> ## 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.

# Concepts and vocabulary

> What a skill, work plan, scheduled chat, template, and lead list each mean in AgentWeb, how they relate, and which ones people most often confuse.

AgentWeb has a small vocabulary that does a lot of work. Getting these five straight — **skill, work plan, scheduled chat, template, conversation** — removes most of the confusion people hit in their first month.

## The one-line version

| Term                  | One sentence                                                                                                    |
| --------------------- | --------------------------------------------------------------------------------------------------------------- |
| **Emma**              | The AI marketing agent. Everything else on this page is something Emma uses or you configure for her.           |
| **Agent Mode**        | The chat interface in the Customer Portal where you work with Emma. Most work starts here.                      |
| **Conversation**      | A single persistent chat thread. Context and installed skills live here and do not carry to the next chat.      |
| **Skill**             | A capability: a bundle of tool grants plus standing rules that change how Emma behaves while it's installed.    |
| **Work plan**         | A sequence: ordered steps with instructions, state, and checkpoints where you review before Emma continues.     |
| **Scheduled chat**    | A prompt Emma re-runs on a cadence, with a name, a schedule, and somewhere to send the result.                  |
| **Template**          | A reusable HTML layout Emma fills in — structure and styling for email and recurring content formats.           |
| **Brand Hub**         | Where your brand identity, positioning, templates, and reference docs live. Emma reads it on every run.         |
| **Knowledge Base**    | The reference material inside Brand Hub that Emma searches and reads during conversations.                      |
| **Market Strategy**   | Your business overview, value proposition, ICP segments, and competitors.                                       |
| **ICP persona**       | A validated definition of who you sell to — behavior-based, not just demographic.                               |
| **Founder profile**   | Your personal voice description inside Brand Guidelines. Without it, Emma writes in a neutral brand voice.      |
| **Lead list**         | A group of leads in the CRM with its own pipeline stages, custom fields, and point of contact.                  |
| **Enrichment**        | Emma researching leads and filling in missing fields, with a 2-lead preview before the batch runs.              |
| **ICP score**         | A 0–100 score Emma assigns a lead by reading it against your Market Strategy ICPs.                              |
| **Connected account** | An authorized link to an outside platform. One platform can have several, each granting different capabilities. |
| **Organization**      | A shared workspace — members, roles, and shared brand assets, leads, campaigns, and integrations.               |
| **GEO**               | Generative Engine Optimization: your visibility inside AI-generated answers, tracked alongside SEO.             |

## Skill vs. work plan

This is the distinction people conflate most, and the two compose rather than compete.

|                       | Skill                                                     | Work plan                                                          |
| --------------------- | --------------------------------------------------------- | ------------------------------------------------------------------ |
| What it is            | A capability — tools plus standing rules                  | A sequence — ordered steps with gates                              |
| Question it answers   | *Can* Emma do this?                                       | *In what order*, with what checkpoints?                            |
| Grants tools          | Yes                                                       | No — it installs skills that do                                    |
| Has order and state   | No                                                        | Yes                                                                |
| Persists across chats | No                                                        | No, but the plan definition persists                               |
| Where you create it   | Say "make this a skill" in chat, or **Settings → Skills** | Say "make this as a workplan" in chat, or **Settings → Workplans** |
| Where you run it      | Install it in a conversation                              | **New Chat → Select a workplan**                                   |

Reach for a **skill** when the reusable thing is judgment — "here's how we evaluate quality, always apply this lens." Reach for a **work plan** when the reusable thing is a sequence with checkpoints — "do these five steps in this order, stop here for my approval."

They connect at the step level: a work plan step declares the skills it needs, and launching the plan auto-installs them. Mature capabilities often ship as both.

<Note>
  Neither one is a schedule. To run either on a cadence, create a **scheduled chat** whose prompt launches it.
</Note>

## Scheduled chat vs. work plan

A work plan answers *what steps, in what order*. A scheduled chat answers *when, and where do the results go*. They're orthogonal, and a scheduled chat is how a work plan gets a cadence.

A scheduled chat needs four things: a name, a cadence, the prompt to re-run, and where to send results.

<Warning>
  **Unattended runs don't pause for approval.** Scheduled runs proceed on a best-effort basis rather than stopping to ask. Before scheduling anything, check whether a step sends, posts, or spends — if so, restructure it to end at a draft.
</Warning>

## Template vs. work plan

A **template** is a layout — the structure and styling of an email or a recurring content format. A **work plan** is a workflow — the steps that produce the content.

If what you want to reuse is *how the output looks*, that's a template. If it's *the sequence of steps that got you there*, that's a work plan.

## Conversation vs. everything else

A conversation is the unit of context. It holds your objective, Emma's output, your corrections, and any skills installed during it.

What carries between conversations: your Brand Hub, Market Strategy, Knowledge Base, CRM, connected accounts, and your saved work plans and skills.

What does **not** carry: installed skills, mid-thread corrections, and pasted context. That's why converting a good thread into a work plan is worth doing while the thread is still fresh.

## Connections aren't one thing

"Connected" is not a single state, and this trips people up constantly:

* **Same platform, different capabilities.** LinkedIn has three separate connections — organic posting, Outreach, and Ads. Having one doesn't grant the others.
* **A skill existing doesn't mean an account is connected.** Emma has Meta and Google Ads skills whether or not you've linked those accounts.
* **Connected doesn't always mean fully authorized.** A connection can be active while missing the specific permission a request needs.

Ask Emma *"what accounts do I have connected?"* before assuming a channel is live. See [Capabilities](/capabilities) for which connection each action requires.

## Next steps

* [What is Emma?](/what-is-emma) — the entity, the scope, and the limits.
* [Capabilities](/capabilities) — what Emma can read, draft, publish, and spend on, per channel.
* [Skills](/user-guide/skills) and [Work plans](/user-guide/work-plans) — the full reference for each.