Spaces
Use case / Lead qualification

Lead qualification with your AI agent

Spaces lets your AI agent qualify the leads that message your business on WhatsApp, Instagram, LinkedIn and Facebook Messenger. It replies within moments, asks the two to four questions you use to tell a good fit from a poor one, saves the answers, tags each lead as hot, warm or not a fit, and passes the hot ones to a person on your team with a summary.

Example

See it in a conversation.

Names and details are examples.

LeadLead qualificationAI agent
Setup

How to set it up step by step.

The full reference is in the partner docs.

  1. 1

    Connect your accounts

    In your Spaces dashboard, connect the accounts you already use.

  2. 2

    Add Spaces to your AI agent

    Add Spaces to the AI agent you already use, such as Claude, ChatGPT or your own code, through the MCP server or the API.

  3. 3

    Write the qualifying brief

    List your questions, what counts as hot, warm and not a fit, what the agent may say about price, your booking link and who owns which kind of lead.

Details

The details.

Quick answer

Spaces handles the conversations and keeps the answers on the contact. Spaces does not connect to CRMs: if you want leads in yours, connect it to the agent through its own tools or MCP server, and the agent writes them there itself.

What the AI agent does on each channel

Spaces works with Instagram, WhatsApp, LinkedIn, Facebook and TikTok (coming soon). On Facebook, that means Messenger on a personal Facebook account.

  • WhatsApp: Enquiries from your website, listings and ads arrive as WhatsApp chats. The agent answers the first question, then asks about budget, timing and need, one question at a time, and reads any files or photos the lead sends.
  • Instagram: Leads write in after a post or a story, or comment “price” or “info”. The agent answers in their messages, sends a private reply from the comment where Instagram allows it, and qualifies them in the same chat.
  • LinkedIn: The agent answers prospects who message you, looks up their public profile for company size and role, and skips the questions the profile already answers.
  • Facebook Messenger: The agent qualifies people who message your personal Facebook account about your offer, and tells you when one is ready to talk.
What questions should an AI agent ask to qualify a lead?

The same ones your best salesperson asks, in plain words. Most businesses need three: what the person needs, when they need it, and whether the budget fits. Some add a fourth, such as location for a local service or company size for software. Write them in your brief, along with the answers that make a lead a good fit and the ones that rule it out.

The agent asks one question at a time and answers the lead’s own questions in between, so the chat feels like a conversation, not a form. If a lead already said their budget in the first message, the agent does not ask again.

How does the agent score and tag leads?

You decide the rules, and the agent applies them. A simple version: hot when all three answers fit, warm when one is unclear, not a fit when the budget or timing is far off. The agent tags the chat, saves each answer as a field on the contact, and can save the lead as a custom object you define, with fields such as budget, timing, source and score.

Tags make the rest easy. Ask your agent for every warm lead from this week, assign all hot leads to one salesperson, or start a follow-up for warm leads who asked to hear back after a month. Follow-ups stop as soon as the person replies.

When does a lead go to a person?

As soon as it is hot. The agent books a call with your booking link or its own calendar tool, assigns the chat to the right owner, and writes a short private note so your salesperson walks in prepared. Ask your AI agent to hold replies as drafts, and nothing goes out until you approve it. Many teams keep drafts on for the first week and switch them off once the questions read well.

After setup
  • Connect your CRM, if you want. To copy leads into your CRM, connect it to the agent through its own tools or MCP server. The agent reads the chat through Spaces and writes the lead itself. Spaces does not connect to CRMs.
  • Set up triggers. Use a trigger to wake the agent when a new chat starts or a comment arrives, so no lead waits for someone to check the inbox.
  • Test it. Send your own account an enquiry from another phone or profile, as a good lead and as a poor one, and check the tags and the hand-over.
What always goes to a person

Tell your agent to hand these to a person every time:

  • every hot lead, with a summary and the call booked if possible
  • discounts, custom quotes and anything outside your price list
  • contracts, terms and anything legal
  • a lead who asks to speak to a person
  • answers the agent cannot place, or anyone who seems unsure or upset
Safe by default, on every account

Qualifying works best on leads who wrote to you first. Replies to someone who wrote in are not held back by the warm-up, so new enquiries get an answer from the first day.

Spaces is not a tool for messaging bought or scraped lists, and on LinkedIn any outreach should be careful one-to-one messages to people you chose. Spaces lowers the risk with limits, pacing and warm-up, and pauses sending if an account shows signs of a restriction. No tool can promise that a platform will never restrict an account, and Spaces does not either.

  • A new chat only goes to someone who has messaged your number before, or whom you marked as opted in on the Accounts page.
  • Instagram replies to people who wrote in: 250 a day and 40 an hour, at least 15 seconds apart (60 a day and 15 an hour on days 1 to 3).
  • LinkedIn: up to 100 new conversations and 100 messages a day, at least 20 seconds apart.
  • Facebook Messenger: up to 50 messages and 8 new chats a day, at least 20 seconds apart.

Every channel’s limits are on sending limits, and how Spaces protects accounts is on account safety.

Read more
FAQ

Questions, answered.

01How fast does the AI agent reply to a new lead?

Usually within a minute. Spaces adds a short, natural pause before each reply, and a trigger can wake the agent the moment a new chat starts.

02Can the agent score leads automatically?

Yes, by the rules you write. It tags each lead, saves the answers on the contact, and can store a score on a custom lead object you define.

03Does Spaces connect to my CRM?

No. Connect your CRM to the agent through its own tools or MCP server, and the agent writes leads and notes there itself.

04Can it book a sales call?

Yes. It can share your booking link, or book the call itself through its own calendar tool if you connect one.

05What happens to leads that are not a fit?

The agent thanks them, answers politely, and tags them “not a fit”. You decide whether it suggests an alternative or simply closes the chat.

06Can I check the questions before they go out?

Ask your AI agent to hold replies as drafts, and nothing goes out until you approve it.

07What does it cost?

Free to start, then $19 per connected account a month. Start on the Free plan with no card, and see the pricing page for the details.

Built for

Industries that use this most.

More use cases

Other ways to use Spaces.

Start building.

Start with a workspace of your own to try the API, then email hello@spacesos.com to become a partner.