Meta enterprise AI patterns

Leading & designing the way employees use AI on Meta internal tools

Co-architected Meta’s canonical enterprise AI design guidance, which defined 28 interaction patterns across 9 categories before organizational adoption accelerated across 220 internal products.

Role:

Co-Lead & Principal Lead

Coverage:

220 Enterprise Apps

Catalog:

28 Patterns, 9 Catagories

Measured impact:

+40 pts CSAT jump

Role:

Co-Lead & Principal Lead

Coverage:

220 Enterprise Apps

Catalog:

28 Patterns, 9 Catagories

Measured impact:

+40 pts CSAT jump

The AI era was here, but enterprise products had no guidance

Meta's central AI assistant was not positioned to

The Enterprise Orchestration Gap

In 2024, Meta's central AI assistant was built inside an engineering-focused org for developer workflows (PRs, code reviews). Enterprise Products, which powers HR, performance tools, and internal ops for tens of thousands of employees, had zero GenAI interaction patterns. Teams were about to create fragmented, unvetted UIs.

Scaling the Guild Operating Model

After founding the EP GenAI Guild, initial group roundtables had low turnout. I pivoted from passive group discussions to embedding directly inside ML engineering reviews, identifying AI capabilities before designers were assigned, and offering targeted 1:1 design consultations across 10+ teams.

I created 12 enterprise-grade AI UX patterns

Designed for real-world enterprise workflows, covering key variants, edge cases, and failure mode

Visibility, then priority

I embedded in the ML team's own meetings, seeing product ideas before teams had a designer assigned. I also audited which patterns products were actually using, so EPS could prioritize by evidence, not guesswork — chat came out on top.

One patternthe company adopted wholesale

Chat was the pattern every team wanted first.

Teams either built their own bespoke pattern, or stalled — reluctant to design an interaction language from scratch.

One fully specified pattern any team could pick up directly. Meta's design system adopted it as the company standard.

What mattered wasn't that a pattern existed — it removed the reason not to build at all.

Chat was the pattern every team wanted first.

Teams either built their own bespoke pattern, or stalled — reluctant to design an interaction language from scratch.

One fully specified pattern any team could pick up directly. Meta's design system adopted it as the company standard.

What mattered wasn't that a pattern existed — it removed the reason not to build at all.

The patterns a small library, not one component

Twelve patterns came out of this work, adopted across seventeen product-team experiments. Chat came first — these are a few others.

Results

12

Shipped patterns

17

product team adoptions in 2024

Chat pattern became basis for all internal chat experiences

Later extended into agentic patterns by our design systems team

Leadership recognition

My pattern work featured in a presentation that reached Zuckerberg's small circle

None of this looked obvious at the time. It reads as default now, the way good patterns eventually do.

Leadership support stayed ambiguous, and I rolled off as priorities shifted. Even so, this is still EPS's design system guidance as of 2026.

None of this looked obvious at the time. It reads as default now, the way good patterns eventually do.

Leadership support stayed ambiguous, and I rolled off as priorities shifted. Even so, this is still EPS's design system guidance as of 2026.

Jonathan LoPorto