DEV Community: Amrendra N Mishra

Production GenAI: Hallucination Guardrails and PII Redaction

Amrendra N Mishra — Sat, 12 Sep 2026 05:20:13 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Smart File Organizer: AI Watches Your Downloads Folder

Amrendra N Mishra — Fri, 11 Sep 2026 05:34:19 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

LangGraph Practical Guide: When to Use It Over LangChain

Amrendra N Mishra — Thu, 10 Sep 2026 05:31:22 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

GitHub Actions for Free 24/7 AI Automation

Amrendra N Mishra — Wed, 09 Sep 2026 05:40:38 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

Build a Local ChatGPT UI with Zero API Costs

Amrendra N Mishra — Tue, 08 Sep 2026 05:33:35 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

AI Code Reviewer: Never Ship Bugs Again

Amrendra N Mishra — Mon, 07 Sep 2026 05:37:39 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

From SDE to VP in 12 Years: What Actually Works

Amrendra N Mishra — Sun, 06 Sep 2026 05:27:14 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

System Design: Status Page for 400M Users

Amrendra N Mishra — Sat, 05 Sep 2026 05:12:52 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

DynamoDB Design Lessons from 2M Daily Transactions

Amrendra N Mishra — Fri, 04 Sep 2026 05:24:14 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Java 21 Quarkus AWS Lambda: My Production Serverless Stack

Amrendra N Mishra — Thu, 03 Sep 2026 05:26:00 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev

MCP Protocol: The USB-C Standard for AI Tools

Amrendra N Mishra — Wed, 02 Sep 2026 05:23:08 +0000

Why Automate Content Creation

Creating content manually for 9 channels would take 8+ hours daily. I have a full-time job as VP at JPMorgan. The math doesnt work.

The Pipeline

Trending Topic CSV
       ↓
  AI Script (Ollama/Gemini)
       ↓
  Google Cloud TTS (Voice)
       ↓
  Pexels Images + MoviePy Video
       ↓
  YouTube API Upload

Scheduling with Mac LaunchAgents

<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.gyaaninfive.youtube</string>
  <key>ProgramArguments</key>
  <array>
    <string>/usr/bin/python3</string>
    <string>/path/to/upload.py</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key><integer>18</integer>
    <key>Minute</key><integer>15</integer>
  </dict>
</dict>
</plist>

One plist per channel. Runs at the exact scheduled time.

Total Monthly Cost

Google Cloud TTS: Free (4M chars/month)
Pexels API: Free
YouTube API: Free
Ollama: Free (local)

Total: ₹0/month

Full code on GitHub

9 channels. Daily uploads. Zero manual work.

Voice Commander: Control Your Mac with Hey Jarvis

Amrendra N Mishra — Tue, 01 Sep 2026 05:58:35 +0000

The Problem With Cloud AI

Every token costs money. Every API call adds up. And your data goes to their servers.

The Local Alternative

brew install ollama
ollama pull llama3.2
ollama serve

Now you have a GPT-4 level model running on your MacBook. Free. Private. Fast.

Real Code Example

import requests

def ask_local_ai(question):
    r = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3.2", "prompt": question, "stream": False}
    )
    return r.json()["response"]

# Works immediately, no API key needed
answer = ask_local_ai("Explain Docker in one paragraph")
print(answer)

Available Models

Model	Size	Best For
llama3.2	2GB	General use
codellama	4GB	Code tasks
mistral	4.4GB	Fast reasoning
phi3	2.2GB	Lightweight tasks
gemma2	5.4GB	Complex reasoning

What You Can Build

RAG systems for your documents
Voice assistants that work offline
Code reviewers on every git commit
Content generators at zero cost
Personal AI that remembers you

My Setup

I built 45 tools using this stack. All free. All local. All open source.

github.com/amrendramishra/ai-tools

VP at JPMorgan Chase. Building AI tools at amrendranmishra.dev