Pular para o conteúdo
NovoVeja como
Melhoria

Faster replies with sharper, to-the-point AI first emails

Your campaign first emails now read tighter and land on one clear ask, no more filler getting in the way of a reply.

Your AI-drafted first emails just got a rewrite in how they're written, not just what they say. The writer behind your campaign's opening email now favors sharper openers and a single, obvious ask over the padded, generic-sounding drafts that used to need heavy editing before they felt sendable.

What changed

When you generate or review a first-email draft in your campaign flow, you'll notice three differences right away:

  • Sharper opening lines. The first sentence gets to a real, specific point instead of a throat-clearing intro. Less "I hope this finds you well" energy, more "here's why I'm writing." The opener now does actual work: it references something concrete about the prospect's situation rather than opening with a generic pleasantry that could apply to any recipient on any list.
  • One clear call to action. Every draft now ends on a single, unambiguous ask, not two or three competing asks buried in the same paragraph that leave the reader unsure what to do next. Previously a draft might close with "let me know if you're interested, or happy to send more info, or we could hop on a call" — three exits instead of one door. Now it closes on the one action that matters for that campaign.
  • Less filler. Padding, throat-clearing, and generic AI-sounding phrasing are trimmed out. The draft reads more like something a real person wrote with a point to make, and less like a template stretched to fill space. Sentences that existed only to sound thorough or polite, without adding information, are gone.

Nothing about where you generate drafts or how your sequences are structured has changed. This is purely a quality upgrade to the copy itself — the campaign flow, the review step, and everything downstream of the first email are untouched.

How to use it

You don't need to configure anything — this applies automatically to new first-email drafts. That said, here's how to get the most out of it when you review a draft in your campaign:

  1. Read the opening line first. It should make a specific, relevant point about the prospect or their situation, not a generic greeting. If it still feels vague, that's a good signal to tighten your campaign's input context (company details, pain points, etc.) rather than a sign the writer needs manual rescue.
  2. Check for exactly one ask. Scan the closing lines. You should find a single, clear next step — book a call, reply with a time, confirm interest. If you want a different ask, edit it directly; the draft is still fully editable before you approve it for send.
  3. Scan for anything that still feels padded. Drafts should be noticeably shorter and more direct. If a paragraph still feels like filler, trim it — this is a good baseline to build from, not a final draft you have to accept as-is.
  4. Treat it as your new floor, not your ceiling. The draft arriving tighter means less time cutting fat and more time on the parts only you can do well — matching tone to a specific account, adding a detail from recent research, or adjusting the ask to where that prospect sits in their buying process.

As always, review every draft before your campaign sends it. This update makes the starting point stronger — it doesn't replace your judgment on tone, personalization, or fit for a specific prospect.

Why it matters

Cold email replies come down to one thing: does the recipient immediately understand why you're writing and what you want them to do. Long, padded emails with multiple asks make a prospect do the work of figuring out what actually matters, and most won't bother — they'll skim, lose the thread, and archive. Concise, concrete emails with a single clear ask respect the reader's time and make the next step obvious — there's no ambiguity about what happens if they reply.

Better first-email quality is the top of your funnel — it's the email that decides whether a prospect reads on, replies, or archives without a second thought. Sharper opening lines and a single clear CTA feed straight into your reply rate, and higher reply rates mean more conversations that turn into booked meetings. A cleaner first touch also means less back-and-forth spent clarifying what you're actually asking for, so the conversations that do start move toward a meeting faster.

This is a foundational improvement: every sequence you run benefits from a stronger first touch, without you changing anything about how you build or send campaigns. The gains compound across every campaign you launch from here, not just the next one.

Todas as novidades

Prospecção que continua quando você desconecta.Leads, emails, follow-ups e respostas, resolvidos.

Conecte caixas ilimitadas e deixe os agentes de IA encontrarem leads, escreverem cada email e fazerem follow-up. Ou envie seus próprios modelos no modo manual. A partir de $29/mês.

$1 por 3 dias · Cancele quando quiser · Sem contrato

Instalar com IA

Seu agente de código configura a CLI e as skills do FirstSales para você.

Prompt para 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.