Skip to RoutePilot case study
PK® / RoutePilot

Independent product case study · AI operations

RoutePilot / AI inbound lead-routing workflow

Turn every inquiry into an explainable next action.

A human-gated workflow that preserves unknown company facts, classifies the request, models implementation scope from real delivery drivers, assigns a regional representative, and prepares—not sends—the operational artifacts a team needs.

Run the planning workflow Request private source review
  • 0workflow-data transmissions
  • 6visible workflow stages
  • 1required human gate
ROUTEPILOT / TRACE 01
Fixture evidenceVisible rulesNo send
Primary user
Revenue-operations and growth teams
Runtime
Browser-local deterministic planning model
Core decision
Who should review this inquiry next?
Safety boundary
No lookup, storage, submission, or send
Investment-grade operating lensRevenue operations
Executive decision

Who should own an inbound inquiry, what response clock applies, and what information must be clarified before a reply?

Primary KPITime to qualified human response

Elapsed time from inquiry receipt to the first approved response from the correct owner with required context present.

Human outcome

Prospects reach the right human sooner while sales teams spend less time re-reading, forwarding, and reconstructing inquiry context.

Outcome targets require the organization’s own baseline; the portfolio does not invent performance or ROI.Build the 30-day pilot →

01 / Working prototype

The complete decision trail, in one interaction.

Start with a tested scenario or enter an ordinary company domain. Every conclusion exposes its inputs, arithmetic, limitation, route, and next human responsibility.

Private browser demo

You may use a real-looking company and domain to test the workflow. Inputs stay in this browser tab and are not sent, stored, researched, or added to a CRM. The three .example fixtures and all named owners are fictional demonstration data; entered facts and derived estimates remain visibly separate.

  1. 1
    Load or editStart with a complete example, then change only what you know.
  2. 2
    Check assumptionsEvery field explains why it matters and shows a concrete example.
  3. 3
    Review, never auto-sendInspect the route, questions, risks, and drafts before any human action.
01 / Inquiry & commercial context

Describe the work, not just the company.

Two short sections capture the route. Four pre-filled refinements stay in one disclosure. Headcount informs routing only; the range uses visible delivery assumptions.

Step 1Who is asking?Identity fields are formatted locally and never researched or sent.
Use the person who should receive the human-reviewed reply. A name personalizes the draft but never changes the estimate.
Used only to address the local response draft.Example: Maya Chen
The demo checks only the shape of the address. It does not verify the mailbox, company, consent, or deliverability.
Format is validated locally; the address is never sent or stored.Example: maya@northstar.example
Enter the organization exactly as the contact stated it. The demo will not correct or enrich the name from the web.
Preserved as an entered fact; human verification is still required.Example: Northstar Fabrication
A domain is normalized and compared with three local .example fixtures. Unknown domains yield no industry, size, location, or buying-signal claims.
Any valid domain works. Unknown domains receive domain-derived context only—never invented research.Example: northstar.example or company.com
Step 2What outcome is needed?These facts control classification, planning range, and owner selection.
Describe the current workflow, pain, desired outcome, systems, scale, constraints, and human approval point. More concrete context produces better deterministic questions.
126/1,000Weighted signals compete across categories; ambiguous inquiries remain in discovery.Example: Automate service-request triage, connect our ERP, and keep a human approval step
Use the contact's stated current headcount, not a guessed value. Headcount is one late routing signal and is excluded from the cost calculation.
Used for routing only; employee count does not determine the estimate.Example: 420
Choose the region that should own the first human response. Region selects a named demo owner only after the team rule is resolved.
Selects regional coverage after evidence and complexity determine the team.Example: Americas for a US-led first response
Choose the smallest credible first delivery boundary. This sets the base hours before scale, integration, urgency, and risk adjustments.
Sets the base delivery-hours range; choose assessment when scope is still unclear.Example: Production-minded pilot for one workflow
Count people who need access, training, permissions, or support in the first scope. This models enablement effort, not subscription pricing.
Adds enablement, permissions, and rollout complexity—not a per-seat price.Example: 75 people in the first department
Estimate the number of cases, requests, documents, or runs in one year. Use a first-party operational count when available.
Adjusts reliability and scale effort; it is not revenue or lead value.Example: 24,000 service requests per year
Step 3 · Refine assumptionsFour pre-filled controls for integrations, timeline, risk, and budgetShow / hide

The loaded examples already contain safe demonstration values. Open this section when the inquiry has different constraints; every change remains local.

Count distinct external systems that must exchange data or trigger work. Discovery must still name owners, APIs, authentication, environments, and failure handling.
Each integration adds a transparent 40–100 hour implementation block.Example: 2 systems: CRM and ERP
Choose the expected delivery window, not the desired first reply. Accelerated work adds coordination effort but does not guarantee feasibility.
Accelerated delivery adds a 12% coordination allowance; discovery must confirm feasibility.Example: This quarter for a normal pilot
Choose yes when the workflow may affect protected data, safety, access, money, employment, legal rights, or regulated decisions. Choose unsure rather than guessing.
Yes adds assurance work. Unsure preserves uncertainty in the upper bound until discovery.Example: Yes for patient-support operations
Enter an approved or working budget only if known. It is compared after the cost range is modeled and never anchors or inflates the estimate.
Optional fit check only; leave blank when no approved range exists.Example: 175000 for a $175,000 working budget

Creates an explainable planning record, questions, risks, response draft, and team alert in this tab. It does not research, submit, email, or write to a CRM.

  1. 01
    CaptureValidate browser-local inquiry
  2. 02
    ContextNormalize domain without lookup
  3. 03
    ClassifyScore visible inquiry signals
  4. 04
    EstimateModel hours, rate, and complexity
  5. 05
    RouteUse first matching owner rule
  6. 06
    PrepareBuild previews for human review
WORKFLOW / READY

No record exists yet.

Run a scenario to see the evidence, calculation assumptions, routing decision, draft-only outputs, and human-review timer.

02 / Architecture

A production-shaped system with every adapter disconnected.

The prototype proves orchestration and interface behavior without pretending a local portfolio interaction is a deployed revenue system.

  1. 01

    Inquiry intake

    Validate company, region, rollout scope, affected users, annual volume, integrations, timeline, budget, and problem context.

    Browser-local form · no transmission
  2. 02

    Domain context

    Normalize any valid company domain. Exact demo fixtures may add context; every unknown domain remains explicitly unverified.

    No web lookup · no invented research
  3. 03

    Classify + estimate

    Score competing inquiry signals, model implementation hours from operational complexity, then apply a visible blended-rate range.

    Inspectable assumptions · budget never anchors price
  4. 04

    Route

    Evaluate regulated context and complexity before technical category, then select a regional representative for the matched team.

    Evidence-first regional policy
  5. 05

    Prepare previews

    Assemble a CRM-shaped record, response draft, and team alert as local artifacts without transmitting them.

    Preview/download/copy only
  6. 06

    Human review

    Keep the inquiry in a visible review state with an SLA clock; a person remains responsible for every external action.

    No autonomous send or status update

Reading order: inquiry intake → domain context → classify and estimate → route → prepare previews → human review. Connectors represent the local decision flow, not workflow-data transmission.

03 / Walkthrough

Watch the workflow make—and explain—a decision.

The adjacent outline repeats the demonstration stages so the content remains understandable without audio.

Product walkthrough / user-controlled playback
Written walkthrough
  1. Load or edit a scenario

    Select manufacturing, healthcare, or enterprise inputs—or enter any valid company domain.

  2. Run the decision flow

    See domain context, classification evidence, hours-and-rate math, budget fit, and regional routing.

  3. Inspect every artifact

    Review the CRM JSON, response draft, alert preview, and their no-transmission labels.

  4. Exercise the human gate

    Advance the SLA simulator and mark the inquiry reviewed locally.

04 / Technology

Implemented now. Integration seams made explicit.

The distinction matters: a credible portfolio should separate working code from a proposed production adapter.

Implemented in this prototype

  • Next.js + ReactServer-rendered case study with a focused client-side workflow.
  • TypeScriptTyped form state, result contracts, and accessible interaction states.
  • Deterministic JavaScript modelDomain context, weighted classification, scope estimates, regional routing, drafting, and SLA logic shared with tests.
  • CSS ModulesRoute-scoped responsive system with no dependency on a component library.
  • Browser Clipboard + Blob APIsExplicit local copy and JSON download actions; no hidden handoff.
  • Node test runnerExecutable fixtures validate decisions, fallbacks, thresholds, and safety language.

Production integration seams · not connected

  • Structured AI classificationA production classifier could return a schema-validated category and abstain when evidence is weak.
  • Research providerLive enrichment would need licensed sources, provenance, freshness, consent, and an unknown-data fallback.
  • CRM adapterA least-privilege integration could create or update a record only after validation and idempotency checks.
  • Email + team messagingDraft and alert delivery would require explicit authorization, rate limits, audit logs, and human approval.

05 / Evaluation

Fixture-tested outcomes, not vague confidence.

These checks execute against the same deterministic decision module used by the interactive prototype.

2/2

Domain paths verified

Exact demo fixtures enrich; arbitrary valid domains preserve unverified facts without failing or fabricating.

5/5

Category paths classified

Evaluation, automation, product, advisory, and ambiguous discovery scenarios resolve from weighted evidence.

4/4

Routing teams exercised

Trust, enterprise, technical, and general teams each win a tested scenario before regional owner selection.

3/3

SLA states verified

On-track, attention-due, and exceeded thresholds remain mutually exclusive and inspectable.

0

Lead-payload transmissions

The component contains no fetch, form action, webhook, CRM, email, or team-messaging request.

06 / Safeguards

Automation stops where accountability begins.

The demo optimizes for a useful recommendation while preserving uncertainty, consent, reversibility, and a clear owner.

01

Browser-local input boundary

Ordinary work emails and domains are accepted for realistic testing, but the form has no submission endpoint and does not store or transmit the inquiry.

02

Unknown stays unknown

Unmatched domains receive a normalized label and explicit unverified fields instead of invented company research, industry, location, size, or buying signals.

03

No pricing theater

The range starts with rollout scope and adds visible user, volume, integration, urgency, regulated-context, category, and delivery-rate assumptions. Headcount is excluded from pricing.

04

Visible routing policy

Every owner rule and priority is shown, including the selected rule and the reason it won.

05

Preview-only actions

CRM, response, and alert artifacts are clearly labeled local previews. Copy and download are the only available actions.

06

Human gate + SLA

The timer measures waiting for review; marking reviewed changes browser state only and never updates an external system.

Designed and engineered by Prasiddha Karki

Route the evidence.
Keep the human.

Run RoutePilot again Private source review