> ## Documentation Index
> Fetch the complete documentation index at: https://docs.introw.io/llms.txt
> Use this file to discover all available pages before exploring further.
# AI Agents
> Introw's AI agents answer partner questions 24/7, coach every deal, and take action across your CRM - so a small team can run a large program.
export const Headless = ({prompts = []}) => {
const PromptRow = ({prompt}) => {
const [copied, setCopied] = useState(false);
const copy = () => {
try {
navigator.clipboard?.writeText(prompt);
} catch {}
setCopied(true);
setTimeout(() => setCopied(false), 1600);
};
return ;
};
return <>
Introw is headless by design: run everything here in plain language from Claude, ChatGPT,
Slack, Teams, or your own CRM through Introw's MCP server, with every
action written straight back to your CRM source of truth. The portal is one surface, never the only one.
{prompts.length > 0 ? :
The agentic playbook - lifecycle deep dives and a Claude Code skill library that run your partner program
from Claude, ChatGPT, Slack, and your CRM.
}
;
};
> Introw is AI-native, not AI-bolted-on. The partner support agent answers questions in every language around the clock, deal coaching puts a coach in every deal, and both can take real actions in your CRM - not just chat.
## What this area does
The partner support agent answers partner questions wherever they work: the portal, Slack, Teams,
email, and AI assistants connected over MCP. It draws on a knowledge base you control, your websites,
snippets, documents, and live portal data like tiers, commissions, and assets, and it can act,
registering deals, updating CRM records, and more, scoped to each partner's permissions.
Deal coaching gives partners and sellers segment-specific guidance in every deal. You build coaching
playbooks, stage instructions, objection handling, enablement, and rules of engagement, and they
surface right on the deal and through the agent. Together these agents take the mechanical work off
your team so they can focus on relationships and revenue.
## Why it matters
* **AI-native** - Agents do the mechanical work, with humans in the loop where judgment matters.
* **CRM-native** - Agents ground their answers and coaching in your CRM data and write outcomes back to the same records, so a coached deal or a logged interaction lands in the source of truth and the assistant never creates a parallel version of reality.
* **Work where you already are** - Partners get answers and coaching in Slack, email, and their own AI assistant.
## How it fits together
The knowledge base feeds the support agent, and coaching playbooks feed the deal coach:
```mermaid theme={"theme":{"light":"github-light","dark":"github-dark"}}
flowchart LR
kb["Knowledge base"] --> agent["Partner support agent"]
agent --> action["Answers and CRM actions"]
playbooks["Coaching playbooks"] --> coach["Deal coach"]
coach --> guidance["Guidance on every deal"]
```
## Capabilities
Answer partner questions 24/7 across every channel.
Control what the agent knows.
Put a coach in every deal.
## Who works in this area
Configures the agent and its knowledge.
Shapes the agent's tone and coaching content.
Defines deal coaching playbooks.
## Headless
## All guides
{/* ROLLUP:START - generated content goes here */}
Turn on AI channel-conflict screening for a deal form, then review and resolve any overlap from the Submissions inbox before it syncs to your CRM.
Create a deal coach, scope it to the right partners and deals, and refine its stage guidance, objections, enablement, and rules so partners get the right coaching on every matching deal.
Give the partner support agent live tools by connecting your own MCP server, so it can fetch real-time data and take actions beyond your static knowledge base.
Ground the partner support agent by crawling your websites, adding snippets for specific answers, and uploading PDF documents the agent can draw on.
Enable the partner support agent, give it a name, instructions, welcome message, and logo, test it, surface it in the portal, and monitor real conversations.
Connect Slack and map partners to shared channels so the partner support agent answers partner questions where they already work.