LIVE · SAT 8 AUG · 7–8 PM IST
RETHINK AI ACADEMY · SESSION DOSSIER 001
What is a Forward Deployed Engineer, and how to become one.
One hour, no jargon. We'll follow one real business with one real problem, and watch an engineer fix it. Then I'll show you how to get this job.
Rashin PothanPresented by
7th Pillar InfotechCEO · Kochi
ReThink AIFounder & CTO · Arizona
I didn't read about this role. I do it.
RASHIN POTHANSINCE 2014
CEO, 7th Pillar Infotech (Kochi) · Founder & CTO, ReThink AI (Arizona, US)
- Building software since 2014. For the last three years, nearly all of it AI that real companies use every day.
- I started on my own company first. Looked at how we actually work, picked the few places AI would genuinely help, and built only those.
- Most of that job was the boring safety work. That's the part that makes it okay to trust.
- I also run ReThink AI in Arizona. We build phone agents for home service companies: they answer, ask the right questions, book the job. Day and night.
- Then I ran the same audit-and-build for clients, on four continents.
- Nobody taught me any of this in a classroom. Tonight I'll show you how I picked it up.
0yrs running 7th Pillar
0continents served
0AI companies in production
24/7voice agent live in the US
A Day in the Life of a Forward Deployed Engineer.
Easier to show you than to define it. So we're going to follow one, on one real job, from the day he walks in to the day it goes live. One business in Arizona. One problem. Six weeks. Watch what he builds, then watch what he says no to.
Case no.
2026 / AZ-04
Sector
Residential cleaning
Location
Chandler, Arizona
EXAMPLE CASE
BASED ON REAL PROJECTS
NAMES AND NUMBERS CHANGED
NAMES AND NUMBERS CHANGED
Complete Cleaners LLC
The cleaning company Emmanuel started back in 2014, in Chandler, Arizona. Most customers book the same slot every week or every fortnight. They also do one-off deep cleans and end-of-tenancy cleans.
Who's in charge
EmmanuelFOUNDER & OWNER
Started the company in 2014, cleaning houses personally, with one car and an ad online. Still knows half the customers by name, and runs the whole business from a phone.
Marisol Reyes38 · OPERATIONS
She sends 17 teams out every morning, sorts out who's called in sick, calms down upset customers, and answers most of the phone calls. If she takes a day off, the week falls apart.
Tyler24 · OFFICE ADMIN
Rings people back. Asks happy customers to leave a review.
The crews34 CLEANERS
17 teams of two, 12 vans. Same customers, same day of the week, every week.
WHAT THEY USE: Jobber for the schedule and the bills · QuickBooks for accounts · one phone line · ads on Google and Yelp
None of it is connected to anything else.
None of it is connected to anything else.
0earned in a year
0cleaners
0regular customers
0calls a month
It starts with a phone call at 10:52 on a Tuesday.
INCOMING · MOBILE
(480) 555-0147
RINGING… 4 RINGS
"Hi — yeah, I'm looking to get a quote? We're in Gilbert, near Val Vista and Baseline. Four bedroom, three bath, about twenty-eight hundred square feet. Two dogs. It hasn't been done properly in… a while. My in-laws land Thursday."
TV on. Dog barking. Toddler.
What actually happened next
Phone rings. Marisol is already on another call.
4 RINGS
It goes to voicemail
10:52 AM
The message sits in the inbox
—
Tyler gets round to the voicemails
+ 6h 00m
Tyler rings her back. She doesn't pick up.
4:52 PM
Tyler leaves a voicemail
1 MIN
Nobody at Complete Cleaners ever knew this call happened.
Result: nothing.
She booked with another company at 11:20 that same morning. They picked up on the second ring.
Here's the part that stings. Answering her would have taken ten minutes. But nobody was there to pick up, and the same thing happened 230 more times that month.
Everyone blamed the scheduling. But the money was already gone before scheduling.
Calls that came in, one month0
Somebody picked up0
↓ 230 calls nobody ever answered. That's 36%.
Were new people wanting a price0
Actually turned into a booking0
01
36% of calls went unanswered. Lunchtime, busy mornings, and every single evening and weekend. When your house needs cleaning you ring three companies and book whoever picks up.
02
About 1 in 5 callers speaks Spanish. They were told someone would call them back. Usually that meant tomorrow. Usually it meant never.
03
Marisol spent 3.5 hours a day on the phone while also running 17 teams. She was the safety net and the traffic jam at the same time.
04
9 booking mistakes a month. Two crews sent to one house, wrong address, no gate code. Each one wastes a van, two people and half a morning.
of the calls came in when the office was shut.
Nobody picked up a single one.
Nobody picked up a single one.
They were flat out busy and losing money in the same hour. Both were true.
He didn't open a code editor for nine days.
A Forward Deployed Engineer does two jobs at once. First they work out what the business actually needs. Then they build it. Same person, both jobs. That's the bit most people get wrong.
STEP 1 · THE AUDIT
Go and watch how the work really happens.
Sit in the office. Ride in the van. Listen to old phone calls. Then decide what is actually worth building.
4 DAYSNO CODE YET
STEP 2 · EVALS
Write the evals before you write the code.
An eval is a test for an AI system. Real examples from the past, each one marked right or wrong by the person who does the job today. You score every version against it.
5 DAYSSTILL NO CODE
STEP 3 · BUILD IT
Build one thing. Score it against the evals. Switch it on slowly.
Build, test, look at what broke, fix that, test again. Then turn it on in the place where it can do the least damage.
4 WEEKSBUILD + LAUNCH
Most engineers start at step 3. That's why most AI projects quietly die.
Before writing a single line, he went and watched.
What he actually did for four days
Spent two full days out with the cleaning teams, in the van and in the houses.
Sat next to Marisol for a whole Monday morning, the worst hours of her week.
Listened to 120 recorded phone calls from start to finish. Not skimmed. Listened to.
Talked to Emmanuel, Marisol, Tyler and three team leaders. Then rang six customers who had left, because the people who quit tell you the truth.
He timed things and counted things. What people think is happening is not data.
Everyone told him the problem was scheduling. The recordings showed the money was already gone an hour before that.
What he handed over: a map of all 16 steps, with a decision written on each one
01
Call arrives
NO SOFTWARE
02
Answer and talk
NEEDS AI
03
Understand what they want
NEEDS AI
04
Look up the caller
PLAIN CODE
05
Work out price and slots
PLAIN CODE
06
Put it in the calendar
PLAIN CODE
07
Pick the team
NO SOFTWARE
08
Plan the day's route
NO SOFTWARE
09
Load the van
NO SOFTWARE
10
Team checks in
NO SOFTWARE
11
Clean the house
NO SOFTWARE
12
Quality check
NO SOFTWARE
13
Cover a sick day
NO SOFTWARE
14
Send the bill
NO SOFTWARE
15
Take payment
NO SOFTWARE
16
Ask for a review
NO SOFTWARE
0need no
software at all
software at all
0just plain code,
no AI
no AI
0genuinely
need AI
need AI
Every business runs a dozen processes. Two of them were worth AI.
The processTimes a monthWhat it costs them todayVerdict
Taking enquiries
640
36% never answered. Every miss is a customer who books someone else.
AI
Quoting a job
185
The work takes minutes. The customer waits hours. Whoever quotes first usually wins.
AI
Invoicing & payment
1,100
The biggest number on this slide. Jobber already does it. Volume on its own is not a reason.
LEAVE IT
Working out the price
185
Size × bedrooms × how often. A formula, not a judgement call.
PLAIN CODE
Slots & booking
185
Read the calendar, write to the calendar. Rules all the way down.
PLAIN CODE
Crews & routes
26
Same crews, same houses, same days, inside 22 miles. Already close to optimal.
LEAVE IT
Complaints & damage
11
Somebody has to own the apology. This one is a judgement call, every time.
HUMAN
ENQUIRIES
= VOLUME
= VOLUME
640 a month, and more than a third of them hit the floor. Fix the leak that happens most often, first.
QUOTES
= SPEED
= SPEED
In home services the first quote in usually gets the job. Speed isn't a nice-to-have here. Speed is the conversion rate.
AI earns its place when a process is high volume, still done by hand, and the delay is costing you the sale. Miss any one of those three and something cheaper will beat it.
Of the four things they asked for, he said no to three.
That isn't him being awkward. That is the job they were paying for.
"We want our own system to replace Jobber."
Jobber works fine. The problem is at the front door, not in the database. Rebuilding it would cost a fortune and still not answer one extra call.
NO
"We need an app so cleaners can check in."
Jobber already has one. Nobody had ever shown the teams how to use it. Two hours of training sorted it. Cost: nothing.
NO
"Can AI plan better routes for us?"
17 teams, same houses, same days, all inside a 22 mile circle. The routes are already about as good as they get. The software would cost more than it saved.
NO
"People calling in sick ruins our whole day."
A real problem, but software is the wrong shape of fix. They made a standby list and paid $40 to anyone who covered at short notice. Sorted in a week.
A RULE,
NOT CODE
NOT CODE
The most useful thing he produced in his first week was a list of things he refused to build.
If you can write the rule yourself, don't use AI.
◀ PLAIN CODE — YOU WRITE THE RULES
Price = size × bedrooms × how often
Extra charges for the fridge, oven, windows
Is this address inside our area?
Which slots are free right now
Put the job in the calendar
Send the confirmation text
THE LINE
AI — YOU CAN'T WRITE THE RULES ▶
Understand someone talking over a barking dog
Work out that "it hasn't been done in a while" means deep clean
Do the whole call in Spanish
Notice this is a complaint, not a booking
Ask the one question that's actually missing
Let AI do the pricing and it starts handing out discounts nobody agreed to. It rounds the house size down to be helpful, and you won't spot it for months. The proper word for the left column is deterministic: same question in, same answer out, every single time.
Now try the other way round. Hand an upset customer to a set of if statements and you've earned yourself a one star review. Getting this line in the right place is most of the job.
The AI answers the phone. The clever part is knowing when to hand over.
● THE AI HANDLES IT ON ITS OWN
- A price for a normal house inside their area
- Moving or cancelling a booking
- "What time is my cleaner coming?"
- Gate codes, key box codes, "the dog is in the garden"
- The whole call in English or Spanish
■ HAND TO A HUMAN, RIGHT NOW
- Any complaint, or anyone getting annoyed
- Anything broken or damaged
- Big jobs: builders' cleans, or houses over 3,500 sq ft
- Offices, or an address outside their area
- Anyone who asks to speak to a person
- Anyone who has asked the same thing twice
◆ MARISOL CHECKS IN THE MORNING
- She reads every booking the AI made before the vans go out
- Every single day for the first two weeks
- After that, just spot checks
- Every call is recorded and written down, so anyone can go back and look
This was never about getting rid of Marisol. She was missing the eleven calls that really needed her, because she was buried under the other six hundred. Now she gets those eleven.
So what exactly is an eval?
evalSHORT FOR "EVALUATION"
A repeatable test for an AI system. You gather real examples, a human expert marks the correct answer for each, and then you score every version you build against that same set. It's how you know whether a change made the system better or worse, instead of guessing.
Here's what that looked like. He pulled 300 real recorded calls from the last six months and wrote down, for each one, what price was given and what got booked. Then Marisol and Emmanuel went through all 300 and marked them. The person who does the job decides what counts as right. Not the engineer, and definitely not the AI.
0to practise on
0kept hidden
0the nasty ones
The 20 nasty ones are what tell you if it really works
Someone calling with the telly on, a toddler and a dog all going at once
An existing customer ringing to move their slot. Must never be treated as a new lead.
A salesman cold calling to sell them SEO
A furious customer whose cleaners never turned up. Hand over within 20 seconds.
Someone switching between Spanish and English halfway through a sentence
Someone asking for carpet shampooing, which they don't even offer
Six things to score · all agreed with Emmanuel before any code was written
01
Worked out who was calling: new customer, existing one, complaint or salesman
≥ 97%
02
Price within $15 of what Marisol would have said
≥ 95%
03
Booked the right slot. Never two crews to one house.
MUST NEVER HAPPEN
04
Passed a complaint to a person within 20 seconds
MUST ALWAYS HAPPEN
05
Handed over correctly on everything else in the red list
≥ 95%
06
Never promised a service they don't do, or a slot they don't have
MUST NEVER HAPPEN
They agreed what "working" actually means before anyone wrote code. That one habit separates an engineer who gets kept from one who doesn't.
Three of these six can never be broken. Break one and the whole test fails, however good the rest looks.
The first eval run scored 74%. It sent two crews to the same house, and argued with an angry customer.
RUN 1 · FIRST TRY
74%
clashes 3 · handovers 71%
It failed on the eval set, in private, before any real customer ever heard it.
RUN 2
87%
clashes 2 · handovers 79%
Check the phone number against Jobber first. Is this already our customer?
RUN 3
93%
clashes 2 · handovers 88%
Took pricing off the AI and gave it to plain code. The AI kept rounding house sizes down to be nice.
RUN 4
95.6%
clashes 0 · handovers 96%
Check the calendar the moment the phone rings, instead of once at the start of the day.
RUN 5 · SHIP IT
96.8%
clashes 0 · handovers 100%
Nothing on the never-break list is broken. Only now does it speak to a real person.
The evals didn't just tell him it was bad. They showed him where. Half the failures on the first run came down to one thing: people ringing to move their booking were being treated as brand new customers. He moved one lookup to the front and got thirteen points back.
That's the loop. Run it, look at what broke, fix that one thing, run it again. It is not "keep fiddling with the prompt until it sounds okay."
On day one, it didn't go anywhere near the main phone line.
What he built · one job, start to finish
Call comes
in
in
AI picks
up
up
Look them up
in Jobber
in Jobber
Work out
what they need
what they need
Price it
Check free
slots
slots
Book it in
the calendar
the calendar
Send a
text
text
Save the
recording
recording
FIRST
Nights and weekends only
10 DAYS
It answers between 6pm and 8am, and all weekend. Those calls were going to voicemail anyway, so there is nothing to lose.
THEN
Only when nobody else can
14 DAYS
In the daytime it picks up anything that rings more than four times. Marisol reads every booking it made the next morning.
NOW
It answers first
ONGOING
Anything it hands over, a person takes. Nobody was asked to trust it. They watched it work on their own calls for a month first.
WEEK 1Watch and count
WEEK 2Write the evals
WEEKS 3–4Build, test, fix, test
WEEKS 5–6Nights only, then live
Six weeks. One engineer.
Start where the current option is voicemail. You can't do worse than voicemail.
Same crews. Same vans. Same area. Someone finally answers the phone.
Measured over the first three monthsBEFOREAFTER
Calls someone picked up
64%
99%
How fast it gets answered
4 rings, then voicemail
2 rings, any time
Calls outside office hours
none
all of them
Jobs booked from calls
74 a month
109 a month
Spanish calls dealt with there and then
almost none
all of them
Booking mistakes
9 a month
1 a month
Time Marisol spends on the phone
3.5 hrs a day
40 min a day
0
a year in extra repeat business
48 more regular customers than the three months before · each worth about $3,700 a year
0
a month from the extra jobs
35 more jobs a month, at about $285 for a first clean
0
a month handed back to Marisol
She runs the teams and looks after customers now, instead of living on the phone.
It costs about $1.90 per call answered. A receptionist costs $3,400 a month and can't work nights, weekends or in Spanish. It paid for itself in the first month.
"I've stopped waking up at 5am to check the voicemail."
— EMMANUEL, FOUNDER
— EMMANUEL, FOUNDER
The code took nine days. Watching took four. The watching was the real work.
What he builtOne job
Phone call, price, booking. Not the whole company. One job.
What he refused to build11 of the 16 steps
Including three of the four things they walked in asking for.
What they thought they wantedA system, an app, routing
None of it would have earned them a single dollar.
Anyone can write code now. The AI does that bit.
The hard part is knowing what's worth building, and being able to prove it works.
That's what a Forward Deployed Engineer does. It's also why companies can't find them.
So how do you become one? That's the rest of tonight.