arrow_backAI PrototypespsychologyProduct Case Study

AI Product Case Study

The thinking behind both tools: problem scoping, user segmentation, customer research, trade-offs, and success metrics. Grounded in 350+ career coaching sessions and a live job search.

About this study

This AI Product Case Study walks through two AI tools I built and shipped: the Profile Optimization Tool and the Job Application Workflow Agent. Rather than just describing what they do, it shows the product thinking behind them: how I scoped the problem, picked the right user, mapped their journey, prioritized what to build, and defined what success looks like.

350+

Coaching sessions

2

Shipped AI tools

8

Product sense steps

Both tools grew directly from 350+ career coaching sessions, direct user observation, and my own active job search. Not hypothetical personas.

Step 1: Scope the problem

It started with a deliberately vague observation: job seekers are struggling with their applications. That's too broad to build anything meaningful, so the first step was to get specific.

QuestionAnswer
What kind of struggling?Not finding roles. Job boards handle discovery. The real pain is converting applications: getting past the first filter.
Where in the process?Before applying (is my profile ready?) and while applying (how do I tailor for this JD?).
What channel?Desktop web. Job seekers prep materials at a desk, not on their phone.
Core mechanism?Resumes and LinkedIn profiles evaluated against a job description. The gap is the problem worth solving.
Job seekers don't know how well their profile matches a specific role, and they don't have a fast way to close those gaps before they apply.

Out of scope

Not solvingWhy
Job discoveryLinkedIn and Indeed already solve this
Interview prepDifferent tools, different moment in the journey
Salary negotiationHappens after application
Auto-applying on behalf of usersTrust and accuracy risks are too high

Step 2: Segment the users

SegmentWho they areApplication behaviorCore challenge
Early-career (0-3 yrs)Recent grads, first or second jobHigh volume, 20-50 apps/monthGeneric resumes; don't know which keywords matter to recruiters or ATS
Mid-career (3-10 yrs)Professionals pivoting roles or industriesSelective, 5-15 apps/monthRich experience but struggle to translate it; bullets describe tasks not outcomes
Senior / career changersDirectors, VPs, or major domain switchesVery selective, 2-8 apps/monthHard to condense scope; risk of appearing over- or under-qualified

Segments based on behavioral patterns observed across 350+ career coaching sessions.

Step 3: Pick the target segment

Target: Mid-career professionals with 3-10 years of experience who are pivoting into a new role or industry, e.g. an operations manager moving into product management.

ReasonDetail
Highest pain-to-value ratioExperience exists. It needs reframing. AI is strong at translation without inventing facts.
Most common in coachingThis group came up most often for tailoring help and bullet rewrites.
Invests time per applicationSelective applicants who want real return on tailoring effort.
Outcomes are measurableFit scores before/after, completion rates, acceptance rates.

Step 4: Persona & journey

Meet Kathy, the frustrated career pivoter

AttributeDetail
BackgroundFive years in operations at a SaaS company. Vendor workflows, cross-functional projects, JIRA and Notion
GoalMove into a Product Manager role at a tech company
Behavior8-12 PM roles/month; 30-45 min tailoring each application; rarely hears back
In her own words"I know I have the skills. I've done PM work. But I have no idea why I'm not getting calls."

Kathy's seven-stage journey

StagePain pointSeverity
Discover roleNo quick way to validate fit before committing timeHigh
Assess fitSlow, subjective comparison; unsure which keywords matter to ATSHigh
Tailor resumeBullets describe tasks not outcomes; gives up and sends same resumeHigh
Update LinkedInProfile static and generic, not positioned for target rolesModerate
Write cover letterGeneric opening; no connection to specific JDModerate
SubmitNo confidence she put her best version forwardLow
WaitNo feedback loop after rejectionLow (out of scope)

Step 5: Prioritize pain points

Pain pointPriorityAI suitability
Can't quickly tell if she's a fit before tailoringHIGHHigh. Keyword pattern-matching is core LLM strength
Can't rewrite bullets in JD languageHIGHHigh. Grounded in user's existing text, low hallucination risk
LinkedIn not positioned for target roleMODERATEHigh. Once per campaign, not every application
Cover letter from scratch every timeMODERATEHigh. Best after fit analysis and rewrites
No feedback loop after rejectionLOWLow. Outside our control

Top pains to solve: (1) Instant fit assessment with grounded JD citations, (2) Bullet reframing in outcome language, (3) LinkedIn audit as a complementary baseline check.

Step 6: List the solutions

FeaturePain it solvesHow it works
Fit score engineCan't tell if she's a fit0-100 score with tier, keyword breakdown, and JD line citations
Skill gap analysisDoesn't know what's missingRequired skills from JD vs. resume with evidence attached
Bullet rewriterCan't reframe in JD languageRewrites each bullet; user accepts or rejects one by one
Cover letter generatorStarts from scratchStreams a letter built from fit analysis and accepted rewrites
LinkedIn section auditProfile not positionedScans headline, About, Experience, Skills with JD-tied fixes
Match report & printNo record of submissionExportable report: score, keywords, actions, print to PDF

Step 7: Prioritize features

FeatureShip priority
Fit score & gap analysisSHIP FIRST. Entry point; needs only resume + JD
Bullet rewriterSHIP SECOND. Conversion step; grounded in user's text
Cover letter generatorv1. Downstream of fit + rewrites (Step 4)
LinkedIn section auditv1 parallel. Separate moment, Profile Optimization Tool
Match report & printv1 bundled. Needs score first

The cover letter ships in the Workflow Agent because it's downstream of fit analysis and rewrites. The LinkedIn audit lives in Profile Optimization because it serves a different trigger: baseline readiness, not active application.

Step 8: Wireframes & success metrics

Profile Optimization Tool

Solves LinkedIn/resume baseline readiness. Score-first layout: match %, then gaps, then actions. Nothing stored between sessions. A deliberate trust decision.

MetricTypeTarget
Analysis completion ratePrimary> 85%
Time to report (p50)Primary< 60 seconds
Action plan engagementSecondary> 60% scroll past score
Print / export rateSecondary> 20% of sessions
AI hallucination rateGuardrail0 per 100 analyses

Job Application Workflow Agent

Four-step guided workflow: Analyze Fit, Surface Gaps, Rewrite Bullets, Draft Cover Letter. Accept/reject on every bullet. Streaming cover letter. Golden-set regression before every ship.

MetricTypeTarget
Workflow completion (all 4 steps)Primary> 60%
Fit score accuracy (golden set)Primary5/5 per deploy
Bullet acceptance rateSecondary> 50% of rewrites accepted
Cover letter generation rateSecondary> 40% who reach Step 3
Step 1 to Step 2 drop-offSecondary< 20%
Hallucination rateGuardrail0 per 100 analyses

Summary: how I think about product

Framework stepDecision made
Scope the problemNarrowed to closing the gap between profile and a specific JD
Segment usersThree segments by experience level and application behavior
Pick target segmentMid-career pivoters. Highest pain, best AI fit, largest in coaching data
Persona & journeyKathy's seven-stage journey maps real pain at every touchpoint
Prioritize painsFit assessment and bullet rewriting ranked highest
List solutionsSix features, each tied to a specific pain. Nothing without justification
Prioritize featuresFit score first, bullet rewriter second, LinkedIn audit in parallel
Wireframes & metricsPrimary metrics per tool + hallucination guardrails
The persona, pain points, and feature priorities are not hypothetical. They come from 350+ career coaching sessions, direct observation, and my own active job search.
fluid

Ankit's AI Assistant

Ask anything about Ankit

Hey! I'm Ankit's AI Assistant, ask me anything about his work, experience, or skills. How can I help?