Products AI Voice Agents WhatsApp Agents Sales Meeting Agents Rocket Sales Agent TenderCraft Procurement Intelligence Customer Risk Intelligence AI for SAP AI for Manufacturers SAP AI Copilot Sales Order Email Agent Voxdonna Personal Assistant Donna Photoshoot Virtual Try-On Prescription OCR Explore Demos How it works FAQ Book a Demo Resources Blog About
Rooftop solar ยท Sales, subsidy, commissioning, O&M

Sized from the bill. Booked for survey. Tracked to the net meter.

A solar lead arrives with one useful fact in it: the electricity bill. Everything after that is your team retyping the same twelve answers about subsidy slabs, shadow-free roof area and where the net meter has got to. Voxdonna builds an AI employee that owns the whole chain. It sizes the system from the bill, books the survey, files and tracks the subsidy and net-meter stages, and tells the customer where things stand before they ask you twice.

22 Indian languages in one agent 14 days to a working line Bill to sized system to booked survey, in one conversation
Where the margin goes

Six conversations your team has a hundred times a month.

Every one of them is answerable from data you already hold. None of them is answerable at 11:30 PM by a person who has gone home.

๐Ÿงฎ

Every lead arrives as a bill amount and leaves as a quote request

"My bill is about this much a month, is solar worth it?" is the entire brief you get. Sizing it, explaining the subsidy slab and getting to a survey slot costs a trained person most of half an hour, and that message arrives all day, every day, from people who have not decided anything yet.

๐Ÿ“œ

The subsidy conversation is the same twelve answers, forever

Who qualifies, how much for 1 kW versus 3 kW, whose name has to be on the connection, whether a rented roof counts, when the money actually lands. Your sales team answers these instead of selling, and one wrong answer puts an application in the rejection pile.

โณ

The DISCOM queue is your reputation, not the DISCOM's

Panels went up three weeks ago and the customer is calling you about a net meter you do not control. Name mismatches across Aadhaar, bill and bank account, pending load enhancement and bidirectional meter stock are the usual causes, and none of them are visible to the customer unless somebody tells them.

๐Ÿงพ

The first post-solar bill turns a happy customer into a complaint

Import gets billed without the export being adjusted, the bill lands far above near-zero, and the customer concludes the system does not work. That call comes to you, not to the DISCOM, and you have no evidence at hand unless the generation data is already pulled.

๐Ÿšš

A red light on the inverter becomes a truck roll

Most red lights are grid-side faults the inverter cleared itself. Without remote diagnostics in the first message, you dispatch a technician for a voltage excursion that resolved before he reached the gate.

๐Ÿงน

Nobody hears from you again until the AMC renewal

Generation drifts down because the panels have not been cleaned in five weeks, the customer never sees a generation report, and the referral you were owed goes nowhere. The best salesperson you have is a customer holding a near-zero bill, and you never ask them to show it.

What the AI employee does

Three chains it owns from bill photo to generation report.

Sales, subsidy and service are one continuous relationship in rooftop solar. The agent treats them that way.

Workflow A

Bill to booked site survey

  1. Lead arrives from a Meta or Google ad, a National Portal referral, a WhatsApp click-to-chat or the website form. Often at 11:30 PM.
  2. Agent opens the conversation in seconds, in the customer's language, and declares itself AI.
  3. Segments first: own house, flat or society, or business. That decides the subsidy path versus the CAPEX or OPEX path before any sizing happens.
  4. Takes the monthly bill amount, or reads the uploaded bill photo, and derives monthly units and the kW band.
  5. Returns a sized recommendation with net cost after the applicable PM Surya Ghar slab, and a payback range. Bands, never a final quote.
  6. Pre-checks the three things that actually reject applications: connection in the applicant's name, own roof, residential connection. Flags a name mismatch before it becomes a rejection.
  7. Books a free site survey, physical or WhatsApp-video, and confirms roughly how much shadow-free roof area the recommended size needs.
  8. Writes the lead into the CRM with bill, sized system, subsidy eligibility, city and slot, scored, and assigns the surveyor.
  9. Routes anything factory or warehouse scale to the C&I desk instead, with a 12-month bill upload link.
Workflow B

Subsidy and net-meter status, tracked without a phone call

  1. On order confirmation, the agent opens a tracked case per customer covering both the subsidy claim and the net-meter application.
  2. Document pre-check: name on the electricity bill against the application and the bank account, ownership proof, load sanction. Anything mismatched gets fixed before filing.
  3. Files the National Portal application and the DISCOM net-metering application, and records the reference numbers.
  4. Tracks the four stages: application, feasibility, meter inspection, physical meter swap. Pushes a WhatsApp update the moment a stage moves, unprompted.
  5. Escalates when the queue slips past the expected window, and tells the customer it has, which is the part that keeps them calm.
  6. On commissioning, triggers the subsidy claim against the commissioning certificate and states the expected credit window rather than a date it cannot control.
  7. Audits the first two post-solar bills against the generation data, catches the import-billed-without-export-adjusted error, and drafts the billing-correction request with the meter data attached.
  8. Logs the case outcome, so the operations head can see which DISCOM circles are actually slow and which are only badly documented.
Workflow C

Service and O&M, triaged before dispatch

  1. Customer sends a WhatsApp voice note, in Hindi, at whatever hour the inverter went red.
  2. Agent transcribes, identifies the system, and pulls live inverter data.
  3. Returns the fault code and what it means in plain language, separating a grid-side self-protection event from an actual hardware failure.
  4. If it is self-clearing, explains it and confirms generation resumed. No truck roll.
  5. If it is not, books a technician visit inside a real window, preferring the engineer who installed the system, and states whether it is covered under warranty.
  6. Checks generation against forecast in the same conversation and offers a panel-cleaning slot when output has drifted.
  7. Sends the monthly generation and savings report on the first of the month to every active system: units generated versus forecast, bill before and after, cumulative saved, payback progress.
  8. Uses that report as the referral moment, issues the referral link and logs the new lead against the existing customer.
Example AI employees

Five roles a solar company hires. Start with the first one.

Each owns a stage of the same customer relationship. Most EPCs begin at lead-to-survey, because the volume is obvious and the arithmetic never changes.

01

The Solar Sales Engineer

Reads the electricity bill, sizes the system, applies the right PM Surya Ghar slab, and books the site survey without a human doing the arithmetic.

02

The Subsidy Case Officer

Pre-checks the documents that actually cause rejections, files the National Portal and DISCOM applications, and reports every stage change before the customer asks.

03

The Net-Meter Tracker

Owns the gap between installation and commissioning, escalates a slipped DISCOM queue, and keeps the customer informed through the wait you do not control.

04

The Bill Auditor

Checks the first post-solar bills against generation data, catches the unadjusted-export billing error, and files the correction with evidence attached.

05

The O&M Desk

Triages inverter faults from a voice note, separates grid events from hardware failures, books only the technician visits that are actually needed, and sends the monthly generation report.

Business outcomes

What changes once the waiting stops being silent.

Directional, because we publish what we can point at. The magnitude is yours to measure on your own pipeline and your own dispatch log.

01Every enquiry gets sized and answered on arrival, including the ones that land after the office shuts, which is when most ad clicks happen.
02Survey slots get filled by qualified roofs rather than by whoever answered the phone first.
03Applications stop failing on name mismatches and missing load sanctions, because the check happens before filing rather than after rejection.
04The commissioning wait stops generating inbound calls, because the status arrives before the question does.
05Fewer technician dispatches for faults that cleared themselves, and faster dispatch for the ones that did not.
06The first-bill complaint becomes a filed correction with meter data attached instead of an argument about whether solar works.
07Existing customers hear from you monthly with a number, which is the only referral engine that costs nothing.
08Operations gets a record of which DISCOM circles are slow, which is a planning input rather than an anecdote.
Integrations

It reads the portals and the inverters, and writes back to your CRM.

Nothing new to buy. The agent sits on the systems that already hold the answer and stops your team retyping it.

PM Surya Ghar National Portal and state nodal agency portals

The application, the reference number and the stage are the spine of the whole post-sale experience.

DISCOM net-metering application portals

Per state, per circle. The four-stage tracker lives or dies on reading status back from here.

WhatsApp Business Platform

Where bill photos, voice notes, stage updates and generation reports actually land in India.

Inverter and plant monitoring platforms

Growatt, SolarEdge, Enphase, SolarMan and the OEM portals. Fault codes and generation data are what make the service agent useful instead of apologetic.

CRM: Zoho, Salesforce, HubSpot or a solar-native CRM

Lead, sized system, subsidy eligibility, survey slot, case status.

Meta lead ads and Google Lead Form extensions

The majority of residential solar inbound, and the reason the 11:30 PM response matters.

Field service and scheduling tools

Surveyor and technician calendars, so a booked slot is a real slot.

Bill and document OCR

Reading the electricity bill turns a photo into units, sanctioned load, connection name and tariff category in one step.

Tally and the accounts stack

Quotations, milestone payments and EMI paperwork, so the quote the agent explains matches the one finance issued.

Slack, Microsoft Teams, WhatsApp groups

Escalation alerts for slipped DISCOM queues, and C&I leads routed to the commercial desk.

Proof you can open

Solar agents, running in your browser.

These are demo builds, not deployments. The figures inside them are illustrative, and each one takes about a minute.

โ˜€๏ธ

Bill to sized system, on WhatsApp

Sizing, subsidy eligibility, survey booking, net-meter stages, first-bill audit and the monthly generation report, in one thread.
Tara, the rooftop solar WhatsApp concierge →

๐Ÿ—ฃ๏ธ

Scheme outreach in Hindi

An outbound line that explains the scheme, answers eligibility questions and logs interest for follow-up.
Suraj, the Hindi PM Surya Ghar outreach voice agent →

๐Ÿ› ๏ธ

Urgent field dispatch

The pattern behind the O&M desk: symptom captured, severity judged, engineer routed with the context written down.
emergency field-service dispatch →

๐Ÿ“Š

Faults caught before the call

Monitoring data turned into a scheduled visit instead of a breakdown, which is what generation-drift alerts become.
predictive maintenance dispatch →

๐Ÿ”Œ

The other side of the counter

What the utility's own connection desk sounds like when it is automated. Useful context for the queue you are waiting in.
the DISCOM new-connection agent →

๐Ÿ—‚๏ธ

Everything else we have built

Voice and WhatsApp agents across industries, all playable without a signup.
all 40+ live Voxdonna demos →

Questions we get

What founders and service heads ask first.

Can an AI agent size a solar system from just the electricity bill?

Yes, and it is the fastest qualification signal you have. In our Tata Power Solar WhatsApp demo the agent takes the monthly bill amount, converts it to monthly units at the local tariff, recommends a kW band, states the net cost after the applicable PM Surya Ghar slab and gives a payback range. It then books the survey, where the engineer confirms shadow-free roof area and issues the real quote. Bands from the agent, final numbers from your engineer.

How does an AI agent handle PM Surya Ghar subsidy questions without getting them wrong?

It works from a locked knowledge base with the current slabs, and it pre-checks the three things that cause rejections: the connection has to be in the applicant's name, the roof has to be theirs, and the connection has to be residential. Name mismatches across the bill, Aadhaar and bank account are the most common failure, so it catches those before filing, not after.

Can it tell customers where their net-meter application has reached?

That is the point of it. The demo tracks four stages, application, feasibility, meter inspection and physical swap, and pushes an update the moment one moves. When the DISCOM queue slips, the agent says so and records the escalation. Customers stop calling your office about a queue neither of you controls, because the status arrives before the question does.

Will it stop us sending technicians for faults that fix themselves?

Mostly. A red light on the inverter is usually a grid-side voltage excursion the inverter self-protected against, and it resumes when the grid stabilises. The agent pulls live system data, returns the fault code and what it means, and books a visit only when the data says a visit is needed. Our demo runs that triage from a Hindi voice note.

Does it work for housing societies and C&I, or only residential rooftops?

All three, with different paths. Residential runs the subsidy path. Housing societies run common-area systems on group net metering, which needs an RWA resolution and six months of bills. C&I gets routed to a commercial desk with a CAPEX versus OPEX comparison on a real 12-month load profile rather than brochure numbers, because a CFO is not buying a subsidy, they are buying a tariff.

What languages does it handle, and does it read voice notes?

It runs in 22 Indian languages in one agent, and it switches when the customer does. Voice notes in Hindi come in and answers go back out as voice notes, which matters because the customer who sends one is usually standing in front of the inverter. Technical terms customers use in English, kW, net meter, inverter, subsidy, stay in English.

What does it cost us in engineering time to get this live?

Fourteen days to a working line, using the channels you already run. No new CRM, no portal rebuild. The agent reads from your existing system catalogue, subsidy rules and monitoring platform, and writes back to the CRM you already pay for. Start with one workflow, usually lead-to-survey, and add the subsidy tracker once it is earning.

Start where the bills pile up. Usually lead-to-survey.

Bring one week of inbound enquiries and one month of service tickets. We will tell you which chain pays for itself first, and what it takes to stand it up.