Skip to content
NewSee how
New

Reply threads now come with AI insights built in

Every reply in your inbox now carries its own AI-generated read on intent and sentiment, so you can triage faster and know exactly what to say next. It's saved with the thread, so it's there whenever you come back to it.

Cold email replies are where campaigns actually get won or lost, but they've always demanded the most manual work. A one-line reply could be an enthusiastic yes, a soft no, or a buried question you almost missed. Reading that correctly, every time, at volume, is hard. Now the reading is done for you.

What changed

When a prospect replies to one of your campaign emails, open that conversation in the Inbox and you'll see a new AI Insights panel sitting alongside the thread. It looks at what the prospect actually wrote — not a generic keyword scan, but a full read of the reply in context — and surfaces:

  • What they're saying — a plain-language read on the reply, translating a terse or ambiguous line into a clear takeaway, not just repeating the raw text back at you
  • Intent and sentiment — whether they're interested, hesitant, declining, forwarding you to someone else, or somewhere in between
  • What they're asking for — specific requests, questions, timing constraints, or objections buried in the message, even when they're not stated directly

The biggest part of this change isn't just that the analysis exists — it's that it sticks. The insight is saved with the thread itself, computed once and attached permanently to that conversation. Come back to that thread tomorrow, next week, or after a long stretch of follow-ups on other leads, and the AI's read is still sitting right there, unchanged. Nothing gets recomputed on reopen, nothing gets lost between sessions, and you're not stuck rereading the whole exchange line by line to remember why you flagged it in the first place. The panel is part of the thread's permanent record, not a one-time popup that vanishes once you click away.

How to use it

  1. Go to your Inbox and open any campaign conversation that has a reply from a prospect.
  2. Look for the AI Insights panel positioned alongside the conversation thread — it sits with the message, not buried in a separate tab or settings menu.
  3. Read through the summary of intent, sentiment, and any specific asks the prospect raised in their reply.
  4. Use that read to decide your next move on the spot — send a quick reply, escalate to a call, loop in a teammate, or move the lead forward in your pipeline — without re-reading the full thread from scratch to reconstruct context.
  5. Return to the thread anytime, whether it's later the same day or weeks down the line — the same insights are still attached, exactly as they were generated, ready the moment you open the conversation.

Why it matters

Reply volume doesn't arrive evenly. Some days a handful of prospects respond within minutes of each other, right in the middle of a busy send window, and every one of them needs a quick, accurate read before you can decide how to respond — is this a real opportunity, a polite pass, or someone who just needs one more piece of information before they say yes. Other times, a thread goes quiet for days after an initial reply, and you come back to it cold, trying to remember the context of a conversation you started a week or two ago, half-scrolling through old messages to piece together where things stood.

The AI Insights panel handles both situations the same way: it does the first pass of interpretation for you, immediately, and it doesn't forget. When replies pile up, you're triaging based on a clear, consistent signal instead of skimming every message individually to guess who's actually interested and who's just being polite. When you return to a thread after time away, the insight is already there waiting — you don't lose the read you had, you don't have to redo the work of figuring out intent all over again, and you don't risk misreading a reply differently the second time around just because the context has gone stale in your head.

The result is a faster, more consistent response to every reply that lands in your inbox, whether it's the first one of the day or the fiftieth, and whether you're acting on it in the moment or picking the conversation back up long after it first arrived.

All updates

Outreach that keeps going after you log off.Leads, emails, follow-ups and replies, handled.

Connect unlimited mailboxes and let AI agents find leads, write each email and follow up. Or send your own templates in manual mode. From $29/mo.

$1 for 3 days · Cancel anytime · No contract

Install with AI

Your coding agent sets up the FirstSales CLI and skills for you.

Prompt for Claude Code

I'm setting up FirstSales (https://firstsales.io), an AI outbound sales platform: campaigns, contacts, a reply inbox, deliverability and lead signals. Help me get my workspace sending real, good emails end to end, from Claude Code.

Read these first so you know how FirstSales works:
- Developer docs and API: https://developer.firstsales.io
- CLI: https://www.npmjs.com/package/@firstsales.io/cli
- Skills for coding agents: https://github.com/firstsalesio/firstsales-skills (read README.md and GUIDE.md)

Setup
1. Install the CLI: npm install -g @firstsales.io/cli
2. Install the FirstSales skills:
   claude plugin marketplace add firstsalesio/firstsales-skills
   claude plugin install firstsales@firstsales
3. Ask me if I already have a FirstSales account. If not, send me to https://app.firstsales.io to sign up.
4. Ask me to create an API key under Settings → API → API Keys, with only the scopes we need.
   Never ask me to paste the key into this chat. Tell me to run this in my own terminal, so the key stays hidden:
   read -rs FS_KEY && firstsales auth login --api-key "$FS_KEY"; unset FS_KEY
5. Run `firstsales whoami` and tell me which workspace and organisation we are connected to.

Then ask me about my business: what I sell, who I sell to (roles, company size, countries), my best customers, and what I use today for outbound (tools, lists, mailboxes). Walk me through:
1. Teaching FirstSales my business: website, offer, proof points and case studies in the knowledge base, so the AI writes like someone who knows the product.
2. Connecting my sending mailboxes and checking my sending domain: SPF, DKIM, DMARC and warm-up. If anything is unhealthy, tell me the exact DNS record to add.
3. Bringing in contacts: import my CSV or CRM export into a clean list, remove duplicates and bad emails, and block domains I must never email (customers, competitors, my own).
4. Building my first campaign: the right list, senders, steps and timing. Write the sequence with me, show me the drafts, and do not launch until I say yes.
5. Setting up Signals if it fits: find people engaging with LinkedIn posts about topics my buyers care about, and turn them into leads.
6. Inviting my team and giving each person the right access.

Once campaigns run, show me how to work the reply inbox from here: which replies need an answer, draft responses in my voice, and move good conversations into deals. If I use Cal.com, connect it so follow-ups can offer my booking link (not the first email).

Throughout, as you learn about my business, proactively suggest and help create:
- Reply templates for the questions and objections my prospects are likely to raise, based on my product, site and codebase if you can see them.
- Campaign ideas and segments worth testing, with the reason for each.

Safety rules:
- Show every change as a dry run (--dry-run) first and wait for my yes. Never send emails, launch campaigns or delete anything without my yes.
- Tell me before anything that spends credits, and how many.

Be opinionated. If the docs give a sensible default, just use it. Don't make me choose between five options.