Who is the fictional business?
GreenNest gets enquiries from Instagram ads, its website and walk-ins at its HSR Layout showroom. Most arrive on WhatsApp. Two designers and an office manager reply when they can. Enquiries are copied into a Google Sheet at the end of the day, sometimes the next day, and follow-up depends on who remembers.
Step 1: what does the process walkthrough reveal?
In a one-hour walkthrough with the office manager and one designer, we map what happens today:
- Enquiries arrive on one WhatsApp number shared on two phones.
- The first reply asks the same things: property type, location, scope (kitchen, wardrobes, full home), budget band and timeline.
- Many enquiries never get a second follow-up.
- Price questions are frequent, and designers prefer to discuss them on a call.
- Nobody knows exactly how many enquiries arrive per week.
Step 2: what does the one-page pilot scope say?
- Trigger: a new WhatsApp conversation, or a message after 14 days of silence.
- Steps: greet, ask five qualifying questions (buttons where possible), offer a call or showroom slot, create or update a lead in Zoho CRM, notify the assigned designer.
- Outputs: a Zoho lead with answers and source; a task for the designer; a confirmation to the customer.
- Success measure: every enquiry logged the same day with an owner; follow-up task created for every qualified lead. Counted for four weeks.
- Owner: the office manager.
Step 3: what does the stop rule say?
- Alone: greet, ask the qualifying questions, share the showroom address and hours, offer slots from the designers' calendar, create the lead.
- With approval: none in this pilot. Anything beyond qualification goes to a person.
- Hard stops: any price or quote question ("A designer will call you to discuss budget and options"), complaints from existing customers, requests for a person, and messages the agent can't understand after one clarification.
- Handover package: the conversation, answers collected, Zoho lead link and reason for handover, sent to the assigned designer on WhatsApp.
Step 4: how is it built?
A WhatsApp Business Platform number via a provider, an n8n workflow for the plumbing, an AI step to understand free-text answers ("3bhk in Sarjapur, mostly kitchen and wardrobes, want it before Diwali"), and Zoho CRM's API. See Zoho and WhatsApp. Templates for the 14-day follow-up are submitted for Meta's approval.
Step 5: how is it tested?
Before going live, the team sends 30 realistic test messages, including awkward ones: a voice note, a message in Kannada, a customer who only says "price?", an angry existing customer. Each result is checked against the stop rule, and two prompts are adjusted.
Step 6: what happens in the review?
For four weeks, the office manager reviews handovers weekly. In this illustration, the team notices that many "price?" handovers come from Instagram ads, and decides to add a line about consultation-based pricing to the ad copy. After four weeks the team decides whether to keep, tune or expand the pilot, for example to post-quote follow-ups.
What should you take from this example?
- The scope fits on one page.
- The stop rule makes pricing a human conversation by design.
- The success measure is something the team can count, not a vanity metric.
- The pilot ends with a decision, not an automatic upsell.
The agent drafts, routes and escalates. A person decides. Before anything is built we write down what the agent may do alone, what needs approval, and when it must stop and hand over with the full context attached.
How do you know whether the pilot worked?
We agree the success measure before building, and it should be something your team can count without a dashboard project. Typical measures include the share of enquiries logged the same day, time to first response, the number of follow-ups that actually happened, hours spent on the task per week, or the number of escalations that were correctly flagged. We count the baseline before launch (even by hand for a week) and again after a few weeks of running.
We also review the qualitative side with the people involved. Do they trust the drafts? Are handovers arriving with enough context? Are customers asking for a person more or less often? A pilot can hit its number and still need tuning, or miss it and teach you something important. Either way, the decision to keep, tune, expand or stop is yours, made on evidence. We don't publish generic success figures, because results depend on your process, volumes and team.
What should you prepare before talking to us?
You don't need a technical brief. A useful first conversation needs only a few things, and gathering them is valuable even if you never work with us:
- The process in plain words: what triggers it, who does what, and where it usually goes wrong.
- Rough volumes: how many messages, orders, tickets or invoices per week. A one-week tally is enough.
- Your tools: WhatsApp app or API, CRM, sheets, accounting or helpdesk software, including versions or plans where you know them.
- Three real examples: typical messages or cases, plus one awkward one, with personal details removed.
- What must never happen: the mistakes that would hurt most. These become the first lines of your stop rule.
- An owner: the person who will review the workflow once it runs.
Send these on WhatsApp or by email, or run the pilot scorecard first.