---
title: "Suresh B (@jarvisbitztech) | Hashnode"
description: "Founder & CEO at JarvisBitz Tech. Read the latest articles by Suresh B on Hashnode."
url: "https://hashnode.com/@jarvisbitztech"
---

@jarvisbitztech

# Suresh B

@jarvisbitztech · Ahmedabad, India · Joined September 2026

Founder & CEO at JarvisBitz Tech

[Website](https://www.jarvisbitz.com/)

## Comments

[Thanks for reading. Your point about MCP servers wrapping existing APIs is the one I'd underline, because that is where most of the engineering actually sits. The trap is doing it one to one. If you map each REST endpoint to a tool, the model gets a list it has to assemble into a workflow, and it guesses. One tool per business capability works better, even when that means a single tool spans three internal calls. The other thing that does not carry over automatically is authorization. Your API already knows who may see what, but the MCP server has to verify the token itself and pass identity down, or you end up with an adapter that quietly bypasses your own rules.](https://hashnode.com/posts/build-mcp-server-internal-tools-auth-error-handling/6ab62228c8262785c4c73031/comment/6ab634f7a80b327fd10584df#reply-6ab7cfbe959346999b74431b)

Reply · Article · Sep 26 · [How to Build an MCP Server for Internal Tools: Architecture, Authentication and Error Handling](https://hashnode.com/posts/build-mcp-server-internal-tools-auth-error-handling/6ab62228c8262785c4c73031)

[Thanks for the comment, Mihai\_LeanZero. Good catch. I covered cancellation, but not the case where a request gets retried or the caller changes their mind while something is already running. I would keep the task state in the application and track each side effect with its own operation or idempotency ID. If the caller changes the request, move the task to a new revision and ignore any result that comes back from the older one. If a request times out, check the backend before retrying so you do not accidentally create the same booking twice. The other important part is not saying something succeeded until the backend has actually confirmed it. “I’m booking that now” is very different from “you’re booked for 3pm.” Really useful point. I’m adding this to the production component table.](https://hashnode.com/posts/production-voice-ai-architecture-2026/6ab28859ab202fa5a0950e1f/comment/6ab2f41e6796c15737927b75#reply-6ab366b2179f1a0d3ec9eb4f)

Reply · Article · Sep 23 · [Production Voice AI Architecture in 2026: How Realtime Conversational Agents Are Built](https://hashnode.com/posts/production-voice-ai-architecture-2026/6ab28859ab202fa5a0950e1f)

[Thanks for the comment, Mihai\_LeanZero. That’s a useful distinction. A transcript can tell you what the agent said happened, but the system of record tells you whether it actually happened. For actions like cancellations or reschedules, I’d much rather compare the agent’s closing claim with the backend state and flag any mismatch for review. I also like your point about intents without a clear ending. If an intent doesn’t have an explicit success or completion condition, the agent can keep talking even after the useful part of the interaction is over. Defining that end state before the intent ships seems better than trying to diagnose it later from the hangup curve. Repeat contact is still a useful slower signal too, because it catches cases where the backend action succeeded but the caller still didn’t get the outcome they expected.](https://hashnode.com/posts/ai-voice-agent-for-customer-service-what-stops-callers-hanging-up/6ab0dfcc721db2384062b376/comment/6ab1e90f98dceb4f14d26dd8#reply-6ab21c28e12f21786fc2835e)

Reply · Article · Sep 22 · [AI voice agent for customer service: what stops callers hanging up?](https://hashnode.com/posts/ai-voice-agent-for-customer-service-what-stops-callers-hanging-up/6ab0dfcc721db2384062b376)

[Good catch Mihai\_LeanZero . I went back through the MRTR spec, and it doesn't give you a built-in idempotency key for this. The spec does give you replay protection around requestState: bind it to the authenticated principal, give it a short TTL, and tie it to the originating request. But it explicitly says that still doesn't guarantee single use. If you need exactly-once behavior, the server has to enforce that itself. There's another edge case too: the client isn't required to retry after input\_required. So if the first pass already reserves something or calls a paid API, you can end up with either a duplicate on retry or an orphan if the retry never happens. I'd keep the first pass side-effect free where possible. If that's not possible, create a short-lived reservation/idempotency ID, carry it through requestState, and have the retry reconcile against that reservation instead of performing the action again. And yeah, idempotentHint doesn't solve this. It's useful metadata, but it's still only a hint, not an enforcement mechanism.](https://hashnode.com/posts/mcp-2026-what-changed-production-integrations/6ab11ceda94daaa897a992da/comment/6ab131ff05d34cf1cb9932eb#reply-6ab1635128c395d6e15c3f59)

Reply · Article · Sep 21 · [MCP in 2026: What Changed in the 2026-07-28 Specification and How to Design Production Integrations](https://hashnode.com/posts/mcp-2026-what-changed-production-integrations/6ab11ceda94daaa897a992da)

[Thanks for reading, Mateo Ruiz . I think you may be thinking of a different article, this one is about business chatbots answering from approved sources rather than coding agents, but your point about concrete examples beating vague rules holds there too. A handful of real example phrasings per intent does more for classification than any amount of instruction text.](https://hashnode.com/posts/how-to-build-an-ai-sales-assistant-that-does-not-make-things-up/6ab0d310ea331ee93db71587/comment/6ab0dc3bc706e0c5bccf740d#reply-6ab0e24e6979badd2f5121dc)

Reply · Article · Sep 21 · [How to build an AI sales assistant that does not make things up](https://hashnode.com/posts/how-to-build-an-ai-sales-assistant-that-does-not-make-things-up/6ab0d310ea331ee93db71587)
