Agent SwarmUX Command Center
A standing UX agent that keeps your product usable — weekly audits against your design system, agentic browser session recording, and proactive UX-improvement proposals from user telemetry. Creates a Linear umbrella with one sub-issue per finding.
A UX-focused agent walks your frontend every week, audits against UX principles and your design system, and creates a Linear umbrella ticket with one sub-issue per finding — so humans process a curated todo list, not a fire-hose audit report.
What it does
A UX agent walks the frontend weekly, audits against UX principles + your design system, and creates a Linear umbrella ticket with one sub-issue per finding — so humans process a curated todo list. The same agent records agentic browser sessions (qa-use) and pulls user-behavior signals from product analytics.
Agents
- UX Principles Agent — React / MUI component analysis, design-system adherence checks, accessibility, frontend code review. Domain-trained on your design system.
Tools & Skills
Built-in (ships with agent-swarm)
- agent-fs — audit reports persisted here for human review across sessions.
- Linear integration — inbound sync. See Linear integration.
slack-post— the weekly audit-complete notification.investigate-sentry-issue— cross-references UX issues that throw Sentry errors.
Custom (swarm-managed)
linear-interaction— outbound Linear writes (creating the umbrella + sub-issues programmatically).posthog-interaction— funnel/cohort data from PostHog via the HogQL API.
Third-party providers
- qa-use — agent-first browser-automation CLI. The agent drives it to reproduce a problematic flow and embeds the recording in the sub-issue.
- PostHog — funnel/cohort/event data for "users are dropping off here" cross-references.
- Sentry — cross-reference UX issues that throw errors.
Workflows / Schedules
weekly-ux-audit— weekly. Clones the frontend repo, runs a full UX-principles audit, creates a Linear umbrella ticket with sub-issues for each finding, posts the umbrella URL to Slack. Each sub-issue is single-component-scoped so it's individually fixable.
Patterns used
- Drain Loops — the umbrella's sub-issues can feed a drain loop to auto-fix the low-risk ones.
Tips for new swarm users
- Scope each audit to one app/dir. Frontend audits compound when focused; running against the whole monorepo every week burns tokens and produces unactionable noise.
- Create Linear sub-issues, not a markdown dump. Humans process work, not raw reports. One sub-issue per finding turns "we should fix UX" into a concrete backlog.
- Pair the UX agent with qa-use for "show me where this UI feels broken" loops. The agent reasons; qa-use reproduces.
- Cross-reference behavioral data. A claim like "users are confused by X" is far more credible with a PostHog funnel showing the drop-off.
- Cap audit-round complexity. If a sub-issue takes more than ~3 review rounds, escalate to a human — it's a design decision, not a UX nit.
Content Generation
Topic mining, blog posts, social posts, memes, comparison and how-to pages, and release notes — at the cadence you want, with LLM-as-judge quality gates and human craft on top before anything ships.
Proactive Customer Support
Standing agents per top account — persistent working directories, scheduled value-showcase reports, automatic post-meeting ingestion, and "what changed since last touchpoint?" briefings on demand.