“By October you'll have a cashflow dip. Starts when the school fee hits. Want me to plan around it?”
Planner reads 8,412 news articles before breakfast — financial, political, commodity, weather, geopolitical — ranks them for relevance to the user's portfolio and life-stage, and maintains a rolling 18-month forecast of cashflows, tax liabilities, expected life events, and macro-risk exposure. Forecast accuracy at the 90-day horizon is 87%; at 12 months it falls to 61% and she will tell you that before you ask.
Three illustrative cases. Examples of the work, not live data. Each is the kind of decision Planner closes on a typical week.
Planner projected a cashflow dip starting October — the user's school-fee payment overlapped with a quarterly advance-tax installment. Flagged in April with seven months of runway.
A user mentioned an upcoming engagement in chat. Planner modelled three budget paths — modest / standard / elaborate — and projected saving trajectories for each.
Global semiconductor news predicted a price bump on laptops. Planner told the user her planned laptop purchase would be 14% cheaper if shifted to March.
8,412 articles before breakfast. Peak hours: 04:00–10:00.
See the full 24-hour cycle →Transactions, statements, news, SMS — read into the Newsroom and the Archive.
Planner drafts a proposal. The Courtroom argues both sides. Sub-200ms.
Signed verdict + SHAP trace + counterfactual ladder out to Saver or back to you.
Hash-chained, replayable, never deleted. DPDP §12 erasure cascades clean.
Planner closes some decisions on her own. Others require a hand-off to one of the other six. The mesh is public — here are the routes Planner uses most.
A relevance classifier scores every article against your portfolio, your life-stage, your stated goals, and your recent spending. If the score is below threshold the article never reaches you. On an average day that threshold eliminates 98% of the 8,412 articles I read.
90 days, with real numbers attached. Beyond that I show ranges, not numbers, and I widen the range every month out. At 18 months I am doing shape, not magnitude. Anyone who gives you a hard 18-month number without a failure mode is selling something.
No. I forecast household cashflows, tax liabilities, goal-funding paths, and macro-risk exposure. Equity picking is a different discipline with a different failure mode. If you ask me for a stock I will route you to a registered analyst and log the handoff in the audit chain.
I ask. A short conversation that captures the expected date, the expected amount, and the flexibility on both. Then I branch the forecast into three paths — planned, compressed, delayed — and update everyone downstream. Saver adjusts buckets; Coach adjusts the monthly plan.
Same specialist. Same Courtroom-signed decisions. Available via our B2B API — priced by verdict, audited by default.