How does it think?

Agents that cite their sources, with a bill you can read line by line.

Agents, retrieval, voice and document AI over tenant-scoped data, with evaluations in CI, cost ceilings per run, and a human step before anything commits the business.

Scope an agent

What it is

We build the thinking layer: retrieval over your own documents scoped to the tenant that owns them, agents that do one named job with one named owner, voice and document pipelines, and the routing that decides which model answers at what cost. Every answer carries its sources, every agent has an evaluation set that runs on each change, and anything that commits price, scope or a date stops for a person. Tenant isolation is proved by tests that ship with the system, not asserted in a policy document.

Who it is for

If none of these sound like your situation, this is probably the wrong arc — and we would rather tell you that than sell you a discovery.

Twelve years of quotes, contracts and specifications sit in a shared drive nobody can search.
Your team answers the same forty questions every week and the answers live in one person's head.
You piloted a chatbot, it invented a price, and the pilot ended there.
Half your inbound arrives as a phone call after six in the evening.

How the work is shaped

Repeatable shapes, not bespoke proposals. Each one has been run before and has a duration we hold to.

01Retrieval Pilot · 3 weeksOne document corpus indexed and tenant-scoped, with a golden question set, measured answer accuracy, and a citation trail on every response.
02Agent Build · 8 weeksOne agent doing one job end to end: tools, guardrails, escalation path, an evaluation suite in CI, and a cost ceiling per run.
03Agent Layer · 14–18 weeksSeveral agents under one registry — shared retrieval, routing by task and cost, human approval queues, and per-agent spend reporting.

What it costs

Published, not gated. The assumptions column is the part that matters — a price without them is a guess you discover was wrong in week three.

Published price bands and the assumptions behind them
Band	From	What it buys	Typical duration	Assumes
Retrieval Pilot	₹6,00,000	One corpus indexed with tenant scoping, a 50-question golden set, and accuracy measured before and after.	3 weeks	Up to 5,000 documents in text-extractable formats One tenant boundary; cross-org sharing rules are separate scope Accuracy measured against a question set your team signs off
Agent Build	₹15,00,000	One production agent: tools, guardrails, escalation, evaluations in CI, and a cost cap per run.	8 weeks	The process the agent takes over is documented, or observed during Envision Model and inference spend is billed at cost, outside the fee Two systems integrated; each additional system is quoted separately
Agent Layer	₹34,00,000	Several agents on shared retrieval with model routing, approval queues and per-agent cost reporting.	14–18 weeks	Three to five agents defined by a signed build plan Source data sits in systems exposing an API or a database we can read Voice channels require a telecom account in your name

What sits inside it

Agents

One job, one owner, one evaluation set — and a human step on anything that commits price, scope or a date.

RAG

Retrieval scoped to the tenant that owns the document, with the isolation proved by tests you keep.

Voice

Calls that book, confirm and escalate, with the transcript written back to the record it belongs to.

Document AI

Intake, extraction and routing for the paperwork that currently moves by hand.

Model routing

The cheap model answers the easy question; the routing rules and per-task ceilings are yours to change.

What it has produced

Every number here comes from work on this page. Follow it to the story and check it.

fewer stock-outs across 400 SKUs: 31%fewer stock-outs across 400 SKUsSee the story
returned to clinic reception staff: 11 hrs/weekreturned to clinic reception staffSee the story
median time to clear a freight exception, from 38: 4 minmedian time to clear a freight exception, from 38See the story
cross-tenant retrieval leaks in the isolation suite: 0cross-tenant retrieval leaks in the isolation suite

The work behind it

48 staff

Three days of stock guesswork, gone

A two-floor clothing retailer replaced a Monday morning reorder meeting with a forecast read from its own till data.

31% target reduction in stock-outs across 400 SKUs

85 staff

The waiting room emptied before the doctor arrived

Four clinics moved patient intake to the phone in the waiting room and got eleven hours a week back at reception.

11 hrs/week target reception time returned across four clinics

150 staff

Thirty-eight minutes to clear an exception, down to four

A freight operator's exception desk stopped being four people reading four screens.

4 min target median time to clear an exception, against 38 observed

35 staff

Proposals that stopped eating the fee-earners' evenings

A consultancy assembled proposals from its own past work instead of from last week's near-miss document.

6-9 hrs → 90 min design target for a first proposal draft

28 staff

Weekend enquiries answered before Monday

A lettings agency stopped losing the enquiries that arrived when nobody was at a desk.

8 min target median first reply to a weekend enquiry

Is Intelligence what you need?

Tell us what is slow and what it is costing. If the answer is a different arc, or no arc at all, we will say so before anyone writes a proposal.

Scope an agent