Pular para o conteúdo
NovoVeja como
Correção

Your formatting rules stop contradicting the drafter

A campaign instructed to avoid bullet points could still receive a bulleted draft. Formatting rules now constrain the layout the drafter chooses, so the two can't disagree.

If your campaign instructions say no bullet points, your drafts won't get a bulleted layout anymore. The formatting rule and the drafter's own layout choices used to be able to disagree with each other.

What changed

Campaign instructions can include formatting preferences, for example telling the AI not to use bullet points in your emails, because bullets can read as impersonal or overly sales-like for certain audiences. Previously, the layout the drafter chose for a given email could conflict with that instruction. A campaign that explicitly banned bullets could still receive a draft formatted with them, because the formatting rule and the layout decision the drafter made weren't fully connected to each other; the drafter could satisfy the wording of your instruction while still choosing a layout that contradicted it.

That's fixed. A campaign instruction against bullets, or any other formatting rule you've set, now constrains the layout the drafter is allowed to choose in the first place, so the two can't end up contradicting each other. The formatting rule is now a shared standard, not advice the drafter tries to follow; it's a constraint on what layouts are available to choose from at all.

How to use it

Set your formatting preference in campaign instructions or the Learning tab the way you normally would, whether that's avoiding bullet points, preferring short paragraphs, or another layout preference specific to your audience. New drafts will respect it in both the wording and the layout now, not just the wording.

If you have an existing campaign where drafts were previously ignoring a formatting rule you'd set, it's worth checking a new draft after this fix to confirm the layout now matches what you originally asked for. You shouldn't need to re-enter the instruction; the fix applies to how existing instructions are enforced, not to the instructions themselves.

Why it matters

A formatting rule you set exists because you know your audience. Bullets can look impersonal or overly sales-y for some prospects, where a plain paragraph reads as more like something a person actually sat down and wrote to them specifically. An instruction that gets silently overridden by the drafter's own formatting choice means you can't fully trust that what you asked for is actually what goes out, which undercuts the reason you set the rule in the first place, and it's the kind of inconsistency that's easy to miss until a prospect mentions it or you happen to spot a bulleted draft in a campaign you thought had that turned off.

Making the formatting rule a real constraint rather than a suggestion the drafter tries to honor closes that gap. Once you've set the rule, it holds, across every draft in that campaign, not just most of them.

This kind of conflict is also the sort of bug that's hard to catch just by reading a single draft in isolation. One bulleted email in an otherwise-compliant campaign can look like an isolated exception rather than a sign that the rule and the layout logic weren't actually connected. It typically surfaces only once you've reviewed enough drafts from the same campaign to notice the pattern, or once a prospect points it out, by which point several bulleted emails may have already gone out under a rule that was supposed to prevent exactly that.

Setting different rules per campaign

Formatting rules work the same way as any other instruction: set them once in campaign instructions or the Learning tab, and they apply to every draft generated after that point. There's no separate formatting settings screen to manage; it's part of the same instruction set you're already using to control tone, content, and voice.

If you maintain formatting rules across multiple campaigns for different audiences, for example allowing bullets for a more technical audience but avoiding them for an executive one, each campaign's instructions are independent, so you can set different rules per campaign without one affecting the other.

The principle behind the fix

Layout is part of how an email reads before a prospect even gets to the words. A wall of bullet points signals a sales pitch; a few well-structured paragraphs signal a note from a person. Getting that signal wrong for a specific audience undercuts the rest of the work you put into Describe and Teach to make the email sound right, since the visual shape of the email is often the first thing a reader registers, even before the first sentence.

This fix also reflects a broader principle worth stating plainly: an instruction you set should behave as a hard constraint wherever the product can enforce it as one, not as a preference the system tries to respect but can still override when its own logic points elsewhere. Formatting rules are a clean example, since layout is something the drafter chooses from a defined set of options rather than generating freely the way it does with wording, which makes it possible to enforce the rule directly on that choice instead of relying on the drafter to remember and apply it correctly every time.

If you've never explicitly set a formatting instruction, this fix has nothing to change for you; the drafter's default layout choices are unaffected. It only matters once you've told it to avoid a specific layout, at which point that instruction now behaves as a rule rather than a suggestion the drafter can talk itself out of.

The same principle extends to any layout preference you set, not just a ban on bullet points specifically. If you've asked for short paragraphs, a particular greeting style, or any other structural choice, the fix applies to that constraint the same way, since the underlying issue was in how formatting instructions connected to layout selection generally, not in one specific rule. You don't need to reapply or restate an existing rule for it to be enforced correctly; the fix changes how existing instructions are honored going forward, not what instructions you have on file.

Availability

This applies to all campaigns with a formatting instruction set in campaign instructions or the Learning tab.

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.