The DIY My Finances Decision Intelligence API gives you a hosted, privacy-first reasoning engine that computes facts, retrieves context, and explains decisions across tax, retirement, budget, investments, debt, and general finance - all through a simple API.
Personal finance is not a knowledge problem. It is a decision problem.
This is not a UX problem. It is an architecture problem.
The Decision Intelligence API combines deterministic financial computation, hybrid retrieval-augmented generation (HYBRID-RAG), and bounded AI reasoning to deliver personalized financial guidance grounded in verified facts.
This is not document chat. It is a decision system.
Most AI systems attempt to find answers in text. The Decision Intelligence API does something fundamentally different:
It computes the decision first - then explains it.
User data and documents are transformed into a verified decision state using deterministic domain engines (tax, budget, cash flow, savings, etc.). Only after the facts are established does the system retrieve semantic context and generate explanations.
Language never determines truth. It explains what has already been computed.
Personal finance imposes constraints generic AI systems were not built for. Answers must be numerically correct, outcomes depend on changing user state, trust and compliance require explainability, and privacy limits document retention. That is why DCR exists.
Traditional RAG assumes the answer already exists in documents:
The authority is no longer text. It is the computed financial state of the user. The AI does not search for an answer. It explains a verified decision.
| Property | Traditional RAG | DCR (This Platform) |
|---|---|---|
| What exists first | Documents | Decisions |
| What is retrieved | Text | Context for a state |
| What changes | Documents | User conditions |
| What must be correct | Language | Computation |
| Role of the model | Infer | Explain |
In DCR:
This is bounded reasoning.
The system still synthesizes, weighs tradeoffs, provides context, and explains implications.
But it does so within constraints defined by verified facts.
The Mental Model Shift
RAG mindset: "Find text that looks like the answer."
DCR mindset: "Compute the truth - then explain it."
We license our patent-pending decision intelligence engine (DCR) that computes truth first, then explains it - without storing your customers' documents.
You call the API. We run the intelligence layer.
No per-token or per-call math in the contract. "Normal business usage" is included.
Financial institutions retain responsibility for governance, model risk, privacy protection, and operational control. The Decision Intelligence API is designed to support those requirements through deterministic decision authority, bounded explanation, and structured execution artifacts.
This is not a chatbot transcript system. It is a replayable, verifiable decisioning layer engineered for regulated personalization.
Regulated financial institutions operate under established supervisory expectations and emerging AI risk frameworks, including:
While each institution applies its own internal controls and jurisdictional requirements, the architecture is designed to support:
Decision-Centric Reasoning (DCR) ensures that:
This allows replayability and audit inspection independent of language generation.
The platform uses commercial or institution-approved LLMs as a bounded explanation layer. Decision authority remains in deterministic DCR engines. The LLM does not compute financial outcomes and cannot override the decision contract. The architecture is model-agnostic and does not require institutions to depend on a specific model provider.
Privacy is enforced as runtime behavior, not only documentation.
Documents can be processed for extraction and then discarded. The system is designed to avoid becoming a document vault.
Hybrid-RAG operates subordinate to deterministic decisioning.
This separation prevents probabilistic inference from becoming decision authority.
A regulated decision system must answer four questions: what happened, what inputs were used, which policies were in force, and can we prove the output wasn't altered. Every run in DCR/Hybrid-RAG produces a trace record designed as audit evidence, not application logging.
A typical trace captures, at minimum:
This is the difference between "we log activity" and a verifiable system of record: the institution can replay a decision under the same versions, validate governance controls, and confirm the returned output matches the original execution - without turning raw customer documents or free-form transcripts into retained compliance liabilities.
DCR enforces deterministic replay under version control:
Compliance teams can review the structured decision state without relying on model inference.
Platform-level controls include:
Institutions retain control of:
The platform supports inspection of:
This enables governance teams to evaluate AI-assisted personalization without relying on probabilistic black-box outputs.
In scope:
Out of scope:
The system is not offered for credit underwriting or approval workflows.
POST /api/hre/ask
{
"domain": "budget",
"question": "Given my budget, can I invest more money?"
}Your current budget shows a significant overspend relative to your income, resulting in a negative savings rate. This means you are not generating free cash flow to invest more money at this time. Key Budget Insights Monthly post-tax income: $8,967 Planned monthly spending: $11,854 (33% higher than income) Savings rate: -42.0% (negative, indicating overspending) Target savings: $1,793/month (20% of income) Free-to-spend after savings: -$2,887 (deficit, no surplus cash) Discretionary spending share: 14.3% of planned spend Peer Comparison Your monthly expenses exceed peers by $3,976 (50.5% more), indicating room to reduce spending. Category-Level Spending Highlights (monthly) Category Your Spend Peer Average Notes Food $1,329 $1,329 At peer average Utilities $503 $503 At peer average Transportation $518 $518 At peer average
POST /api/hre/ask
{
"domain": "tax",
"question": "Which deductions or credits am I likely missing?"
}Your tax profile shows you are married filing jointly with an AGI of $413,446, using the standard deduction of $29,200, and claiming a Child Tax Credit of $3,300. Your total tax is $77,180 with federal withholding of $68,605, leaving $8,575 owed. Based on this, here are potential deductions or credits you might be missing or could consider: Potential Missing Deductions Itemized Deductions: Since you took the standard deduction ($29,200), check if your itemizable expenses (mortgage interest, state/local taxes, charitable donations, medical expenses) exceed this amount. If yes, itemizing could reduce taxable income further. Retirement Contributions: Maximize contributions to traditional 401(k), IRA, or other tax-deferred accounts to lower AGI and taxable income. Health Savings Account (HSA): If eligible, contributions to an HSA are deductible and reduce taxable income. Education-related Deductions: If you or dependents have education expenses, deductions or credits like the Lifetime Learning Credit or American Opportunity Credit might apply. Potential Missing Credits Additional Child Tax Credit (ACTC): You have a Child Tax Credit of $3,300; verify if you qualify for the refundable portion (ACTC) if your tax liability is low relative to the credit.
POST /api/hre/ask
{
"domain": "retirement",
"question": "Provide a summary of my retirement plan."
}Your retirement plan projects a nest egg of approximately $2.94 million at retirement, which is slightly below your target by about $40,600. With a safe withdrawal rate of 4.0%, your portfolio is expected to generate around $117,400 annually, but this leaves an income gap of roughly $40,600 per year compared to your desired retirement income. Your savings are projected to last 30 years, both nominally and inflation-adjusted. Retirement Plan Summary Projected Retirement Assets: $2,935,276 Shortfall vs Goal: -$40,611 (meaning your nest egg is slightly under your target) Safe Withdrawal Rate: 4.0% Annual Portfolio Income: $117,411 Total Annual Retirement Income: $117,411 Annual Income Gap: -$40,611 (income needed beyond portfolio withdrawals) Longevity of Savings: 30 years (nominal and inflation-adjusted) This indicates your current savings and withdrawal strategy will sustain your retirement for about 30 years but may require either increasing savings, adjusting spending goals, or supplementing income to close the income gap.
Manage API keys, usage analytics, domain activation, and support in one place.