New — live in production across lending, industrial & clinical. See the customers →
Home / Docs

Docs & case studies.

A technical reference: the system, how it deploys in your cloud, and every live deployment in detail — problem, architecture, stack, and measured results.

The system Deployment Helm · lending TRACE · support PowerIQ · industrial KidneyCare · clinical For developers

The system

Aminobots builds the same three products for any industry, running on one engine:

How deployment works

Every system runs inside the customer's own cloud tenancy — the customer's identity, keys, and data residency. Nothing leaves the boundary the customer already audits; an on-prem option is available and the architecture is DPDP-ready.

Engagements follow a fixed shape: Diagnose (a 2–3 week written scorecard — is AI the right move, where's the return, what to build first) → Deploy (build, ship, handover) → Operate (observability, upgrades, audits) → License (your team runs it). Before any code, the build passes a Gate 0–4 discipline: do you even need AI, keep it simple, shape it to the workflow, measure it in your control, and build it to connect.

Live case studies

Four deployments are live in production. Each is summarised below with the problem, the approach, the stack, and the measured results.

Lending · NBFC · BFSI

Helm at IFHL — WhatsApp loan intake to disbursement

Problem. A loan that took days to move from application to disbursement, with manual checks and hand-offs — while faster competitors won the customer.

Approach. An agentic flow (deliberately a flow, not a peer mesh) runs the whole journey over WhatsApp: intake, parallel verification across systems, a one-screen decision, and disbursement — with a human only on the edge cases.

Architecture & stack. Lens deployed as Helm on the Blueprint engine, inside IFHL's own cloud; ~22 APIs orchestrated (KYC, bureau, banking, disbursement); WhatsApp as the customer channel; full audit trail.

MetricResult
Application → disbursement~8 minutes (WhatsApp to money)
Turnaround time~50% faster
Straight-through processing99%+
Cost per case~30% lower
APIs orchestrated22

Read the full IFHL case study →

Customer support · scale

TRACE at GyanDhan — support across 2,000+ WhatsApp groups

Problem. Customer questions spread across 2,000+ WhatsApp groups, with response times that stretched to hours and a support team that couldn't scale with them.

Approach. An agent answers questions autonomously across every group, using a knowledge core with citations, and hands the genuinely tricky ones to a human.

Architecture & stack. Assist for the channels plus Nous for the knowledge, on the Blueprint engine, in the customer's cloud.

MetricResult
Automation rate99%+ handled without a human
Cost per query~$0.02
Response time~2.5 hours → ~15 minutes
Coverage2,000+ WhatsApp groups

Read the full GyanDhan case study →

Industrial energy · manufacturing

PowerIQ at Omega Transmission — cutting the HT electricity bill

Problem. A plant paying a flat rate regardless of when it drew power — an electricity bill that didn't care about time-of-day tariffs — with heavy machines running at the most expensive hours.

Approach. Five-minute metering feeds a decision agent that shifts heavy machines to cheaper time-of-day windows automatically, and produces ESG Scope-2 reporting on demand. Meter data is processed at the edge so it never has to leave the site.

Architecture & stack. Lens deployed as PowerIQ with an edge component (Raspberry Pi on site) rather than moving raw meter data to the cloud.

MetricResult
HT electricity bill~20% lower
Metering granularity5-minute intervals
Time-of-day optimization100%
ESG Scope-2 report~60 seconds

Read the full Omega case study →

Clinical · point of care

KidneyCare at AIIMS Patna — a phone that reads a dipstick

Problem. Early kidney-disease screening needs a pathology lab and a trained eye — neither of which is at the point of care, especially for children in under-served settings. The test strip costs about ₹12; the constraint is reading it reliably.

Approach. A phone camera reads a urine dipstick in seconds; a computer-vision model grades the pads and flags early kidney-risk. A 70% confidence floor means the system says "indeterminate" rather than guess on a child.

Architecture & stack. Lens deployed as KidneyCare with on-device inference; built and validated with the AIIMS Patna paediatrics team, progressing along the CDSCO regulatory pathway.

MetricResult
Accuracy vs pathology lab90%+ (clinical validation, n=30)
Cost per screening70–80% lower
Photo → graded result~11 seconds
MaturityTRL 4→6 · CDSCO pathway

Read the full AIIMS Patna case study →

For developers

Built to integrate, not to lock in.

Every system is defined by a Blueprint spec — one declarative spec compiles to AWS, Azure, or GCP with LLM routing, safety gates, and an audit trail. It runs in your own tenancy and plugs into the systems you already operate.

  • Cloud-native, cloud-agnostic. One Blueprint spec targets AWS, Azure, or GCP — no rewrite per cloud.
  • Runs in your tenancy. Your identity, keys, and data residency; nothing leaves the boundary you already audit.
  • Integrates over standard interfaces. REST APIs and connectors into your core systems, with a clean audit trail.
  • Governed by design. Human sign-off gates and observability are baked into every deployment.
Open resources

Follow along on GitHub.

Integration notes, examples, and the Blueprint spec format — for engineers evaluating a build.

View GitHub →

Want this in your business?

Start with a Diagnose — a written scorecard in 2–3 weeks on whether AI is the right move, where the return is, and what to build first.

Book a diagnosis