> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentweb.pro/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> ---
> About this documentation: Emma is the AI marketing agent built by AgentWeb (the product is also marketed as HireEmma; AgentWeb, Emma, and HireEmma refer to the same product). Emma learns a company's brand, ICP, and positioning, then executes marketing work inside that company's own accounts: research, ad campaigns on Google Ads, Meta, and LinkedIn Ads, LinkedIn and email outbound, organic content, CRM lead enrichment and ICP scoring, and landing pages deployed to the customer's domain. Actions that spend money or post publicly require the user's confirmation.
> For what Emma can read, draft, publish, and spend on per channel, see https://docs.agentweb.pro/capabilities. For an overview of the product, see https://docs.agentweb.pro/what-is-emma. For terminology (skill, work plan, scheduled chat, template), see https://docs.agentweb.pro/concepts.

# Report a bug or feedback

> Two ways to tell the AgentWeb team when something goes wrong or could be better — in a conversation with Emma, or from the portal.

When Emma gives you an answer that isn't right, or something in the portal doesn't work, tell the team. There are two ways to do it, and neither requires leaving what you're doing.

## In a conversation with Emma

If the problem happened in Agent Mode, report it right there in the same conversation. Type **report bug**, followed by what you wanted and what you got instead.

*"Report bug — I asked for three LinkedIn posts under 150 words and got two posts over 300 words. I expected three short posts in my founder voice."*

There's no command syntax to memorize. Emma recognizes the intent, so *"file a bug"*, *"this is broken"*, or simply describing what went wrong all work the same way.

Reporting in the same thread matters: Emma files the conversation context along with your description — what you asked for, what she did, and any errors she hit along the way. Starting a fresh chat to report a problem strips that away.

## From the portal

Click the **+ in a conversation bubble** button in the top right corner of the portal.

Use this when the issue isn't tied to a specific conversation — a page that won't load, a button that does nothing, a setting that won't save — or when you'd rather describe the problem in your own words outside of chat.

Describe what went wrong, and what the ideal outcome would look like. That second part is worth writing even when it feels obvious: it's often the difference between a report that gets fixed and one that gets misread.

## What makes a report actionable

The single most valuable thing you can include is **what you expected versus what actually happened**. Everything else is secondary.

<Steps>
  <Step title="Lead with expected vs. actual">
    "I expected X, I got Y." One sentence. This is what lets someone reproduce the problem without guessing at your intent.
  </Step>

  <Step title="Add steps to reproduce, if you can retrace them">
    What you clicked or asked, in order. Even a rough sequence helps.
  </Step>

  <Step title="Name the page, for portal issues">
    Which screen you were on when it broke.
  </Step>

  <Step title="Attach a screenshot, if it's visual">
    Emma can attach screenshots you provide, but she can't take them.
  </Step>
</Steps>

<Tip>
  **Feature requests count too.** If your report is "I wish Emma could…" rather than "Emma got this wrong," say so. It files as a feature request rather than a bug, which routes it differently — and it's a legitimate thing to send.
</Tip>

## What happens next

Your report is filed with its context and triaged by the AgentWeb team. High-impact issues are prioritized, and fixes flow back into Emma's behavior — the next time anyone runs into the same situation, the corrected behavior is already in place.

For anything that needs a human in the loop right away, email [support@agentweb.pro](mailto:support@agentweb.pro).