TOOLING & STACK·7 min read

Every AI builder has a demo stack and a real stack

The AI Tools I Actually Use to Ship Products (Not the Ones I Demo)

Every AI builder has a demo stack and a real stack. Here's my real one — the tools that survived 1,600+ source files and 4 production systems.

For AI Builders, Full-Stack Developers, Technical Founders

Key Takeaways

  • 4 production AI systems running on ~$100/month total infrastructure cost
  • PostgreSQL + pgvector replaces 3 separate services (vector DB, cache, queue)
  • Smart LLM routing across providers cuts API costs by 75%+
Sivakumar Chandrasekaran

Sivakumar Chandrasekaran

AI Builder & Banking Expert · Abu Dhabi, UAE

Share

There's a massive gap between the tools people demo on Twitter and the tools that survive production. After shipping 4 AI products while working a full-time banking job (15-20 hours/week available), I've become ruthless about what stays in my stack.

If it doesn't save me measurable time, it's gone. Here's what survived.

The Complete Stack (March 2026)

My Production AI Stack

Development

  • IDE: Cursor + Claude Code (primary)
  • Language: TypeScript (90%), Python (10%)
  • Framework: Next.js 16 (frontend + API)
  • Backend: Node.js + Express (when needed)
  • Version control: Git + GitHub

AI / LLM

  • Primary: Claude 3.5 Sonnet (complex reasoning)
  • Fast: GPT-4o-mini (extraction, classification)
  • Grounded: Gemini (real-time web data)
  • Embeddings: text-embedding-3-large (OpenAI)
  • Gateway: Custom multi-provider router

Data

  • Database: PostgreSQL 15 (Cloud SQL)
  • Vector: pgvector (same Postgres instance)
  • Cache: Redis (query dedup, sessions)
  • Queue: GCP Pub/Sub (async jobs)

Infrastructure

  • Compute: GCP Cloud Run (containers, auto-scale)
  • Container: Docker (multi-stage builds)
  • DNS/CDN: Cloudflare
  • Email: Resend (transactional)
  • Monitoring: Custom + Cloud Run logs

Monthly Cost (all 4 products)

ServiceCost
Cloud Run~$15–25
Cloud SQL~$30–40
LLM APIs~$20–50 (depends on usage)
Redis~$10
Domains~$3
Total~$80–130/month

$80-130/month for 4 production AI systems. Not bad.

Why Each Tool Won Its Slot

Claude Code — The 5x Multiplier

This is the single biggest force multiplier. It's not a chatbot — it's an AI agent that reads your entire codebase, understands architecture patterns, and implements changes across multiple files consistently.

What it actually does for me:

TaskWithout Claude CodeWith Claude Code
New API endpoint45–60 min10–15 min
Database migration + types30–45 min5–10 min
React component with API integration60–90 min15–25 min
Total for a typical feature3–4 hours45–75 min

Net savings: ~2.5 hours per feature. At 3–4 features/week: 8–10 hours saved. That's basically my entire available work week.

The skill isn't prompting. It's architecture judgment, context curation, and code review discipline. I wrote about this in detail in my Claude Code article.

PostgreSQL + pgvector — One Database to Rule Them All

I run everything on PostgreSQL. App data, vector embeddings, sessions, job queues — all in one database.

My Database Philosophy

What most people doWhat I do
App dataPostgreSQLPostgreSQL
VectorsPineconePostgreSQL (pgvector)
CacheRedisPostgreSQL (+ Redis for hot cache only)
QueueRabbitMQPostgreSQL (+ Pub/Sub for async only)
SessionsSeparate storePostgreSQL
Services41 (+ 2 optional)
Failure points41
Bills41
Ops complexityHIGHLOW

pgvector handles my RAG needs perfectly. HNSW indexes give sub-100ms similarity search on datasets under 10M vectors. That covers 99% of enterprise use cases.

Why not Pinecone? I already pay for Cloud SQL. pgvector is a Postgres extension — zero additional cost. And I don't need another vendor's dashboard, another API key, another point of failure.

Multi-Provider LLM — The Right Tool Per Job

Provider loyalty is expensive. Here's my actual routing logic:

TaskProviderWhy
Complex reasoningClaude 3.5 SonnetBest instruction-following
Simple extractionGPT-4o-mini10x cheaper, fast enough
Real-time web dataGeminiNative Google Search grounding
EmbeddingsOpenAIBest quality/cost ratio
Voice transcriptionWhisperBest accuracy

Cost impact:

ApproachMonthly Cost
Claude for everything~$200/month
With smart routing~$30–50/month
Savings75%+

GCP Cloud Run — The Underrated Platform

Cloud Run is what I recommend to anyone running side projects or early-stage products. Here's why:

Cloud Run vs Alternatives

FeatureCloud RunVercelAWS Lambda
PricingPer-requestPer-requestPer-request
Idle cost$0$0*$0
ContainerFull DockerServerlessServerless
BackgroundYes (workers)NoStep Functions
WebSocketYesLimitedAPI Gateway
Custom domainYesYesComplex
Deploy speed~3 min~30 sec~2 min
Lock-inLowHighVery High

* Vercel gets expensive fast with API-heavy apps (bandwidth + function invocations add up)

I deploy a Docker container and Cloud Run handles scaling, SSL, and custom domains. My side projects cost under $20/month to run. When Premier Radar gets real traffic, Cloud Run auto-scales — I don't need to change anything.

What I Stopped Using (And Why)

Removed ToolReason
LangChainToo much abstraction for what it does. My RAG pipeline is ~200 lines of TypeScript. Cleaner, debuggable, no dependency bloat.
PineconeUnnecessary with pgvector. One less vendor.
Vercel (for API apps)Cost model doesn't work for API-heavy projects. $20/month became $80/month quickly.
Jupyter notebooks (prod)Great for exploration. Terrible for production. Everything goes into proper TS/Python modules.
MongoDBSwitched to PostgreSQL. Relational + vector in one database beats two separate systems.
SupabaseGood product, but I want full Postgres control. Cloud SQL gives me that.

The Principle Behind It All

Every tool I cut follows the same logic:

Decision Framework

QuestionIf YESIf NO
Does this tool solve a problem I actually have?Continue belowRemove it
Can I solve this with a tool I already use?Use the existing toolContinue below
Is the added complexity worth the benefit?Add the toolBuild a simple alternative (~200 lines max)

Most developers do the opposite: they start with tools and look for problems to solve. I start with problems and find the simplest tool that solves them.

After shipping 4 production AI systems on ~$100/month, I'm pretty confident this approach works.

Ready to move AI from pilot to production?

15 minutes to diagnose what's blocking your AI initiative. No pitch — just a conversation.

Book a 15-min diagnostic call

How did this land?

Sivakumar

Ask about this article

AI-powered — answers based on this article + Sivakumar's expertise

Stay ahead

Get the next insight before it's published

One email when a new article drops. AI strategy, engineering, and banking — from someone who does all three. No spam.

AI toolsdeveloper toolsClaude Codeproductivityshipping
Share
Sivakumar Chandrasekaran

Written by Sivakumar Chandrasekaran

20 years across technology delivery and banking. Building AI products that work in regulated industries. Based in Abu Dhabi.