“You spent less on takeout this week. Nothing to report. Sleep well.”
Coach keeps the whole house balanced. She watches the user's budget categories against their stated intentions — groceries, transport, takeout, discretionary — and notices when a plan starts slipping before the month is over. She does not ping the user every time a category goes red. She waits for a pattern, reads it against the user's recent context, and then opens a conversation. Not a notification. A conversation.
Three illustrative cases. Examples of the work, not live data. Each is the kind of decision Coach closes on a typical week.
A user's takeout spending quietly doubled over six weeks. Coach opened a conversation — asked about stress, workload, anything going on — before proposing a smaller budget cap.
A medical bill pushed the month's discretionary over budget. Coach rebalanced silently — moved the overspend into a 6-month recovery plan and warned Saver to pause a non-essential goal.
A user stopped opening Mukodi for 11 days during a rough period. Coach noticed, didn't pester, and left one gentle check-in message with an easy reply.
Closes the budget ledger before the user goes to bed. Peak hours: 19:00–22:00.
See the full 24-hour cycle →Transactions, statements, news, SMS — read into the Newsroom and the Archive.
Coach 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.
Coach 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 Coach uses most.
Because one overage is noise. A pattern is signal. If your takeout spend jumps once, that is Saturday. If it jumps for three Saturdays and a Wednesday, that is something I should ask about. Alerts on every overage train users to ignore alerts.
Less. I soften the tone, defer the six-week review, pause the aspirational nudges, and keep the emergency scaffolding intact. I might leave one gentle check-in a week. I do not fill the app with red.
I tell you what the choice costs against your stated goals. Whether you can afford it is your call, not mine. If you buy it anyway, I rebuild the plan around the new reality — no moral commentary.
I watch where the money actually goes. After six weeks I have a real picture and the stated plan has a real picture; if they disagree, I ask which one is right. Sometimes the plan was aspirational; sometimes the spending was accidental. Either answer is fine — I just do not keep enforcing a plan that no longer matches the person.
Same specialist. Same Courtroom-signed decisions. Available via our B2B API — priced by verdict, audited by default.