Process, timeline, pricing, tools

How we work: the whole engagement, written down before the call.

Founder-led, fixed fee, weekly working builds, source code yours. This page is the version you can read at midnight before deciding whether to book thirty minutes: how a project runs, what it costs, which tools we use, and the objections we hear most, answered.

Process

Five steps, from a call to a handover

01 · Day 0 · 30 minutes · free

Scope call

You describe the workflow or the product. We ask about volume, systems, who decides what, and what "working" would mean. If it is not a fit, or a cheaper tool would do, we say so on the call.

You get: A recommended approach, a timeline and a firm price range. Sometimes a reason not to proceed.

02 · Within 2 working days

Written brief and fixed fee

A one- to three-page brief: scope, the systems touched, the rules, the measure of success, what is out of scope, the fee and the dates. You sign that, not a proposal deck.

You get: A document both sides can point at when the question "is this included?" comes up.

03 · Week 1

Week one: rules, data model, baseline

The decisions that decide whether it scales: the data model, the permission model, the rulebook an agent follows, the baseline we will measure against. Agreed before features are built.

You get: The rulebook or data model, a data-flow diagram, and a working skeleton on staging.

04 · Weeks 2 onward

Weekly working builds

A running build on staging every week that you can use, not a status report. Slack or WhatsApp through the day, a weekly call, Loom for anything that needs showing. Scope changes are logged and costed, never silently absorbed.

You get: Something to use every Friday, and a log of what changed and why.

05 · Final week

Launch, measure, hand over

Production deploy to your accounts. The measure taken again. Documentation, runbooks, prompts and the repository handed over, with a session for your team. Thirty days of support after go-live.

You get: Your repository, your cloud and model accounts, the numbers, and a written plan for what comes next.

Timeline

How long each kind of engagement takes

EngagementTimelineShape
AI Agent Pilot2–3 weeksOne workflow, two systems, approval step, measured result, handover.
One workflow in production4–8 weeksIntegrated, monitored, with a console and a retainer option.
Agentic workflow across systems6–12 weeksPlanning across several systems, guardrails, memory, review console.
MVP or product build4–14 weeksScoped to the one thing it must prove; Bubble for speed or Next.js and Supabase for scale.
Community platform or LMS8–14 weeksMembers, marketplace, courses, events and an admin console on one schema.

Timelines assume one owner on your side who can answer questions within a day. The commonest cause of a slipped date is a system access request that takes three weeks.

A sample week

What the first week looks like, day by day

Week one of a pilot is the week that decides whether the build is worth doing. This is what happens on each day, what we need from you and for how long, and what exists by the evening that did not in the morning.

Monday
  • Kick-off, 45 minutes: the brief read aloud, the owner on your side named, the measure of success agreed in one sentence.
  • Access requested: read-only to the systems in the brief (calendar, inbox, CRM, practice software), a WhatsApp test number, a shared sheet for the rulebook.
  • Baseline starts: we begin counting how the workflow runs today (hours, first-reply time, completion rate) without changing anything.

From you: 45 minutes on the kick-off, then whoever can grant access. Nothing else.

By evening: A one-page working agreement, an access list with owners, the baseline sheet started.

Tuesday
  • The rulebook sitting, 90 minutes with the person who does the workflow best, yesterday’s messages open: how they decide, what they refuse, who they hand to.
  • We write the first draft of the rulebook and the escalation list from that sitting, in a sheet you own.
  • Systems connected read-only; the first real data flows into the staging environment.

From you: 90 minutes from the person who runs the desk or the inbox. The most valuable hour of the pilot.

By evening: Rulebook v0.1 and the escalation list, in your sheet, with the gaps marked.

Wednesday
  • The tool list and permissions drafted: each verb the agent may use, marked act-alone, with-approval or never.
  • The data-flow diagram: two lines a customer could read, which system sees what, where the log lives.
  • The first skeleton on staging: a message in, a classification, a draft reply, nothing sent.

From you: 20 minutes to read the tool list and strike anything that should never be there.

By evening: Tool list signed, data-flow diagram, a skeleton you can watch classify real messages.

Thursday
  • The red-flag and edge-case set: fifty real-shaped messages, including the mixed and the awkward ones, written with you and run against the skeleton.
  • Rulebook v0.2 from what the set exposed; approval step wired so a person sees every draft before anything goes out.
  • Templates submitted where WhatsApp is the channel, so approval time runs in parallel.

From you: 45 minutes to supply the awkward cases from the last month and mark which replies were wrong.

By evening: A test set that runs on demand, the approval queue, templates in review.

Friday
  • The week-one checkpoint, 30 minutes: rulebook, tool list, data flow, baseline so far, and what the skeleton got right and wrong on the test set.
  • The decision, together: continue into the build weeks, change the scope, or stop here with the artefacts and a fair share of the fee.
  • If continuing, the build-week plan: what ships next Friday and who approves what.

From you: 30 minutes, and the decision. The owner on your side and whoever signs.

By evening: A yes, a no, or a changed scope, in writing; and either way the rulebook, the diagram and the baseline are yours.

About five hours of your time across the week, nearly all from the person who runs the workflow today, in the slots above. We work from Nagpur; the sittings land in your morning for the UK and your early morning for the US East Coast, or in Indian working hours for Indian clients. The commonest reason week one slips is Monday’s access list, which is why it is the first thing on it. The week is the first of the AI Agent Pilot; the rulebook it produces is the fill-in template, and the baseline follows what a pilot measures.

Pricing bands

What it costs, in USD and INR

Ranges, not quotes. The number firms up on the scope call once we know which systems, how much autonomy and how much data work is involved. Every engagement is a fixed fee against the written brief.

EngagementWhat it coversUSDINR (+GST)Timeline
AI Agent PilotOne workflow, up to two systems, an approval step, running on your data with your team using it.$4,500₹3,50,0002–3 weeks
One workflow, in productionA single workflow automated end to end and wired into the systems you already run — inbox, CRM, WhatsApp, spreadsheets.$8,000–$42,000₹6,50,000–₹35,00,0004–8 weeks
Agentic workflowAn agent that plans across several systems, exercises judgment and acts, with guardrails, logging and a review console.$15,000–$60,000₹12,00,000–₹50,00,0006–12 weeks
Agent platform or productSeveral agents sharing memory, permissions and a console, or an AI feature inside a product you sell.$60,000–$150,000₹50,00,000–₹1,25,00,0003–6 months

Running costs after launch, per month

Under 500 runs a month$30–$120₹2,500–₹10,000
500–5,000 runs a month$120–$600₹10,000–₹50,000
5,000+ runs a month$600–$2,500₹50,000–₹2,00,000

Model usage plus hosting, billed to your own accounts. Messaging carrier fees are extra. A retainer for changes and monitoring is optional and scoped on the call.

Fixed fee against a scoped brief, agreed on a free 30-minute call. Changes are logged and costed, never silently absorbed. Source code, prompts and accounts are yours.

Product and MVP builds are priced the same way. For reference, a scoped MVP runs from about $8,000 for a single-module build to $15,000–$45,000 for a multi-module platform; see the MVP development page for the breakdown.

Get a range for your case in two minutes · What an AI agent costs in India in 2026

Tools

The stack, and why each piece is in it

Boring on purpose. Every piece is something your next developer will already know, and every account is yours.

Models and agents

  • Claude (Anthropic API)Reliable tool use and instruction-following on long rulebooks; our default for agents. Model chosen per task for reasoning, latency and cost.
  • Tool-use loops with approval queuesEvery agent is a short list of named tools, a rulebook and a queue for anything that writes to a system of record.
  • Retrieval over your documentsAgents answer from your material and cite it, rather than from general knowledge.

Backend and data

  • Supabase (Postgres, Edge Functions, Auth)One database for the product, the agent’s memory and the logs, with row-level security on everything.
  • Node and DenoEdge functions for agent loops and webhooks; no servers to babysit at SMB volume.
  • VercelHosting for the web app and the review console, in your account.

Frontend and no-code

  • Next.js and ReactFor products that need ownership, performance and scale from day one.
  • Bubble.ioWhen speed to market beats everything else, built with a data model that does not need redoing later.
  • FlutterFor the companion mobile apps where a product needs one.

Channels and integrations

  • WhatsApp Business API (Meta Cloud API)The channel most of our clients’ customers actually open.
  • Stripe, RazorpayPayments and payouts, built once and reused by every module.
  • HubSpot, Zoho, LeadSquared, Tally, Zoho Books, Google WorkspaceWhatever you already run on, through its API or a reviewed export.
How we behave

Six things you can hold us to

You deal with the person building it

Ketan Khamgaonkar (IIT Roorkee) scopes, architects and leads every build, with the SigmaticAI team. No account manager relaying messages.

Overlap hours, not time-zone excuses

We work from Nagpur, India, with 9:00–13:00 US Eastern and 9:00–17:00 UK covered. Slack or WhatsApp through the day, a weekly call, Loom when something needs showing.

Ownership is the default

Your repository, your cloud and model accounts, your Stripe. IP assigned in the contract. Nothing about the handover depends on us still being in the picture.

We tell you when not to build

If a SaaS tool does your job, or a Zap would do, or the process does not exist yet, we say so on the scope call. A pilot that should stop at week one, stops.

A person approves what matters

Agents draft, prepare and act within rules. Anything that writes to a system of record or reaches a customer passes an approval step until the log earns it more autonomy.

Fixed fee, logged changes

The brief fixes the fee. Changes are written down and costed before they are built, so the invoice never surprises either side.

FAQ

The objections, answered before the call

How do we know you can do this?

Read the case studies: The Raising Club, a five-module marketplace in production in the US, first commit 29 May 2026 and live 2 July 2026; Accsys, offline-first accounting with GST reporting. Read the reviews on Google and Clutch, quoted verbatim on the service pages. Try the demo agents. Then book thirty minutes and ask anything.

Why fixed fee rather than hourly?

Because you should know the number before you start, and because an hourly meter rewards slowness. The fee is fixed against a written brief; changes are logged and costed. We carry the risk of estimating badly.

What if the scope changes halfway?

It usually does, a little. A change is written down, costed and agreed before it is built. Small ones are often absorbed; we say so when they are. What never happens is a surprise on the invoice.

Who owns the code, the prompts and the data?

You do. Everything is built in your repository and your cloud and model accounts from day one, and IP is assigned in the contract. The handover is documentation and a session, not a transfer.

What happens after launch?

Thirty days of support are included. After that, a monthly retainer covers monitoring, rule changes, model upgrades and new integrations, scoped on the call. Plenty of clients run without one; the handover is written for that.

How do you handle our data and our customers’ data?

It stays in your systems and your region. Agents see the conversation or document they are working on, not the archive. The model provider does not train on your data under the API terms we use. We write the data-flow diagram into the handover so you can show it to anyone who asks, and design to the DPDP Act, GDPR or HIPAA as your project requires, with the caveat that we say upfront what we have and have not built under each.

Do you work with clients outside India?

Most of our clients are in the US, the UK and India. Billing in USD or INR, contracts in English, overlap hours as above.

How small is too small?

The pilot exists for exactly this question: one workflow, two to three weeks, a fixed fee. If the workflow happens a handful of times a week, we will tell you a person with a checklist is cheaper. If it happens dozens of times a day, it is worth a conversation.

What do you need from us?

One person who owns the workflow and can spend two or three hours a week on it, access to the systems involved (read-only to start), and honest answers about how the work is done today. The rest is ours.

Next step

Thirty minutes, free, with the person who would build it

Bring whatever you have: a sketch, a spreadsheet, a competitor you like. You leave with an approach, a timeline and a price range.

Or write to us

Name and email are all we need. A line about the project gets you a specific reply.