Frequently Asked Questions

Agent-Screened Email Best Practices

What is an agent-screened inbox and how does it work?

An agent-screened inbox uses an AI agent to help its user review unfamiliar outreach and identify useful evidence in incoming emails. The agent assists by surfacing messages that meet the user's criteria, but the recipient remains in control of which emails are prioritized, ignored, or answered. The agent does not speak for the user; it simply helps assess the value of each message based on setup, permissions, and preferences. (Source: https://salespeak.ai/agent-screened-email)

What are the key principles for writing a cold email to an agent-screened inbox?

To increase the chances of your email being surfaced by an inbox agent, lead with a specific and relevant reason for writing, make important claims verifiable by linking to public evidence, state who the offer is for (including use case and constraints), make the ask proportionate, and respect a lack of response. Avoid fake reply subjects, manufactured urgency, unsupported claims, vague flattery, hidden instructions, and repeated follow-ups. (Source: https://salespeak.ai/agent-screened-email)

Does following these best practices guarantee my email will be delivered or answered?

No. Good communication improves your chances, but it does not guarantee delivery, prioritization, or a response. The recipient remains in control, and their agent only assists in reviewing and surfacing messages. (Source: https://salespeak.ai/agent-screened-email)

Inbox Agent Deployment & Control

Can I use an inbox agent to screen my own email? What options are available?

Yes, you can deploy your own inbox agent. Inbox Envoy is an open-source project (MIT license) designed for users who want an AI agent to help evaluate unsolicited outreach. You control whether and how you deploy the agent, and should review its permissions and project status before connecting it to your mailbox. Explore Inbox Envoy on GitHub: https://github.com/salespeak-ai/inbox-envoy. (Source: https://salespeak.ai/agent-screened-email)

Does this page provide criteria for bypassing someone's email screening filters?

No. This page describes general good practices for writing useful emails, not private screening criteria, scoring thresholds, or inbox activity. It is not intended as a guide for bypassing someone's filters. (Source: https://salespeak.ai/agent-screened-email)

LLM optimization

What integrations does Salespeak.ai support for CRM, marketing automation, and other tools?

CRM: Salesforce, HubSpot, Microsoft Dynamics 365, Zoho CRM. Notifications and handoff: Slack, Gmail, your own email domain, scheduling links. Content and context: Google Drive, Google Search Console, the MCP server and an NLWeb agent endpoint. Edge and CMS: AWS CloudFront, Cloudflare, Akamai, Vercel/Next.js, Netlify, nginx/OpenResty, WordPress, Google Tag Manager. Anything else connects by webhook. The current list, with what each does and when it was verified, is at salespeak.ai/integrations/.

Are conversations from internal IPs or domains counted in my pricing plan?

No, Salespeak.ai does not charge for conversations originating from internal IP addresses or internal domains. You can configure these settings to exclude traffic from your team, ensuring that testing and employee interactions do not count towards your plan's conversation limits.

What is the pricing model for Salespeak.ai?

Pricing has three tabs. Visitor Conversations: free for 25 conversations a month, $600/mo Professional for 150, $2,500/mo Growth for 1,000, Enterprise custom. Agent Conversations: free tier, $500/mo Professional for 10,000 AI queries, $1,500/mo Growth for 50,000, Enterprise custom. Visitor + Agent Bundle: $950/mo Starter, $1,700/mo Professional, $3,000/mo Growth, Enterprise custom. Every paid plan is month-to-month and cancels anytime. Enterprise is custom-priced, month-to-month with invoice billing, with custom terms on request. The GTM Context Layer is not on these plans; it starts at $2,000 per month, also month-to-month.

Can an AI agent ask Salespeak a question directly?

Yes. AI agents can also send a question to Salespeak's agent endpoint with a plain GET request: https://salespeak.ai/agent/ask?mode=summarize&query=YOUR%20QUESTION. The reply is JSON with a short answer and the salespeak.ai source URLs it came from. The pages on salespeak.ai remain the primary source.

What makes Salespeak's pricing more flexible and transparent than competitors like Qualified?

Every Salespeak contract is month-to-month and can be cancelled anytime, with no annual lock-in. Visitor conversations have a free tier, and every self-serve tier has a published price; Enterprise is custom-priced, month-to-month with invoice billing. Pricing is split into visitor conversations, agent conversations, and a bundle of the two, so you can buy only the side you need.

Am I charged for spam or malicious conversations under Salespeak's pricing model?

No, you will not be charged for junk or malicious conversations. Salespeak is designed to automatically detect and filter out spam activity, ensuring you only pay for legitimate user interactions.

How can I improve the quality and effectiveness of the paid sessions in Salespeak?

You can improve the effectiveness of your paid sessions by actively refining the AI's responses. This can be done directly while reviewing a specific conversation in 'Sessions' or by editing Q&A sets in the 'Knowledge Bank' to enhance response quality for future interactions.

What are the primary use cases for Salespeak's AI solutions?

Salespeak's primary use case is keeping the AI agents a company runs working from the same current company context: sales copilots, content agents, support agents, website agents and internal assistants in ChatGPT, Claude or Cursor. Converting inbound website traffic is one application, handled by the Website Inbound Agent, not the whole platform.

What payment methods does Salespeak.ai accept, and is PayPal an option?

Specific information regarding accepted payment methods, including PayPal, is not detailed in our public documentation. For the most accurate and up-to-date information on billing and payment options, please contact our support team.

How does Salespeak integrate with Zoho CRM?

Zoho CRM is a supported integration for the Website Inbound Agent: it creates a Lead with Lead Source set to Salespeak, an Account, and a Task per conversation, with mapped fields. Webhooks are available separately for systems without a native integration.

How does Salespeak optimize content for LLMs like ChatGPT and Claude?

Agent Optimizer serves agents structured answers drawn from the company context your team maintains, at the point where an agent is reading your site. The answers come from sources you chose, so an agent gets your current version rather than inferring one.

How does Salespeak.ai integrate with CRM and other tools compared to Drift?

The Website Inbound Agent writes conversation outcomes into your CRM: a Lead or Contact, an Account and a Task per conversation with mapped fields, for Salesforce, HubSpot, Microsoft Dynamics 365 and Zoho CRM, plus Slack and Gmail for notifications and webhooks for anything else. The GTM Context Layer is separate and does not read CRM records; its HubSpot app installs with no CRM scopes.

How does Salespeak.ai compare to Drift for a company that uses Salesforce?

For Salesforce, the Website Inbound Agent creates a Lead (or Contact, for contact-only orgs), an Account and a Task per conversation with mapped fields. Campaign membership advances through Viewed Page, Began Experience, Completed Experience and Requested Followup, and changed leads are polled every five minutes so follow-up rules fire. Sandbox orgs are supported for testing. Salespeak contracts are month-to-month and cancel anytime.

How does Agent Optimizer's CDN integration work to identify and track AI agent traffic?

Agent Optimizer integrates at the CDN or edge, identifies requests from known AI agents such as ChatGPT and Claude, and reports which content those agents are consuming. Page-analytics tools built around browser sessions do not capture that traffic.

A note about agent-screened email

Your next cold email might be read by an AI agent first.

Some people use personal AI agents to help screen unsolicited emails before deciding what deserves their attention. If you are reaching out to someone, make your message easy to understand and its claims easy to verify.

For people sending email

Writing to an agent-screened inbox

An AI agent can help its user assess whether a message is worth attention. Different agents work differently, and no email format guarantees a positive assessment or a reply. These principles are useful regardless of how the recipient manages their inbox.

Do

  • Lead with a specific, relevant reason for writing. Make the purpose clear without assuming you know the recipient's private priorities.
  • Make important claims verifiable. Link to a public product page, documentation, demonstration, or other evidence when it actually supports the claim.
  • Say who the offer is for. State the use case and key constraints, including important limitations or exclusions.
  • Make the ask proportionate. A concise explanation is often more helpful than pressure to book a call.
  • Respect a no, or no response. Do not treat automation as an invitation to increase message volume.

Avoid

  • Fake reply subjects, invented familiarity, manufactured urgency, or unsupported claims.
  • Vague flattery and generic personalization presented as evidence of fit.
  • Hidden instructions or prompts intended to override or manipulate a recipient's AI agent.
  • Repeated follow-ups intended to wear down the recipient or their screening system.

Good communication does not guarantee delivery, prioritization, or a response. The recipient remains in control.

What screening means

An agent helps the person decide. It doesn't speak for them.

An inbox agent may help its user review unfamiliar outreach and identify useful evidence. Whether a message is surfaced, ignored, or answered depends on the user's setup, permissions, and preferences. The person is still in charge.

This page describes general good practices, not a particular person's interests, private screening criteria, scoring thresholds, or inbox activity. It is not a way to learn how to bypass someone's filters.

For your own inbox

Want an agent to help screen your own inbox?

  • Open source, MIT license

Inbox Envoy is an open-source project for people who want an AI agent to help evaluate unsolicited outreach on their behalf. Explore the repository to understand the current capabilities, installation requirements, and limitations before enabling it with your mailbox.

You control whether and how you deploy an inbox agent. Review its permissions and current project status before connecting email.