FIELD // KHUSHI SHAH

03 / Client Workflow Deployment

RiskLink

Deploying AI into an expert intake workflow
without replacing human judgment.

“The first conversation should collect context — not consume all the expert time.”

VOICE AICyber Risk AssessmentHUMAN HANDOFF

A "useful" first conversation reduces repetition without pretending to replace judgment.

Follow the workflow ↓

The Situation

The RiskLink team did not need an AI chatbot.

They needed a reliable way to gather foundational security context before an expert had to spend two hours on a first call — with a real client owner and a real downstream team waiting on structured handoff.

That first assessment was necessary, but repetitive and time-consuming. An average call took about 2 hours.

What a RiskLink Team Member Needed to Learn

How is the customer's environment set up?

Which security practices are already in place?

Where are the gaps or follow-up areas?

What context is needed before a human conversation?

What had to remain human

Final underwriting decisions · quote timelines · eligibility · exceptions requiring expert context

01

What the intake looked like before

The problem was not a lack of expertise. It was that human time was spent repeatedly gathering foundational information before the team could focus on higher-value judgment.

01Prospective client
02Call with RiskLink team
03Network & security questions
04Manual notes + interpretation
05Follow-up or quote workflow

The first conversation should collect context — not consume all the expert time.

The Product Insight

The first conversation
is a workflow.

It can be made more consistent, less repetitive, and easier to hand off — without making the AI pretend it can make the final decision.

02

What we chose to build first

The MVP focused on one reliable path from conversation to structured output — not a complete underwriting engine.

Voice conversation
Domain questions
Clarifying follow-ups
STRUCTURE + ASSESS
STRUCTURED JSON OUTPUT
REPORT + TEAM HANDOFF
VOICE-LED INTAKESTRUCTURED RISK MAPHUMAN FOLLOW-UP

What became reusable

The reusable capability was not only the voice agent. It was a repeatable structure for intake: domain prompts, clarification logic, structured outputs, report generation, and a safe handoff boundary.

Intentional scope

We intentionally did not try to build personalization, historical tracking, compliance mapping, advanced cross-domain intelligence, or a fully automated underwriting engine in the first version.

03

Making the risk conversation structured

The conversation needed to surface enough context across core security domains to give the RiskLink team a structured starting point for follow-up.

Access ControlsAntivirusAsset ManagementBackupsData ProtectionIncident ResponseSystem SecurityTraining &AwarenessInitial cyber-riskpicture
04

What I built

01

Understanding the intake workflow

Mapped the intake workflow with the RiskLink client owner — what their team needed before quote or underwriting.

02

Voice interaction

Implemented voice intake using OpenAI Realtime so the first interaction felt natural, not like a static questionnaire.

03

Structured outputs

Built the structured JSON output layer so conversational answers became organized assessment data.

04

Report-generation flow

Connected structured outputs to PDF report generation for team follow-up.

05

Product boundaries

Defined where the AI clarifies, answers directly, or defers to the RiskLink team.

06

Outcome

Reduced average intake call from ~2 hours to ~30 minutes using voice AI, while generating structured handoff reports.

05

Useful AI also knows when to defer.

When users asked questions outside the product's authority — quote timelines or final insurance decisions — the system did not invent certainty. It clarified the next step and handed the conversation back to the RiskLink team.

A user asks

When will I get a quote?

Can you tell me whether I qualify?

What is my final insurance decision?

The product response

“A member of the RiskLink team will follow up with you.”

RESPONSIBLE HANDOFF

The system paused at the boundary of its authority and passed the conversation to a human — every time.

06

Turning a conversation into something the team could use

Structured assessment outputs were converted into a final report through a JSON-to-template generation flow.

API STORAGEREPORT GENERATORuser_information.jsonDomain JSON FilesDOCX Templatereport_generation.pyGenerated DOCXFinal PDF Report

What This Flow Makes Possible

01

Conversation becomes structured input

02

Structured data feeds a repeatable report

03

The report creates a usable handoff for the team

What the MVP Did — and Did Not Do

The MVP did

guide a first risk conversation

capture structured answers

ask clarifying questions

organize information across eight domains

generate a report

create a human follow-up path

The MVP did not try to

replace underwriting judgment

make final insurance decisions

fully personalize every question path

map every compliance framework

predict risk outcomes

automate future steps of the customer journey

07

Proof, not decoration

The voice-led workflow changed how long intake took and what the team received before follow-up.

2 hrs → 30 min

Average intake call duration

~75%

Time saved per assessment

8

Structured domains in generated report

Team used handoff report as starting point for follow-up

08

What I would validate next

I would test how different conversation structures affected completion quality, user comfort, and how useful the resulting report was for the RiskLink team.

Testing Loop

ConversationflowCompletionqualityReportusefulnessRevisedquestions