HomeBlogTrafficPrompting a model to write comments people actually read

Prompting a model to write comments people actually read

Читать по-русски

Bad comments are almost always a bad brief rather than a model limitation. What the instruction has to contain.

Prompting a model to write comments people actually read

A model writes exactly what it was asked for. Comments that read as filler are nearly always the product of a thin instruction rather than of the model's ceiling.

What the brief must contain

Who is speaking

Not "an expert" — a specific person with a specific occupation and a reason to be reading this channel. Vagueness here produces the generic voice everyone recognises.

What counts as a good comment

Add a fact, an experience, a correction or a question that moves the thread. State it explicitly, because the default behaviour is agreeable summary.

What is banned

Praise without content, restating the post, mentioning your product, links, greetings. The prohibition list does more work than the instruction list — why moderators delete comments.

Length

Two or three sentences. Without a limit the model writes an essay, and long comments under short posts read as an attempt to hijack attention.

Language and register

Match the post. A formal comment under a casual post is as conspicuous as the reverse.

Variation is a requirement, not a nicety

Identical constructions across accounts are the clearest automation signal there is. Ask for different openings and forbid recurring phrases explicitly — the account fingerprint.

Test before scale

Generate thirty comments for real posts and read them as a moderator would. Anything you would delete, the moderator will — commenting without a ban.

What the brief cannot fix

A wrong channel list. A perfect comment in a channel your audience does not read returns nothing — how many channels you need.

How Neurogram does this

Everything above is manual work that runs into the number of hours in a day. Neurogram does it on your own accounts and without you: it collects channels and audiences, writes comments and replies with a language model, and keeps limits and quiet hours so the accounts survive. See pricing or look at your case.

Topic: Traffic

More on this topic: The tool for this

Read next

Generated or template comments

Comparing prewritten templates with generation on cost, response rate and why identical text is the clearest signal to filters.

When AI comments come out off topic

Why a model writes generic filler instead of answering the post, and the three prompt changes that fix it fastest.

Why a moderator deletes your comment, and what survives

What reads as advertising even without a link, what gets removed automatically, and the one test that predicts whether a comment stays.

Ready to put this to work?

Neurogram automates parsing, commenting and DM conversations on Telegram. Three days free — no card required.

Try it free