Skip to content
Mirai Minds

Booking new builds for Q4 2026, updated

AI that talks, reads and gets work done.

Voice agents, WhatsApp agents and custom AI for real operations — built and run by a senior studio in Surat, India. Live in 2–8 weeks.

Live call · voice agentSample

Hi, can I move my appointment to Thursday?

Sure. Thursday has 11:00 and 4:30 PM free. Which works?

4:30, please.

Done. I've sent the confirmation on WhatsApp.

✓ calendar.check → 2 free slots

✓ booking.update → Thu 16:30

✓ whatsapp.send → confirmation

In short

Mirai Minds is an AI engineering studio in Surat, India. We design, build and run production AI: agents that act inside your tools, voice and WhatsApp agents that talk to customers, document AI that turns drawings into SAP-ready data, and computer vision for photos and products. Most builds ship in two to eight weeks.

Built for

  • Photo Experience
  • iKoMatch
  • Myva.ai and CallPaaS
  • Rouh

…and a public-sector refinery we can't name.

Five kinds of AI systems. One studio.

Each one designed, built and run by the same senior team, with a person in the loop until the numbers say otherwise.

AI agents and automation

Agents that read, decide and act inside your tools, with every tool call logged and a person approving the risky ones.

  • Operations copilot over internal APIs
  • Browser or desktop task agent
  • Research and enrichment pipeline with human approval
See the service

Voice AI agents

Phone agents that answer, qualify and follow up in English or Hindi, and bring in a person when the caller needs one.

  • Inbound support line with live handoff
  • Outbound qualification campaign
  • Abandoned-cart recovery calls
See the service

WhatsApp AI agents

WhatsApp agents that remember each customer, answer from your documents and let your team step in from an inbox.

  • Lead qualification and follow-up on WhatsApp
  • Customer support with answers from your documents
  • Onboarding that turns a chat into a profile
See the service

Custom LLM and document AI

Language models grounded in your documents and data, measured on your own test set, with people reviewing what matters.

  • Document extraction into ERP or SAP
  • Question answering over policies, manuals or catalogs
  • Call and meeting analysis
See the service

Computer vision

Vision models that find faces and products, cut out backgrounds and edit photos, fast enough for a queue of real customers.

  • Face search for event and venue photos
  • Background removal and compositing
  • Generative photo effects with identity checks
See the service
Not sure which?Tell us the job. We'll say if AI is the right tool.Book a scoping call →

Every system we've built, in one ledger.

Shipped to productionUpdated

Shipped to production, updated 23 September 2026
ProjectWhat we builtResultYearStatus
Resin manufacturer (India)Catalog chat assistant with text and photo product searchPilot on a 15-product catalog sample2026–present Pilot
Photo ExperienceGenerative photo editing, face search and the image pipeline18.7 s per generative photo on one A100 (was 60–90 s)2023–present Pilot
iKoMatchWhatsApp and voice fundraising assistant with explainable matching6,717 investor records; each day's matches graded by an LLM judge2026 In production
CallAuditAIIn-houseCall audit service: recordings scored against a weighted rubricScorecards for an admissions counseling team's recorded calls2026 In production
Ethnic-wear e-commerce brand (India)Visual product search and abandoned-cart recovery callsVisual search live for store staff since July 20262026 In production
WhatsApp AgentsIn-houseWhatsApp agent service with memory, summaries and document searchRuns iKoMatch's founder conversations on WhatsApp2026 In production
AI outbound-calling startupPipecat voice bot, campaign dialer and per-call recordingLive for outbound campaigns2025–2026 In production
Voice AgentsIn-houseMulti-tenant platform for AI phone agents and calling campaignsLive at voice-agents.miraiminds.co2025–2026 In production
Indian public-sector refineryDocument AI: engineering drawings to SAP-ready bills of materialDelivered and handed over; every row reviewed before it reaches SAP2025–2026 Delivered
US logistics software companyChat agent over the client's platform APIs through MCPDelivered; every tool call's arguments are checked before it runs2025 Delivered
Gurbani learning appTransliteration, explanation and speech API for Gurbani linesDelivered to the app team as an authenticated API2025 Delivered
Myva.ai and CallPaaSDocument-grounded chatbot platform and call-center AI with GPTBoth products built and extended across 2023–20252023–2025 Delivered
RouhDesktop computer-use agent with MCP tools, scheduling and memoryWorking desktop prototype, reviewed by the founder2024–2025 Prototype

How three of them were built

All shipped work

What we build with

Chosen per project, from what we've already run in production.

Models

  • GPT-4.1
  • Claude
  • Gemini
  • Llama 4
  • Qwen Image Edit

Voice

  • Pipecat
  • LiveKit
  • Deepgram
  • Cartesia
  • ElevenLabs
  • Sarvam
  • Silero VAD
  • Twilio
  • Plivo
  • Vapi

Agents and data

  • MCP
  • OpenAI Agents SDK
  • LangChain
  • LangSmith
  • Mem0
  • Pinecone
  • FAISS
  • Playwright

Vision

  • PyTorch
  • YOLOv11
  • InsightFace
  • ArcFace
  • Diffusers

Platform

  • WhatsApp Business
  • FastAPI
  • PostgreSQL
  • Redis
  • Docker
  • AWS

What founders said after launch

Best place to get job done.
Mark BanarovFounder, Myva.ai, CallPaaSThe project →
Awesome work!!! Everything works as expected. I don’t have any major feedback other than keep going.
Humaid AlfalahiFounder, Rouh.aiThe project →

From first call to production in two to eight weeks

  1. Week 01

    Discovery call

    Thirty minutes with an engineer. You describe the job; we say whether AI is the right tool and what it would take.

  2. Week 12

    Scope and evals

    We agree what done looks like and build a test set from your real data before writing the system.

  3. Weeks 2–63

    Build

    Working software every week, measured against the test set, with your team trying it early.

  4. Launch4

    With human review

    The system goes live with a person checking the risky steps and a clear way to reach a human.

  5. Ongoing5

    Run and improve

    We watch real traffic, fix what breaks and tune on real cases, or hand over with documentation.

Products we run ourselves

Client work starts from parts already tested in production.

Asked on the first call

What does Mirai Minds build?

Five kinds of production AI systems: AI agents that take actions in your software, voice AI agents for phone calls, WhatsApp AI agents, custom LLM and document AI, and computer vision for photos and products. We also run three products of our own: Voice Agents, WhatsApp Agents and CallAuditAI.

How long does a typical build take?

Most builds ship in two to eight weeks. The first week goes to scope and evaluation, building a test set from your real data; the build follows in weekly releases; launch happens with a person reviewing the risky steps. We give a timeline on the first call.

Which models and providers do you work with?

Whichever fits the task: OpenAI, Anthropic, Google Gemini, Meta Llama, Mistral, DeepSeek and Qwen models, and open-weight models on dedicated GPUs. For voice we use Deepgram, Cartesia and ElevenLabs over Plivo or Twilio. We say when a smaller or cheaper model is enough.

What stage should my company be at to work with you?

Any stage. We have built for founders with a first product, for growing software companies and for a public-sector refinery. What changes is the scope, not the bar: every system gets an evaluation set, monitoring and a way for a person to step in.

Can you work with our in-house engineers?

Yes. We can build alongside your team, hand a finished system over with documentation, or keep running it for you. On the refinery document AI project we handed the system over to the client's IT partner at the end of the engagement.

Have a system in mind? Let's scope it.

A 30-minute call with an engineer who has shipped this before. You leave with a plan, a rough timeline and what it would take — whether or not we build it.