Endless copy-paste
Leads, tickets, and status updates get re-keyed by hand from one app into another, all day, every day.
Automation & AI integrations · Zoho · Zapier · MCP · code
I make your disconnected tools talk — and put AI to work on the busywork.
For teams whose tools don't talk and whose AI never gets past a chat tab. I'm a hands-on engineer who wires your stack together (Zoho, Zapier, APIs, MCP, code) and puts AI on the real work: triage, routing, drafting, updates. One engineer, fixed scope, shipped in days — not quarters.
// this week I could ship you churned customer → owner pinged in Slack, save-play ticket filed new lead → enriched, routed, first reply in 60 seconds overdue invoice → chased politely until it's paid support inbox → triaged, drafts waiting every morning deal won → onboarding kicked off in every tool at once Friday 5pm → the ops digest writes itself
automation ~ live live
Stripea subscription just churned trigger
AI reads the accountpicks the right save-play
HubSpotfind the account owner
Linearopen a save-play ticket
SlackDM the owner with context
runs in ~3s · you own every step
replies in 1 business day / 12+ yrs in automation & ops / fixed scope, fixed price / you own all the code
// the problem
Sound familiar?
Most B2B SaaS teams aren't short on tools. They're short on the glue between them — and on the hours spent being that glue by hand.
Tools that don't talk
Your CRM, billing, and support desk each hold a slice of the truth — and none of them stay in sync.
AI stuck in a browser tab
You know AI could triage, draft, and summarize — but wiring it into real workflows never makes the roadmap.
No one owns it
Engineering is heads-down on the product. Ops is left holding the duct tape. The busywork just keeps growing.
// what you actually get
Less manual work. Fewer dropped balls. More of the day back.
In plain terms: your tools start doing the repetitive work themselves, and AI handles the judgment-heavy steps — with you in the loop where it counts.
Work that runs itself
Routine handoffs — new signup, churn, ticket, invoice — trigger and finish without anyone touching them.
AI on the judgment calls
Drafting replies, classifying tickets, summarizing threads, routing to the right person — reviewed by you when it matters.
One source of truth
Your tools stay in sync, so your CRM, billing, and support desk finally agree on what's true.
You own everything
Code, prompts, and docs handed over to you. No lock-in, no per-seat tax, no dependency on me to keep it running.
// under the hood
What the work actually looks like.
Three builds I actually shipped — told in the apps and the logic, not code. Tap the dots to walk each one through.
you own every line
Whatever it takes — and the code is yours.
What an MCP server signature looks like — the kind your agents connect to. We set them up (Zoho MCP, GitHub MCP, etc.), wire MCP-native platforms (Workato), or build one when you really need it.
shipped as code you keep · TypeScript · n8n · Deluge · raw APIs// hubspot-mcp/server.ts
import { Server } from "@modelcontextprotocol/sdk/server";
import { hubspot } from "./client";
const server = new Server({
name: "hubspot-mcp",
version: "0.1.0",
});
server.tool("contacts.search", async ({ query }) => {
return hubspot.contacts.search({ q: query });
});
server.tool("deals.update", async ({ id, patch }) => {
return hubspot.deals.update(id, patch);
});
server.listen(); // process
Five stages, no surprises.
Same shape every time. Audit fits inside a calendar week. Sprints and setups extend stages 3 and 4.
- 01
Brief
30-min call. What's bleeding time, what's already automated, what's politically off-limits.
~30 min - 02
Map
Async stack walkthrough. Read-only access to your tools. Identify the 3–5 highest-leverage interventions.
~2 days - 03
Build
Build in a private staging env. Daily Loom updates — you see progress every 24 hours.
1–3 weeks - 04
Ship
Production deploy. Documentation handoff. Loom walkthrough. You own everything — code, prompts, recipes.
~1 day - 05
Tune
Post-ship support window. Tweaks, bug fixes, edge cases. Optional move into Care retainer.
14–30 days
// interop
Plugs into the stack you already run.
Tool-agnostic by design — code and raw APIs, Zapier, n8n, Zoho, the major LLMs, and MCP. I meet your stack where it is instead of asking you to adopt mine, and you own every integration I build.
A tool with an API but no off-the-shelf connector? I read the docs and write the bridge myself. Going deep on one platform? See the n8n, Zapier, and Zoho tracks.
// field reports
What's been shipped in the lab.
Lab builds — projects shipped to prove patterns, not paid client engagements (yet). Tap a row to expand. Live walkthroughs available on request — much faster than a static page.
FR-01 · · v0.1 · lab CRM Sync Dashboard
Zoho ↔ HubSpot field-mapping with webhook-driven sync and telemetry. Currently a controlled-data demo; real OAuth + live API rebuild is the next ship.
FR-02 · · shipped AI-Driven Support Chatbot
First-line CS automation on Crisp and Zopim. ChatGPT + Gemini for intent detection, drafting, and confident escalation to humans when the model isn't sure.
// missions
Productized missions — priced on a call, not a page.
The only upfront cost is 30 minutes. Send a short brief, we talk for 30 minutes — free — and every mission ships with a fixed scope, a fixed timeline, and a number agreed before work starts. Start small with a Spark or an Audit; most teams grow into a Sprint, a Build, or the full Stack. See the whole ladder →
30 min intro call
Automation Spark
One workflow, one integration, or one broken thing made reliable. The smallest way in.
- 1 automation or fix, built on your stack
- Error handling + a failure alert
- Loom walkthrough + 7-day support
30 min intro call
Workflow Sprint
Build 2–3 production workflows on n8n or Zapier, with one AI-powered step.
- 2–3 production workflows (n8n or Zapier)
- One AI step — triage, routing, drafting, extraction
- Docs + Loom + 14-day post-ship support
30 min intro call
Custom Build
A custom internal app, an AI agent / MCP integration, or a platform migration — shipped to production.
- A custom app, AI agent, MCP setup, or migration
- Observability + 30-day support + one iteration round
- You own all the code — no lock-in
// FAQ
Things people ask.
Where are you based and what timezone do you work in?
Based in India (IST). Day-to-day operating window aligned to 9 AM EST onwards — meaningful overlap with US East Coast and full overlap with US Pacific evening. UK clients catch me through their morning. Async-first; calls fit your calendar, not mine.
How does billing work?
Spark and Audit are paid up front. Sprints and builds split 50/50 — half on signing, half on delivery; larger Stack engagements are billed by milestone. Care retainers are monthly, 3-month minimum then monthly cancel. Payment methods: Wise, AirTM, PayPal, or bank wire — whatever your finance team prefers. We confirm the right rail at signing. Invoiced in USD.
NDAs? IP? Who owns the code?
NDAs welcome — I sign yours, or use a clean mutual NDA on request. You own the work product end-to-end: code, prompts, recipes, documentation. I keep no proprietary IP claim on client builds. Open-source dependencies stay under their licenses.
What's explicitly out of scope?
I don't build production SaaS apps, mobile apps, or marketing sites. I don't run paid ads or manage social. I don't take on roles that require being on-call 24/7. Anything outside that — automation, AI agents, integrations, internal tooling — is fair game.
Can I pause or cancel the Care retainer?
3-month minimum to start (so we both have runway to do real work). After that, you can pause for up to 60 days no questions asked, or cancel with 30 days notice. Unused hours don't roll forward — the retainer buys ongoing capacity, not a banking arrangement.
Why one engineer instead of an agency?
Because agencies introduce account managers and PMs between you and the person actually writing the code. With us, the engineer takes the brief, designs the system, ships the build, and answers the support thread. Twelve-plus years of operating experience — the kind of background that sees the political angles, not just the technical ones.
// contact
Send me a brief.
Fastest path: tell me your stack and the workflow that's eating hours. Reply within 1 business day with a recommendation — and times for a free 30-minute scoping call, where the scope and the number are agreed before any work starts. Or an honest "not the right fit."
// 60-second idea
Not sure where to start? Tell me your stack — I'll point you at the quickest win.