Skip to the interactive prototype
PK® / AccountBrief

Portfolio project / Evidence-first sales research

AccountBriefAutomated account-research assistant.

Turn a real company name or domain into a sourced, reviewable account brief—without turning missing data into confident fiction.

ResearchEvidenceHypothesesReviewOutreach draft
Investment-grade operating lensSales intelligence
Executive decision

Is there enough verified account evidence to plan discovery, and which unknowns should a seller investigate next?

Primary KPIResearch-to-approved-brief cycle time

Elapsed time from an approved account-research request to a human-reviewed brief ready for its stated use.

Human outcome

Sellers spend less time assembling public records and more time validating relevant questions without turning hypotheses into company facts.

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

01 / Interactive system

Research with a visible evidence boundary.

Live public research + offline fixtures
Public-source research, clearly labeled

Real-company searches use bounded identity discovery, SEC EDGAR, GLEIF, and a company’s public homepage when available. Results distinguish official records, self-published first-party context, discovery-only identity data, user goals, hypotheses, provider outages, and missing fields. No personal contacts or buying signals are invented.

Shape the deliverable

Loaded the offline synthetic Northstar Health Systems fixture.

Offline synthetic fixture

Northstar Health Systems

northstar-health.example

Fixture evidence
Organization summaryHigh confidence

Multi-site outpatient care network

This fictional fixture represents a regional healthcare operator coordinating patient access, referral intake, and revenue-cycle work across a growing clinic footprint.

EvidenceNS-01 · NS-02WarningSynthetic portfolio fixture; it does not describe a real organization.
IndustryHigh confidence

Healthcare operations

The fixture consistently describes outpatient services, patient-access workflows, and revenue-cycle operations.

EvidenceNS-01WarningClassification is valid only inside this synthetic scenario.
Estimated sizeMedium confidence

500–1,000 employees

A fictional careers snapshot and clinic directory support a range rather than an exact headcount.

EvidenceNS-02 · NS-03WarningEstimated range, not a verified employee count.
02 / Account hypotheses

Possible pain points

Pain-point hypothesisMedium confidence

Referral intake may require duplicate entry

The fixture’s operations note describes fax, portal, and phone referrals converging into one central team, suggesting avoidable re-keying and status follow-up.

EvidenceNS-01 · NS-04WarningWorkflow hypothesis; validate volume and rework in discovery.
Pain-point hypothesisMedium confidence

Eligibility checks may constrain scheduling

A synthetic job description emphasizes manual benefit verification before appointments and escalation of incomplete records.

EvidenceNS-03WarningA job description signals responsibility, not measured delay or cost.
03 / Buying group

Decision-maker role hypotheses

Role hypothesisHigh confidence

VP, Patient Access

Likely workflow owner for referral intake, scheduling quality, and access-center performance.

EvidenceNS-03 · NS-04WarningRole hypothesis only; no individual person or reporting line is asserted.
Role hypothesisMedium confidence

Chief Information Officer

Likely technical stakeholder for integration, security review, identity, and clinical-system constraints.

EvidenceNS-02WarningInfluence and purchasing authority require confirmation.
04 / Timing evidence

Buying signals, with evidence attached

Buying-signal evidenceHigh confidence

Patient-access automation role opened

The synthetic careers snapshot includes a newly listed director role responsible for workflow standardization and automation pilots.

EvidenceNS-03WarningFixture evidence only; not a live hiring signal.
Buying-signal evidenceMedium confidence

Two clinics added to the network

The fictional organization update describes expansion that could increase intake volume and process variance.

EvidenceNS-02WarningExpansion suggests possible need; it does not prove budget or purchase intent.
05 / Human discovery

Questions before conclusions

These are questions—not assertions. They turn hypotheses into a measurable discovery conversation.

  1. 01

    How many referrals arrive through each channel, and where is the same information entered more than once?

  2. 02

    Which eligibility exceptions consume the most staff time before an appointment can be confirmed?

  3. 03

    What accuracy, privacy, and human-review thresholds would an automation pilot have to meet?

  4. 04

    How would recovered capacity be measured without assuming it becomes immediate payroll savings?

06 / Executive decision

Use for product demonstration only

The fixture shows the full workflow with 100% source-indexed synthetic claims, but it does not describe a real company or current commercial opportunity.

Next best action: Use the fixture to evaluate workflow behavior, then repeat the process on a correctly resolved public organization before making a real business decision.

Evidence boundary: Wikidata may assist candidate discovery; SEC EDGAR and exact qualified-name GLEIF matches support selected official facts; bounded homepage fields remain self-published first-party context. None of these sources proves a current initiative, pain point, budget, decision-maker, or buying signal. Role suggestions, business problems, and outreach language remain hypotheses until a human verifies them; nothing is sent or saved automatically.

  1. 01

    100% current factual-claim coverage
    3 of 3 displayed factual claims point to a loaded source ID. Coverage shows whether displayed factual claims have source IDs in this brief. It does not prove that the sources are complete, current, or sufficient for a commercial conclusion.

  2. 02

    Shadow-pilot mode
    Run AccountBrief beside the current research process on a consecutive, representative account cohort. Keep existing account decisions and outreach controls unchanged while reviewers record match errors, unsupported claims, corrections, preparation time, and whether the brief was usable.

  3. 03

    Measurement
    Compare source-backed coverage, reviewer corrections, and time to an approved internal brief by company type, source coverage, and match-confidence band. Track not-found and abstention cases as intentional safety behavior.

  4. 04

    Expansion gate
    Choose targets from the organization’s measured baseline. Expand only when reviewers approve the evidence quality and time savings without a rise in identity errors, unsupported claims, privacy issues, or unreviewed outreach.

07 / Executive KPI scorecard

Measure usefulness without rewarding unsupported claims.

Operating KPIHuman-reviewed

Source-backed factual claim coverage

Definition: Displayed factual company claims with at least one traceable approved source ID ÷ all displayed factual company claims.

Decision useMeasures whether an executive can inspect the evidence behind the account narrative rather than trust unattributed prose.GuardrailKeep hypotheses and unknowns outside the numerator; source presence alone does not establish freshness, relevance, or truth.
Operating KPIHuman-reviewed

Material reviewer correction rate

Definition: Briefs requiring removal or correction of an identity, factual, timing, recipient, or evidence claim ÷ all briefs reviewed.

Decision useShows whether research output is decision-ready and which claim types or providers create avoidable rework.GuardrailDo not lower the rate by omitting decision-critical context; track correction severity and abstention separately.
Operating KPIHuman-reviewed

Median time to approved internal brief

Definition: Median elapsed work time from research start to human approval of an internal evidence brief, with the 90th percentile also reported.

Decision useMeasures preparation efficiency while preserving the human gate before CRM use or outreach.GuardrailExclude provider-wait outages from active-work time, disclose them separately, and never count copied but unreviewed text as approved.
08 / Need-aware deliverable

Prospecting email, with a human gate.

Title / subjectA research-first workflow question for Northstar Health Systems

Hello Northstar Health Systems team,


I'm researching whether there is a measurable opportunity to find one repetitive workflow that can be improved safely and measured against a baseline. Public records provide this limited context: This fictional fixture represents a regional healthcare operator coordinating patient access, referral intake, and revenue-cycle work across a growing clinic footprint.


Working hypothesis to validate: Referral intake may require duplicate entry I would validate that with Operations or transformation leader before recommending a solution or estimating value. A useful first step would be to document volume, cycle time, rework, exceptions, and required human approvals for one workflow.


Would a brief conversation be useful to determine whether there is a responsible, testable opportunity?


Use the attached source registry to verify each company fact before sharing.

Why this formatUses a conditional premise and proposes discovery, avoiding a false claim that the company has a known initiative or pain point.
Human review gate
  • Confirm the organization match and every source-backed fact.
  • Replace the role archetype with a verified recipient only after human review.
  • Remove any premise the source registry does not support.
  • Keep business outcomes conditional until a baseline is measured.
09 / Source registry

Every sourced fact points back here.

NS-01Company fixture

Synthetic service-line profile

Fictional description of services and operating model.

NS-02Company fixture

Synthetic clinic-network update

Fictional footprint and expansion update.

NS-03Hiring fixture

Synthetic careers snapshot

Fictional roles and responsibilities; not a live job board.

NS-04Research fixture

Synthetic operations interview

Fictional workflow notes created for evaluation.

Loaded source IDs: NS-01 · NS-02 · NS-03 · NS-04. Fixture content is fictional and exists only to demonstrate product behavior.

Next safe step: after a human verifies the organization and inquiry context, open RoutePilot to prepare a browser-local routing decision and review-only handoff.

02 / Accessible architecture

A pipeline built to stop unsupported claims.

Semantic HTML · CSS diagram

Read left to right on larger screens or top to bottom on mobile. The ordered list remains understandable without its visual connectors.

  1. 01

    Input boundary

    Accept a company name or public domain; normalize it, reject personal emails and private hosts, and cap request size.

  2. 02

    Entity resolution

    Prefer exact root-domain evidence, reject same-name legal-entity collisions, and cross-check SEC aliases or exact qualified GLEIF names.

  3. 03

    Evidence registry

    Preserve regulator, legal-entity, and first-party links with retrieval time; leave missing or unverified fields unknown.

  4. 04

    Need-aware drafting

    Use one evidence-aware planner to turn company context, hypotheses, gaps, and the user’s goal into the visible questions and selected deliverable.

  5. 05

    Claim guard

    Expose field-level confidence, warnings, point-in-time qualifiers, limitations, and an honest not-found path.

  6. 06

    Human review

    A person verifies the company, evidence, recipient, tone, and proposed next step before any outreach.

03 / Product walkthrough

See the research boundary in motion.

The recorded walkthrough demonstrates the offline fixture path, claim-level evidence, outreach review, and safe abstention. The live interface above now adds sourced public-company resolution.

MP4 demonstrationWritten summary below
Read the written video summary

The recording opens an offline synthetic account fixture, reviews its summary and source IDs, checks pain-point and decision-role hypotheses, reads buying-signal warnings, copies a draft for human review, then searches an unmatched company to show that unsupported claims are withheld. Live public-company lookup was added after this recording and is available in the interactive section above.

04 / Fixture evaluation

Measure the behavior that earns trust.

Deterministic evaluation set
6/6Known resolution cases

Each fixture resolves through its exact company name and canonical domain.

100%Fixture claims source-indexed

Every offline-fixture claim carries confidence, at least one source ID, and a verification warning.

0Personal contacts generated

No fixture or fallback contains an invented person, email address, or phone number.

2/2Unknown-company abstention cases

Each fallback withholds industry, size, pain points, roles, signals, and personalized outreach.

What this proves

The fixture suite verifies deterministic behavior, while mocked route checks cover entity disambiguation, same-name legal-entity rejection, SEC aliases, root-domain preference, bounded first-party structured data, provider-state separation, company-specific plans, and safe abstention. It does not prove that public records are complete or current, nor does it prove sales conversion or production readiness.

05 / Technology

Small architecture.
Strong boundaries.

  • Next.js App Router
  • React + TypeScript
  • CSS Modules
  • Deterministic fixture resolver
  • SEC EDGAR data APIs
  • GLEIF Legal Entity API
  • First-party Organization JSON-LD
  • Evidence-tier + provider-state ledger
  • Bounded identity resolution
  • Organization entity scoring
  • Source-indexed claim schema
  • Browser Clipboard API
  • Node test runner
  • Cloudflare-compatible server route

06 / Safeguards

What the system
refuses to do.

01

No fabricated contacts

The prototype never invents names, email addresses, phone numbers, or reporting relationships.

02

Bounded public website inspection

An exact public domain may supply homepage metadata or Organization JSON-LD. Fetches stay HTTPS, follow a short same-registrable-domain redirect chain, enforce time and size limits, and run behind a public-network-only fetch policy.

03

Unknown means unknown

An ambiguous or unmatched organization receives no invented facts, buying signals, people, or personalized outreach.

04

Claims stay inspectable

Public-source facts include confidence, source IDs, retrieval time, and a warning about what still needs verification.

05

Hypotheses look like hypotheses

Possible workflows and role archetypes are visibly separated from sourced company facts.

06

Human approval is final

Nothing is sent, saved to an account, or acted on automatically.

Project handoff

Evidence first.
Outreach second.

Request private source review ↗Back to all projects ↑