing automated changelogs generated directly from OpenAPI specifications, keeping documentation synchronized with API changes at scale.

    • Collaborated with the CTO's office on responsible AI initiatives and AI governance policies.

  • Program Manager Intern, Microsoft

    Jun, 2019 - Sep, 20193 months

    • Led development of a customer support tool from concept to MVP, conducting user research and designing wireframes.

Projects Experience

Projects Experience

  • Agentic Output Evaluation System, Ascendion

    - Present

    Designed a 9-point rubric-based scoring framework for evaluating AI-generated product artifacts including PRDs, features, stories, and tasks enabling comparative quality measurement across prompt sets and establishing a repeatable standard for production readiness.

  • Banking Regulatory Compliance Templates, Ascendion

    - Present

    Translated 15 UK banking regulations including FCA Principles, BCOBS, PSR 2017, and the Data Protection Act into structured story templates encoding compliance requirements as a first-class input to AI-generated product artifacts; replacing ad hoc reviewer recall with systematic coverage.

  • Copilot Agent Tool Validation Framework, Microsoft

    - Present

    Led development of a C# validation framework enabling Microsoft 365 Copilot agents to safely connect to any OpenAPI-compliant REST API using plugin manifests and JSON schema validation, preventing unsafe tool execution.

  • API Documentation Validation Infrastructure, Microsoft

    - Present

    Built automated testing infrastructure validating SDKs and API documentation examples by compiling and executing code samples against thousands of Microsoft Graph endpoints, with zero-permission security testing to detect privilege escalation risks.

Skills

Skills

  • Agentic AI Systems

    Agentic pipeline design

    Pre/post execution hooks

    MCP server integration

    Context window management

    Instruction partitioning across files

    Tiered model routing

    Agent tool validation

    Plugin manifest design

    JSON schema validation

  • Prompt Engineering & Evaluation

    Prompt architecture design

    Token optimization

    Script harness design

    Comparative prompt evaluation

    Rubric-based quality scoring

    Research-informed eval design

  • API & Developer Infrastructure

    OpenAPI specifications

    REST API tooling for AI agents

    SDK testing infrastructure

    Automated documentation validation

  • Regulated Product Development

    FCA Principles & Handbook

    BCOBS / MCOB / PSR 2017

    Data Protection Act 2018

    WCAG 2.1 Accessibility Standards

    Compliance-as-input product design

  • Programming

    Python

    JavaScript

    C++

    Haskell

Education

Education

  • Computer Science, Master's Degree, Portland State University

    Jan, 2016 - Jan, 2019

    3.8
  • Political Science and Government, Bachelor of Arts, Sam Houston State University

    Jan, 2012 - Jan, 2014

Volunteer Work

Volunteer Work

  • President, PSU Chapter, Association for Computing Machinery (ACM)

    Aug, 2018 - Mar, 2020

    Led the Portland State University ACM chapter.

    • Expanded membership from one member to over 70 active members.

    • Hosted events with more than 50 attendees connecting students with industry professionals.