5 Python Scripts That Run My Entire Consulting Business

#python #productivity #ai #consulting

I run a solo AI consulting practice. My total tooling cost is $47/month. Here are the 5 Python scripts that keep everything running.

Script 1: The Email Classifier

Reads every email, categorizes it, drafts a response.

import anthropic
import imaplib
import email

client = anthropic.Anthropic()

CATEGORIES = {
    "urgent_client": "Respond within 1 hour",
    "routine_client": "Respond within 24 hours",
    "prospect": "Route to sales pipeline",
    "vendor": "Auto-file, respond if action needed",
    "newsletter": "Archive",
    "spam": "Delete"
}

def classify_email(subject: str, body: str, sender: str) -> dict:
    response = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=512,
        messages=[{
            "role": "user",
            "content": f"""Classify this email and draft a response.

From: {sender}
Subject: {subject}
Body: {body[:1000]}

Return JSON:
- category: one of {list(CATEGORIES.keys())}
- priority: 1-5 (1=highest)
- summary: one sentence
- draft_response: appropriate reply (or null if no response needed)
- action_items: list of tasks to create"""
        }]
    )
    return response

Saves: 4.2 hours/week

Script 2: The Meeting Summarizer

Records → transcribes → structures → emails the summary.

import whisper
import anthropic

model = whisper.load_model("base")
client = anthropic.Anthropic()

def process_meeting(audio_path: str) -> dict:
    # Transcribe
    result = model.transcribe(audio_path)
    transcript = result["text"]

    # Summarize
    summary = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=2048,
        messages=[{
            "role": "user",
            "content": f"""Create a structured meeting summary:

{transcript}

Format:
## Key Decisions
## Action Items (with owner and deadline)
## Open Questions
## Next Meeting Agenda Items"""
        }]
    )
    return summary

Saves: 30-45 min per meeting (I have ~8/week)

Script 3: The Report Generator

Pulls data from 5 sources, generates a formatted client report.

def generate_weekly_report(client_id: str) -> str:
    # Pull data from various sources
    analytics = fetch_google_analytics(client_id)
    social = fetch_social_metrics(client_id)
    email_stats = fetch_email_metrics(client_id)

    report = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=4096,
        messages=[{
            "role": "user",
            "content": f"""Generate a professional weekly report:

Analytics: {analytics}
Social Media: {social}
Email Marketing: {email_stats}

Include: executive summary, key metrics (with week-over-week 
comparison), insights, recommendations for next week.
Format as clean markdown."""
        }]
    )
    return report

Saves: 5.1 hours/week across all clients

Script 4: The Content Multiplier

One article → 20+ pieces of content across platforms.

def multiply_content(article: str) -> dict:
    output = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=8000,
        messages=[{
            "role": "user",
            "content": f"""From this article, create:
1. 5 LinkedIn posts (each with a different angle/hook)
2. 3 Twitter/X threads (5-8 tweets each)
3. 10 short social captions
4. 2 email newsletter sections
5. 5 SEO-optimized meta descriptions

Article:
{article}

Adapt voice and format for each platform."""
        }]
    )
    return output

Saves: 6.1 hours/week

Script 5: The Proposal Generator

Client brief → customized proposal with pricing.

def generate_proposal(brief: str, client_research: dict) -> str:
    proposal = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=8000,
        messages=[{
            "role": "user",
            "content": f"""Generate a consulting proposal:

Client Brief: {brief}
Company Research: {client_research}

Structure:
1. Executive Summary (personalized to their situation)
2. Problem Analysis (reference their specific pain points)
3. Proposed Solution (3 tiers: Good/Better/Best)
4. Timeline
5. Investment (value-based pricing)
6. Expected ROI (with calculations)
7. About Us
8. Next Steps

Make it specific and data-driven, not generic."""
        }]
    )
    return proposal

Saves: 2+ hours per proposal, improved win rate from 23% to 41%

Total Impact

Script	Time Saved/Week	Annual Value
Email Classifier	4.2 hrs	$8,700
Meeting Summarizer	5.0 hrs	$10,400
Report Generator	5.1 hrs	$10,600
Content Multiplier	6.1 hrs	$12,700
Proposal Generator	3.5 hrs	$7,300
Total	23.9 hrs	$49,700