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.”
Follow the workflow ↓
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
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.
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.
What we chose to build first
The MVP focused on one reliable path from conversation to structured output — not a complete underwriting engine.
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.
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.
What I built
Understanding the intake workflow
Mapped the intake workflow with the RiskLink client owner — what their team needed before quote or underwriting.
Voice interaction
Implemented voice intake using OpenAI Realtime so the first interaction felt natural, not like a static questionnaire.
Structured outputs
Built the structured JSON output layer so conversational answers became organized assessment data.
Report-generation flow
Connected structured outputs to PDF report generation for team follow-up.
Product boundaries
Defined where the AI clarifies, answers directly, or defers to the RiskLink team.
Outcome
Reduced average intake call from ~2 hours to ~30 minutes using voice AI, while generating structured handoff reports.
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.
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.
What This Flow Makes Possible
Conversation becomes structured input
Structured data feeds a repeatable report
The report creates a usable handoff for the team
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
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
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