NJNeel JaiswalSenior Product Manager · Mint MobileAll work
06 / AI-enabled executionMint Mobile

Resolve the need, not just the message.

Shipped a GPT-based sales and support assistant with retrieval, memory, and tool skills—measured on resolution, satisfaction, and safe escalation rather than demo quality.

At a glance
Role
Senior Product Manager
Period
Mint tenure
Team
Product, Care, engineering, analytics, and operations
Customer
Sales and support customers
Surface
Conversation → resolution
  • 56%Contacts self-served
  • 3.1 → 4.44CSAT
  • −34%Escalations

02 / Operating system

Conversational AI resolution loop

  1. 01Intent

    Classify the customer need and urgency.

  2. 02Retrieve

    Ground the response in approved context.

  3. 03Act

    Invoke approved tools or route to a person.

  4. 04Evaluate

    Measure resolution, CSAT, and escalation.

03 / Problem

The constraint behind the outcome.

A production assistant needed to resolve real customer needs without turning a persuasive demo into an uncontrolled support surface.

04 / Mandate

What I was accountable for.

Move an assistant from persuasive demo to governed production product, with explicit grounding, actions, escalation, and outcome measurement.

05 / Decisions

The product choices that shaped the system.

  1. 01

    Separate intent, retrieval, action, and evaluation.

  2. 02

    Treat memory and tools as governed capabilities.

  3. 03

    Optimize for resolution and safe escalation rather than response fluency.

06 / What shipped

The product and operating system delivered.

  • Retrieval grounded in approved knowledge.
  • Memory and tool skills treated as governed capabilities.
  • Escalation paths for unsupported or higher-risk needs.
  • An evaluation loop spanning self-service, CSAT, and escalation.

07 / Tradeoffs

The boundaries that made it operable.

  • Tighter grounding reduces creative flexibility.
  • Human escalation protects quality but limits full automation.

08 / Learning

The principle I carried forward.

AI becomes a product when the team defines what the system may know, do, escalate, and measure—not when the model simply sounds fluent.

09 / Evidence

What the evidence can—and cannot—support.

Support boundary

AI performance metrics are owner-supplied portfolio outcomes. Architecture references describe the system pattern without disclosing internal domains or implementation details.

Measurement context

Owner-reported production portfolio outcomes. Definitions, evaluation sets, and internal architecture remain confidential.

  • Owner-reported outcomeContacts self-served

    A production GenAI assistant self-serves 56% of customer contacts.

    • Neel Jaiswal
  • Owner-reported outcomeCSAT

    Assistant CSAT increased from 3.1 to 4.44.

    • Neel Jaiswal
  • Owner-reported outcomeEscalations

    The assistant reduced escalations 34%.

    • Neel Jaiswal
  • Owner-reported outcomePublished evidence

    The production assistant combines retrieval-augmented generation, memory, and tool skills.

    • Neel Jaiswal