Collect
Preserve traceable market, filing, news, and industry-source inputs in a versioned research snapshot.
Research that keeps evidence attached. Trace a company, constellation, market signal, or strategic question through sourced evidence, deterministic calculations, explicit gaps, and a report built for human review.
Follow five short steps. The example is illustrative, but every button leads to a real product workflow.
Start with one company, an industry, or a choice you need to make. LaurenceYang sends the question to the right workflow.
Open Ask LaurenceYangWhat supports this satellite operator’s moat, and what could weaken it?
Understand the companyBusiness, financials, and valuation
Check the riskEvidence, events, and counterpoints
Review the numbers, sources, assumptions, and missing-data notes before trusting the conclusion.
Open company researchPut companies side by side with the same fields and assumptions, so the differences are easier to explain.
Open comparison workflowA live comparison needs provider coverage for at least two companies.
Test the valuation, challenge the thesis, or study the wider market without crowding the first step.
Open advanced analysisChange the model or screen a wider set of companies.
Turn the research into a report you can review, update, and export to PDF.
Start with the workbench. Open a specialist module only when the question needs it.
Ask, research, compare, value, challenge, and save—inside one connected workspace.
Classify events, test thesis impact, and compare CEO and investor views.
Read the current evidence snapshot, changes, catalysts, and source freshness.
Track the thesis, counter-evidence, risks, and next review actions.
Focused topic pages for versioned market snapshots, trends, alerts, peers, moat, and bull/bear views.
Browse concepts, entities, relationships, and source references.
The architecture keeps evidence, calculations, explanation, and review separate. This public release uses versioned snapshots and fixed, labeled narrative examples; it does not connect to live providers or a model.
Preserve traceable market, filing, news, and industry-source inputs in a versioned research snapshot.
Normalize identifiers, cross-check sources, calculate DCF, peers, screens, and risk signals.
Turn the results into a clear summary. If no AI model is connected, show a fixed sample response instead.
Expose assumptions, freshness, missing data, and counter-evidence for human judgment.
Data, calculations, and research tools work together, so every step follows the same rules.
The deployed portfolio surface uses fixed, labeled examples. No live provider, model API, credential, or restricted Wiki full text is exposed.
This personal, non-commercial release serves only the curated static product surface. It contains versioned examples and public previews; the provider adapters, local APIs, credentials, and restricted Wiki full text stay outside the deployed artifact.
Use the Workbench to inspect the product flow, then open How It Works to review the workflow, trust controls, and contribution boundary.