Start here
The free tool below runs entirely in this browser — no account, nothing stored or transmitted. Redact anything you would not want kept before you type it.
Open the companion tool →Why accountability is the dividing line
A general chatbot can explain what an index fund is, how compounding works, or what a fee ratio means. That is education, and it is genuinely useful. It cannot know your income, obligations, risk tolerance, or tax position, and it is not liable for a decision you make from its answer.
The moment a question becomes 'should I, with my money, in my situation' it needs someone accountable: a licensed adviser with a fiduciary or suitability duty, a tax professional, or an attorney. That is a different kind of answer, not a better worded one.
The protocol
- Write the question exactly as you asked it. The wording usually reveals whether it is general or personal.
- Ask what a chatbot cannot know here: your full financial picture, your obligations, your tax situation, your time horizon, and your tolerance for loss.
- If the answer would move money, change a tax position, or affect a retirement plan, move the question to a licensed professional.
- Ask any adviser directly how they are paid and what standard they owe you — fee-only and fiduciary are answerable questions, not marketing.
- Keep the chatbot's explanation, if it helped, as background reading to bring to that conversation.
What the tool does
Describe the money question you were about to ask and get a boundary reading: what a general assistant can explain, what it cannot know, and who owes you a duty if you act. It runs in this browser; nothing is sent or stored.
Limit first: This is a boundary-reading aid, not financial, tax, or legal advice. It cannot assess your situation and it does not recommend any product or professional.
Open the companion tool →One human next step
For anything that would move real money, talk to a licensed professional and ask how they are compensated. Your state securities regulator or the SEC can tell you whether someone's registration is current before you take advice.
Research log and safety checks
AI-assist path: not used for a verdict. The boundary is drawn on legal duty and personal data, both of which the reader can check; a model's opinion about its own reliability would be the least credible source in the exchange. §6.10: not a frontier-pace topic.
§0.5 protection result: category is financial-agent-exposure; crisis-adjacent: no; fear/urgency/scarcity toolkit used: no. The protective function is free and the paid feature is convenience only.