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
THE BUSINESS AI belongs here IN PRODUCTION

I didn't read about this role. I do it.

Rashin Pothan
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

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.
COMPLETE CLEANERS EAST VALLEY · PHOENIX METRO
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.
41% OFFICE SHUT
of the calls came in when the office was shut.
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
Two full days out in the van with the crews
A whole Monday morning sat next to Marisol
120 recorded calls, start to finish. Not skimmed.
Rang six customers who had left. The ones who quit tell you the truth.
Timed it. Counted it. What people think is happening is not data.
Everyone said the problem was scheduling. The recordings said it was gone an hour earlier.
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
0just plain code,
no AI
0genuinely
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. Each miss books elsewhere.
AI
Quoting a job
185
Minutes of work. Hours of waiting. First quote usually wins.
AI
Invoicing & payment
1,100
Biggest number here. Jobber already does it.
LEAVE IT
Working out the price
185
A formula, not a judgement call
PLAIN CODE
Slots & booking
185
Rules all the way down
PLAIN CODE
Crews & routes
26
Same crews, same days, 22 miles. Already fine.
LEAVE IT
Complaints & damage
11
Somebody has to own the apology
HUMAN
ENQUIRIES
= VOLUME
640 a month, a third on the floor. Fix the most frequent leak first.
QUOTES
= SPEED
First quote in usually wins. Speed is the conversion rate.
AI earns its place when a process is high volume, still done by hand, and the delay costs you the sale.

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
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. Real examples, the correct answer marked by a human expert, and every version you build scored against the same set. So you know whether a change helped, instead of guessing.

300 real recorded calls. Marisol and Emmanuel marked every one. 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 · where systems actually fail
A telly, a toddler and a dog, all at once
An existing customer moving their slot
A salesman cold calling to sell SEO
A furious customer whose crew never showed
Spanish and English in one sentence
Asking for a service they don't offer
Six things to score · all agreed with Emmanuel before any code was written
01
Worked out who was calling
≥ 97%
02
Price within $15 of Marisol's
≥ 95%
03
Never two crews to one house
MUST NEVER HAPPEN
04
Complaint to a person in 20 seconds
MUST ALWAYS HAPPEN
05
Handed over on everything in the red list
≥ 95%
06
Never promised what they can't do
MUST NEVER HAPPEN
They agreed what "working" means before anyone wrote code.

The first eval run scored 74%. It sent two crews to the same house, and argued with an angry customer.

60%70%80% 90%100% PASS MARK · 95% 74% 87% 93% 95.6% 96.8% RUN 1RUN 2RUN 3 RUN 4RUN 5 PASSED
RUN 1 · FIRST TRY
74%
clashes 3 · handovers 71%
Failed in private, on the eval set.
RUN 2
87%
clashes 2 · handovers 79%
Check the number against Jobber first.
RUN 3
93%
clashes 2 · handovers 88%
Pricing moved to plain code. It was rounding down to be nice.
RUN 4
95.6%
clashes 0 · handovers 96%
Check the calendar when the phone rings, not at 8am.
RUN 5 · SHIP IT
96.8%
clashes 0 · handovers 100%
Never-break list clean. Now it can meet a customer.

The evals didn't just say it was bad. They showed him where. Half the first-run failures were one thing: existing customers treated as new leads. One lookup, moved to the front. Thirteen points.

Run it. Look at what broke. Fix that one thing. Run it again.

On day one, it didn't go anywhere near the main phone line.

What he built · one job, start to finish
Call comes
in
AI picks
up
Look them up
in Jobber
Work out
what they need
Price it
Check free
slots
Book it in
the calendar
Send a
text
Save the
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

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.

Now let me give it a proper name, and then show you how to get there.

You've just watched one work. Now the definition makes sense.

Someone who reads a business like a consultant and ships like an engineer. A model can't tell you what's worth automating, or what has to stay human. That decision is the job.
● WHAT THEY ACTUALLY DO
  • Watch the real work, decide where AI belongs
  • Write the code, inside the customer's mess
  • Wire it into the tools they already pay for
  • Prove it with evals before anyone trusts it
  • Stay accountable once it's live, on real money
× WHAT THEY'RE NOT
  • Not a salesperson with technical vocabulary
  • Not support, sitting behind a ticket queue
  • Not an architect drawing diagrams for others
  • Not a researcher training models
  • Not someone who hands over a demo and leaves

The name: the military sends people forward, not kept at base. Palantir coined it. The AI labs hire for it now.

"Forward" means inside their workflow, not their building. We've never set foot in a client's office.

Two kinds of judgement that rarely live in one person.

◀ BUSINESS JUDGEMENT
How the work actually flows, not how the manual says it does
What it costs to keep doing it by hand
Who quietly benefits from nothing changing
What happens to the business when it gets one wrong
Whether the staff will actually use it on a Monday
FDE
TECHNICAL JUDGEMENT ▶
What a model can and can't be trusted with
Which systems it has to reach into, and how
What shape the data is really in
How it fails, and how loudly it fails
What it takes to keep it running at 2am
Most people only have one of these columns. If you write software, you already have the right-hand one. The left-hand column is the part you're missing — and it is completely learnable.

How to become one, in 30 days.

Nobody hands you this title first. You do the job, badly and on your own, until you have something you can show. Run this alongside applying and interviewing, not before it.

What you have at the end · four things a stranger can read
ARTIFACT 01
The audit
How the work runs today, what it costs, and which processes you'd rebuild around AI. Including the ones you refused.
ARTIFACT 02
The architecture
The stack, the tools, the guardrails — and a reason each one exists. Gates, logging, and how you roll it back.
ARTIFACT 03
The eval report
Real cases, the pass rate, what kind of failure each one was, and the rule for when it hands over to a person.
ARTIFACT 04
The business case
Hours returned, money protected, cost per run. Written in numbers the owner recognises, not in tokens.
Do the job before you have the title. No CV proves this role. Only delivered work does.
Rehearse the story twice — once for an engineer, once for a CEO. Both of them will interview you, and they want completely different things.

Four weeks. Four checkpoints.

WEEK 1 · DAYS 1–7
Build something that finishes a real loop
  • Sit in on the work and map how it actually runs
  • Wire it into their real tools, not a toy sandbox
  • End to end, unattended, every step visible
WHAT TO LEARN →
WEEK 2 · DAYS 8–14
Turn the demo into something that recovers
  • Structured output, not prose you have to parse
  • Steps you can safely retry — a retry must not double-charge anyone
  • Resume mid-run, and log enough to explain itself
WHAT TO LEARN →
WEEK 3 · DAYS 15–21
Make it measurable, and make it pay
  • An eval set, hand-marked from real cases
  • Set the line where it hands over to a person
  • Cost per run, and what it replaces
WHAT TO LEARN →
FINAL WEEK · DAYS 22–30
Defend it like an FDE
  • Build over the systems they already have
  • Package the four artifacts
  • Rehearse twice — an engineer, then a CEO
WHAT TO LEARN →
DAY 7
A working agent
DAY 14
A system that recovers
DAY 21
An evaluated system
DAY 30
A complete case study
On day 30 you shouldn't just understand the job. You should have evidence you can do it.
WEEK 1 · DAYS 1–7

Build something that finishes a real loop

What you need to learn
  • One agent framework, properly. Pick one and stay in it. Tool calling, system prompts, message history, how a run is structured.
  • Giving a model tools. Tool schemas, how the model decides to call one, and what you do with the result it hands back.
  • Reading an API you've never seen. Auth, pagination, rate limits, sandbox keys versus live ones. This is most of the job in week one.
  • Process mapping. Sit with one person, write down every step they take, and time each one with a stopwatch.
● WHAT YOU SHOULD HAVE BUILT

An agent that takes one real input and produces one real output, in their real system, with nobody watching it.

DAY 7A working agent
WEEK 2 · DAYS 8–14

Turn the demo into something that recovers

What you need to learn
  • Structured output. JSON schemas and constrained decoding, and validating the shape before you act on it.
  • Idempotency. Idempotency keys and safe retries. A retry that charges someone twice is worse than a crash.
  • State and resumption. Persist the run, checkpoint each step, resume from the middle after a failure.
  • Logging and tracing. Every model call and tool call, inputs and outputs, cost and latency, so you can explain any run afterwards.
  • Failure handling. Timeouts, backoff, dead letters, and what you do when the model returns confident nonsense.
● WHAT YOU SHOULD HAVE BUILT

The same agent, but you can kill it mid-run, restart it, and nothing breaks and nobody gets double-charged.

DAY 14A system that recovers
WEEK 3 · DAYS 15–21

Make it measurable, and make it pay

What you need to learn
  • Building an eval set. Sampling real cases, hand-labelling with the person who does the job, and holding a set back that you never look at.
  • Scoring. Exact match, tolerance bands, and LLM-as-judge — including where a judge quietly lies to you.
  • Hard gates versus soft targets. The handful of things that can never happen, scored separately from the percentage.
  • Escalation design. Confidence, thresholds, and the written rule for when it hands over to a person.
  • Cost per run. Tokens, retries and tool calls, priced against whatever it replaces.
● WHAT YOU SHOULD HAVE BUILT

A number you can defend, a list of failure categories, and a cost per run written next to what it saves.

DAY 21An evaluated system
FINAL WEEK · DAYS 22–30

Defend it like an FDE

What you need to learn
  • The audit document. The process map, the verdict on each step, and the things you refused to build with the reason next to each one.
  • The architecture document. Stack, tools, guardrails, where the gates are, what gets logged, and how you roll it back.
  • The eval report. Pass rate, failure categories, the never-break list, and the escalation rule.
  • The business case. Hours returned, money protected, cost per run — in the owner's numbers, not in tokens.
  • Telling it twice. The engineer version is how it recovers. The CEO version is what it returned. Rehearse both out loud.
● WHAT YOU SHOULD HAVE BUILT

Four documents a stranger can read without you in the room, and a story you can tell in five minutes.

DAY 30A complete case study

The webinar hands you the map. The cohort is where you walk it.

The written roadmap goes to everyone on this call either way. The cohort is for people who would rather build the thing than read about it — 30 days, one real workflow, from audit to a deployed and evaluated system.

ONLINE · 40 SEATS
₹20,000
TWO LIVE SESSIONS A WEEK · TUE & FRI · 7–9PM IST
The full cohort, live and online. All sessions, all four artifacts, recordings, and the community.
STUDIO · 30 SEATS
₹30,000
EVERYTHING IN ONLINE, PLUS A DESK IN KOCHI
Same cohort, plus a desk at our Kochi office one afternoon a week. Build next to people doing the same work.
academy.7thpillar.com/fde-online Ends with a case study
that proves you can do the work
Questions. Ask me anything — the roadmap, the tools, the job market, or what you should build first.
SPACE or → next  ·  ← back  ·  F fullscreen