Support Agent

Most support tools send users a help article and hope they figure it out. Floe does the opposite. When a user asks for help, the agent provides proactive support by navigating to the right screen, showing them exactly how it works, and offering to do it for them.

How it works

The same AI agent that demos and onboards also handles support. When a user gets stuck:

  1. They ask the agent (voice or text)
  2. The agent understands what they're trying to do
  3. It navigates to the relevant screen in the user's browser
  4. It shows the user what to do, step by step
  5. If the user says "just do it," the agent executes the task

No ticket. No waiting. No context switching to a help center.

Action, not documentation

Traditional support chatbots search your knowledge base and paste an article. The user reads it, tries to follow the steps, gets confused at step 3, and files a ticket anyway.

Floe skips the article entirely. The agent has the same product knowledge (from ingestion) and the same ability to navigate your product (from exploration). It resolves by doing.

Proactive support

Floe doesn't wait for users to ask. It watches for signals that a user is stuck:

  • Circling the same screen without taking action
  • Repeated failed attempts at a workflow
  • Long idle time on a setup page
  • Visiting the help center (and coming back without acting)

When it detects friction, it offers help proactively. "Looks like you're setting up notifications. Want me to walk you through it?"

Escalation

Not every question can be resolved by the agent. When the agent can't help:

  • It captures the full context: what the user was trying to do, what screens they were on, what they said
  • It creates a support case with this context pre-filled
  • Your support team picks it up with full history, not a vague "I need help" message

What support data you get

Every support interaction feeds into your product insights:

  • Common questions: What users ask about most
  • Friction points: Where users get stuck repeatedly
  • Resolution rate: What percentage the agent resolves without human help
  • First contact resolution: How quickly issues are handled on the first interaction

This data helps your product team prioritize fixes and improvements.

FAQ

Does the support agent replace my support team? No. It handles the repetitive "how do I do X" questions to reduce customer effort score so your team can focus on complex issues that need a human.

Can the agent handle billing or account questions? It can navigate to billing screens and explain what the user sees. For changes that require API access (plan changes, refunds), it escalates to your team with full context.

How does it know the answer? From your ingested content. The more thorough your docs and knowledge base, the better the agent handles support questions.