How we work

Start small, prove it works, then scale it.

We structure engagements so you can stop after any stage. The first commitment is deliberately small — because until we have looked at your data together, neither of us can honestly size the rest.

Engagement model

Three stages, each with a clear exit point

You are never asked to commit to the whole thing up front. Each stage produces something useful on its own.

Discovery

fixed scope, short

Before anything is built, we work out whether it should be. We map the problem, test feasibility against your real data and agree what success would look like.

  • Use-case mapping and prioritisation
  • Technical feasibility assessment
  • Reference architecture
  • Costed delivery plan
  • An honest recommendation, including 'not yet'
Most engagements start here

Pilot

fixed scope

One use case, built properly and put in front of real users. Small enough to be low-risk, real enough to tell you whether it works.

  • One production-ready use case
  • Evaluation suite you can re-run
  • Deployment to your environment
  • Source code and documentation
  • Measured results, not a demo

Production & beyond

per engagement

Take a validated pilot into full production, integrate it properly, and keep improving it — or hand it to your team with everything they need to own it.

  • Full build and system integration
  • Monitoring, logging and rollback
  • Private or on-premise deployment
  • Ongoing support or clean handover
  • Team enablement and documentation
Pricing

How we price

A number quoted before understanding the problem is not useful to either of us. The same request — “an assistant over our documents” — can be three weeks of work or three months, depending on how your data is stored, what it has to integrate with and how wrong it is allowed to be.

So we scope first. Discovery and pilots are fixed-scope, so you know the cost before committing. Larger builds are quoted per engagement once the scope is genuinely clear. Everything is quoted in Indian Rupees, plus applicable taxes.

If budget is a constraint, say so early. We would rather shape the work to fit than spend both our time on a proposal that was never going to land.

Request a quoteQuoted in INR, plus applicable taxes
Delivery

What actually happens once we start

01

Discover

We map the business problem, check technical feasibility and agree what success would actually look like.

02

Design

Reference architecture, data flows, access rules and an evaluation plan — agreed before code is written.

03

Build

Short, eval-driven cycles. You see working software regularly rather than a status report.

04

Deploy

Ship to your cloud, VPC or on-premise, with monitoring and a rollback path in place.

05

Handover

Documentation, source code and a walkthrough — so your team can run and extend the system.

Evaluation-driven

Every build ships with an evaluation suite, so quality is measured rather than asserted.

Deployed your way

Your cloud account, VPC or on-premise — including open-weight models where data cannot leave.

Source-code handover

You receive the code and the documentation. No lock-in to us to keep it running.

Human in the loop

Approval gates and review queues wherever an automated mistake would be costly.

Common questions

Questions about working together

Still unsure where to start? Get in touch and we will help you find the lowest-risk first step.

With a short discovery engagement. We map the use cases worth pursuing, test feasibility against your actual data and produce an architecture and a costed plan — so you can decide whether to build with full information and without committing to a large project first.

Not sure where to start?

Tell us the problem. We will suggest the smallest piece of work that would tell you whether this is worth pursuing.

Skip to content