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.
- 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
- 01Intent
Classify the customer need and urgency.
- 02Retrieve
Ground the response in approved context.
- 03Act
Invoke approved tools or route to a person.
- 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.
- 01
Separate intent, retrieval, action, and evaluation.
- 02
Treat memory and tools as governed capabilities.
- 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.
AI performance metrics are owner-supplied portfolio outcomes. Architecture references describe the system pattern without disclosing internal domains or implementation details.
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