AI-Assisted Design and Research Workflows
Industry
Enterprise AI
Client
Accedo
Platforms
LLM workflows, design systems, ResearchOps, custom MCPs
Date
2022 to present
CASE STUDY BRIEF
Capability
AI product strategy, workflow design, design systems
Leadership level
Director
What I led
Built AI-assisted workflows at Accedo for design-system contribution checks, research synthesis, knowledge retrieval, and internal tool access.
Why it matters
The team reported a 25% reduction in exploration and validation time while keeping people responsible for quality-critical decisions.
DECISION RECORD
Problem and stakes
As the design system and research surface grew, teams repeated contribution checks, intake work, knowledge searches, and synthesis tasks that were necessary but slowed delivery.
Role and scope
Created and introduced the workflows across design-system validation, contribution intake, research, organizational knowledge, and custom internal integrations.
Key decision and trade-off
Used AI to flag, route, retrieve, and synthesize; kept approval and judgment with the people responsible for the product and system.
Systems and artifacts
LLM-assisted design-system linter, contribution-intake workflow, research-synthesis flows, organizational knowledge agents, and custom MCP integrations.
Related content
At Accedo, I targeted the repeatable work around design-system contributions and research rather than adding a general-purpose AI layer. I built an LLM-assisted linter to flag contribution issues, structured intake so proposals arrived with the context reviewers needed, and created knowledge and research workflows for retrieval and synthesis. Custom MCP integrations connected those workflows to internal tools. AI could flag, route, retrieve, and summarize, but the people accountable for the system still approved changes and made quality decisions. The team reported a 25% reduction in exploration and validation time; I do not claim that AI replaced the review work that protected quality.
