Build an AI Content Factory · 50 min · Python · Anthropic Claude API

Build the Content Generators

Six generators sharing one Voice Profile, each enforcing a different platform's actual constraints — not six copies of the same generic prompt with a label swapped.

Hiring signal: This is the actual craft in a content pipeline: writing prompts that reliably produce platform-correct, voice-consistent output. Anyone can call an LLM API; fewer people can make it reliably sound like a specific person across 6 different formats.

What you will learn

Write a platform-specific prompt that enforces real format constraints (thread structure, character limits)
Include the Voice Profile as a few-shot fixture in every generator
Choose model and temperature per generator based on the format's needs

Introduction

Clean input, a Voice Profile ready to go — today you build the actual generators. Six of them, one at a time, each tested against a real input before you move to the next: blog post, Twitter/X thread, LinkedIn post, newsletter section, YouTube script outline, and email.

The shared shape every generator uses

def generate_twitter_thread(source_text: str, voice_profile: str) -> str:
    prompt = f"""{voice_profile}

Using the writing style shown in the examples above, write a 6-8 tweet Twitter/X
thread based on this source material:

{source_text}

Constraints:
- Each tweet under 280 characters
- First tweet must hook attention without needing the thread's context
- Number each tweet (1/, 2/, etc.)
- End with a summary or call-to-action tweet
"""
    return call_claude(prompt, model="claude-haiku-4-5-20251001", temperature=0.7)

Three things every generator in this lesson will reuse: the Voice Profile goes FIRST in the prompt (models weight earlier context differently, and you want voice established before the model starts drafting, not bolted on after), the platform constraints are an explicit bulleted list (not folded into prose, which models follow less reliably), and the model/temperature are chosen per format -- a fast, cheaper model at higher temperature for something short and casual like a tweet thread, versus what you'll use for the longer blog-post generator below.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers Constraints that actually get enforced vs. constraints that don't, Model choice: not every generator needs the same model, What You're Building — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.