Documentation · Messaging

A signal is only useful if the message actually uses it.

Good research means nothing if the message that follows reads like every other cold email. Here is how Deligatr turns a real trigger into a message a prospect actually wants to answer.

Book a Free Strategy Call All Documentation

Quick answer

Deligatr writes outreach using AI grounded in the specific signal that triggered contact, not a generic template. Messages are generated within defined constraints, no performance claims, no guarantees, no generic sales language, reviewed and approved by your team, and refined weekly based on what actually gets replies.

From signal to sent message

Four steps, always in this order

Signal becomes context

The trigger identified during research, a funding round, a permit filing, a growth signal, is passed into the message generation process as grounding context, not a generic prompt.

AI drafts with constraints

Messages are generated within a defined set of constraints: no performance claims, no guarantees, no generic sales language, and a tone matched to your industry and brand.

Human review sets direction

Your team reviews and approves messaging direction during onboarding. This is not a one-time approval, adjustments can be requested at any point.

Performance shapes future messaging

Reply data feeds back into what gets sent next. Messages and angles that perform are scaled, ones that do not are revised or retired.

The standard, in practice

What every message must and must not do

Always

Never

Reference a specific, real, current trigger

Open with a generic capability statement

Ask one clear, low-friction question

Ask for a meeting in the first message

Keep messages under roughly 100 words

Write a long feature-by-feature pitch

Match the tone your industry expects

Use identical phrasing across every industry

State what we do plainly if asked

Use vague, buzzword-heavy language

Signal to message, side by side

What this looks like in practice

The signal

A construction firm's ideal client, a regional developer, files a new land acquisition permit in a market the firm operates in.

The message

“Hi [First Name], saw the filing on the [Neighborhood] parcel. We recently completed a project nearby with a similar density constraint, might be a useful reference point. Worth a quick call before you lock in your design team?”

Questions about messaging

Does a human ever see the messages before they send?

Yes. Messaging direction and tone are reviewed and approved by your team during onboarding, and campaign performance is reviewed weekly. AI generates and personalises messages at scale, a person sets and checks the direction.

How is this different from a mail-merge template with a first name inserted?

A mail-merge changes one variable in an otherwise identical message. AI personalisation here references the actual signal that triggered contact, a funding event, a specific portfolio project, a compliance deadline, so the substance of the message changes, not just the greeting.

Can we set rules about language the AI should never use?

Yes. Every engagement excludes certain language by default, no guarantees, no performance claims, no false urgency, and additional restrictions can be added based on your compliance needs or brand voice preferences.

Does the AI ever make things up about a prospect?

Messages are grounded in verified enrichment data and confirmed signals, not invented details. If a signal cannot be confirmed, it is not referenced in the message.

How does messaging differ across industries?

Consultative tone for accounting and financial services, portfolio-led framing for architecture and design, business-to-business framing for law firms, and so on. The AI is directed by the ICP workshop findings and industry context, not one universal template.

Can we review and change the messaging approach after launch?

Yes, at any point. Weekly reviews are a natural point to request changes, but you can raise a messaging concern whenever it comes up.

See sample messaging for your industry

Book a free strategy call and we will show you real message examples built for your ICP.

Book a Free Strategy Call See Pricing