rohitg00

Pro Workflow

A system for working with AI coding agents that compounds across sessions. Distilled from running pro-workflow in production for several months: shipped initially as a Twitter thread distillation, rewritten three times since, currently 24 skills, 8 agents, 21 commands, 29 hook scripts across 24 hook events, with a SQLite-backed learning store underneath.

This document is what we wish we'd had on day one. Not the marketing version. The honest version: what worked, what we got wrong, who we learned from, and why the system today looks nothing like the system we started with.

The foundation is Andrej Karpathy's observation that 80% of his code is written by AI and 20% is spent reviewing and correcting it. The ratio is correct. The interesting question is what happens to the 20%, and the boring answer most workflows ship is "nothing." Corrections come in, mistakes get patched, the next session starts

rohitg00

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

rohitg00

🔨 Building Docker Image
[#9] COPY . .
[#9] DONE (0.7s)

📦 Exporting to Image
- Exporting layers (2.1s)
- Writing image sha256:957405d9ec2ff6a5014705b07809593ed17ea8a6ec4c09433f262f51e42eec6b
- Naming to europe-west1-docker.pkg.dev/kinsta-app-hosting/kc-apps/97ad2f04-172c-4a35-8dee-933c1134f27c/ai-food-assistant-z11yi:eb339d69-56d2-4a64-9a64-0809d752aeb4
✅ Docker image built successfully

rohitg00

From centos:latest
run yum install wget -y
run yum install net-tools -y


run wget -O /etc/yum.repos.d/jenkins.repo  https://pkg.jenkins.io/redhat-stable/jenkins.repo
run rpm --import https://pkg.jenkins.io/redhat-stable/jenkins.io.key
run yum upgrade -y
run yum install java -y
run yum install jenkins -y

rohitg00

provider "aws" {
  region                  = "ap-south-1"
  profile                  = "EKS"
}


resource "aws_iam_role" "eks_cluster" {
  name = "ViRocluster"

  assume_role_policy = <<POLICY

rohitg00

apiVersion: eksctl.io/v1alpha5
kind: ClusterConfig
metadata:
  name: ViRocluster
  region: ap-south-1
nodeGroups:
   - name: ng1
     desiredCapacity: 2
     instanceType: t2.micro
     ssh:

rohitg00

#Github gist by Rohit Ghumare to augment and create replicas of images  
[
  {
    "dst": "$data",
    "src": [
      "Dataset/*"
    ],
    "action": "data",
    "settings": {
      "classes_mapping": "default"

rohitg00

//Describing Provider
provider "aws" {
  region  = "ap-south-1"
  profile = "rg"
}

//Creating Variable for AMI_ID
variable "ami_id" {
  type    = string
  default = "ami-0447a12f28fddb066"

rohitg00

  //Creating EBS Snapshot
resource "aws_ebs_snapshot" "ebs_snapshot" {
  volume_id   = "${aws_ebs_volume.web-vol.id}"
  description = "Snapshot of our EBS volume"
  
  tags = {
    env = "Production"
  }
  depends_on = [
    aws_volume_attachment.ebs_att

rohitg00

resource "null_resource" "remote1" {
  
  depends_on = [ aws_instance.web, ]
  //Executing Commands to initiate WebServer in Instance Over SSH 
  provisioner "remote-exec" {
    connection {
      agent       = "false"
      type        = "ssh"
      user        = "ec2-user"
      private_key = "${tls_private_key.tls_key.private_key_pem}"