I started Aratavan because most "AI agent" projects don't ship.

I've been building production software for twenty years. I founded Aratavan in September 2017, and in October 2025 I started running it full-time as an AI agent studio. That makes the agent practice new, and I'd rather say that plainly than dress it up with numbers I don't have yet. You won't find client logos or testimonials here for now. What you will find: an engineer who has shipped a lot of software, and who will be the one on your scope call, writing your agent, and answering your messages.

Aratavan, in plain terms

Aratavan is a founder-led company that builds sales and marketing AI for small and mid-sized businesses. It offers ready-made tools, starting with Sella, an AI marketing brief service for Shopify and D2C stores; answer engine optimisation (AEO), which helps a business get cited in ChatGPT, Gemini, Perplexity and Google AI answers; and custom AI agents built into a client’s existing CRM or ad tools for a fixed price and a fixed delivery date agreed in writing before work begins. Aratavan was founded in September 2017 by Saravanan Periyasamy and has focused on AI agents since October 2025.

The two ways to buy are Sella and a custom build.

Where I come from

I started as a software engineer at Mphasis and then Nokia, writing core Symbian system software in C++. From there I moved toward product and leadership: product management at maxHeap Technologies, VP of Engineering at PropGod, where we took a real estate platform from nothing to a funded MVP in under six months, and Director and Technical Architect at Saaragh Solutions, where I built a healthcare MVP from scratch.

For four years I led development and support at Crowd Communications Technology, launching a community management SaaS platform used by 25 enterprise clients. Most recently, as VP of Engineering at Transengage Technologies, I delivered an AI shopping-agent MVP in five months and onboarded six pilot clients. That work, retrieval pipelines, automation workflows, choosing and evaluating models, is what Aratavan does now.

Alongside client work I'm building Sella, Aratavan's own AI marketing product for Shopify and D2C stores, so the agents I build for clients sit on patterns I run in production myself.

The problem I kept running into

Here's roughly how it went, more times than not: a company decides it wants "an AI agent" for something: support, sales, ops, whatever the pain point of the quarter is. They bring in a vendor. The vendor is excited, the client is excited, everyone agrees this is going to change things. Then the scoping starts, and it never really stops. The workflow turns out to be more specific than the pitch deck implied. The vendor wants to build a platform, not a solution to the one problem in front of them, because the platform is what they can resell to the next client. Timelines get "refined." Budgets become retainers. Eighteen months later there's a working demo that has never touched a real customer, and the person who championed the project internally is quietly looking for a new job.

None of this is really about the technology. Large language models are good enough, right now, to handle a large share of the workflows that get pitched as "AI agent" projects. The failure mode is almost always commercial and organizational: open-ended engagements don't have a forcing function to actually finish, and vendors whose revenue depends on ongoing retainers have a quiet incentive not to.

Why fixed scope, fixed price, fixed date

The constraint is the point. When I quote a fixed price and a fixed delivery date before writing any code, three things happen that don't happen in an open-ended retainer:

• The scoping conversation gets serious, fast. If I'm going to be held to a number and a date, I need to actually understand the workflow: every input, every system it touches, every case where a human currently has to make a judgment call. Vague scoping produces vague builds; a fixed quote is a forcing function against vagueness on both sides of the table.
• There's no incentive to keep the engagement open. I get paid to finish, not to keep meeting. A retainer model quietly rewards the vendor for the engagement lasting longer; a fixed-scope model rewards me for shipping.
• You get a real decision point, not a slow bleed. If the quote is too high for the value, you find that out on day two, not month eight. That's a better outcome for you even when the answer is no.

What I say no to

A new practice doesn't mean taking any work that's offered. I won't quote a fixed price against:

• A goal instead of a workflow. "Help our customers succeed" isn't scopeable; "resolve return requests under $75 without a human" is.
• A workflow the client can't currently describe in specific steps, because if you can't describe it, I can't build against it, and the resulting agent will disappoint everyone.
• Fully autonomous decision-making on irreversible financial, medical, or legal outcomes with no human checkpoint. I'll build the triage, the drafting, the first-pass review, the part that removes 80% of the manual load, and leave the final call with a person, because that's where it belongs today.
• A budget that isn't proportional to the scope. If the described work is nine months and the budget is a fortnight, the honest answer isn't a cheaper version of the same promise, because no such thing exists. I'll tell you what the scope as written actually costs. Where a genuinely smaller first build would answer the question you're really asking, I'll quote that instead and say plainly what it leaves out. What I won't do is take the money and hand back something described as finished that isn't.

Saying no on a scope call costs me a sale, and for a new practice that's not nothing. I do it anyway, because the alternative is delivering something that technically shipped but shouldn't be trusted, with my name on it.

Why working with the founder directly helps you

At a larger agency, the senior person runs the sales call and a team you've never met does the build. Here, the person asking the uncomfortable questions on the scope call, what happens when the API is down, when the input is malformed, who gets told when the agent gets it wrong, is the same person who has to answer them in code. Nothing gets lost in a hand-off because there isn't one.

Being early also works in your favour. I take on only as much as I can build well myself, so your project gets my full attention rather than a slot in a queue. And the first clients of a new practice get more care than anyone, because those engagements are what Aratavan's reputation will be built on.

What I'm building toward

I'm not trying to become a platform company, or sell you a no-code builder you'll never touch. I want Aratavan to be who you call when you have a specific, well-understood workflow that's expensive in people-hours and dull enough that a person doing it all day is a waste of what they're capable of, and you want someone who will tell you honestly whether it can be done, what it costs, and when it'll be done, and then be right about all three.