RMFU Desk

AI & workflow

After the AI pilot: when the desk still belongs to humans

Generative tools compress drafting latency; they do not by themselves compress verification. The durable desk pattern treats the model as a fast research assistant whose every sentence must point at ground truth—filings, feed ids, calculator snapshots—or be cut. When prose is cheap, provenance becomes the scarce asset; committees should reward people who slow down to attach receipts.

What actually changed

Drafting speed skyrocketed; verification workload often follows. Teams that skip verification inherit elegant lies.

Capacity planning mistake: staffing for old memo throughput without adding reviewer hours—watch queue age, not word count shipped.

Grounding patterns

Require each paragraph of machine summary to link to object ids: filing accession, data pull id, or calculator snapshot. If a link cannot be produced, the paragraph does not ship.

Use structured summaries: claim → evidence handle → confidence class (high/medium/speculative). Speculative without flag is a defect.

Human review economics

Batch machine output by risk: client-facing, IC-grade, internal scratch—different review depth per class. Do not pretend everything needs the same eyes.

Pair junior drafting with senior spot-check on highest-risk pages—invert the old pyramid if juniors lean on models hardest.

Prompt and model inventory

Version prompts like APIs; log model family and temperature for outputs that leave the building. ‘We used ChatGPT’ is not an audit trail.

Maintain a kill list of prompt patterns that historically hallucinate in your domain—ban them from external paths.

When models suggest numbers

Treat suggested figures as untrusted until replayed through deterministic desk tools. AI can propose parameters; the calculator owns the result.

Log parameter suggestions separately from accepted runs—future disputes distinguish ‘model idea’ from ‘desk decision.’

Training and culture

Reward catching errors in drafts; punish shipping unverified claims even if fast. Speed without trace is liability.

Celebrate engineers who tighten grounding UI—better checkboxes beat another policy PDF.

Vendor and data rights

Understand whether prompts and outputs may be retained by third parties; client NDAs may prohibit certain routes.

If vendors train on customer uploads by default, route sensitive drafts through enterprise contracts with explicit retention.

Red-team sampling

Weekly random sample of AI-assisted paragraphs; label grounded, over-generalized, or wrong; trend by desk and model version.

Spikes correlate with model upgrades—treat upgrades like feed migrations with replay tests.

Metrics

Track correction rate on AI-assisted memos, time saved vs verification added, and incident count tied to missing grounding.

Add ‘rescued before external’ count—organizations undervalue invisible quality work until it vanishes.

Public desk routes referenced above

Same URL discipline applies after you authenticate—bookmarkable paths, no tenant data on these pages.

  • Public calculator hub GET-shareable patterns you can mirror for every material desk run; use as the pattern for replay links.
  • Operating rhythm Template language for stages, owners, and completion rules in a mandatory morning loop.
  • Product atlas Route-level map so reviewers can open the exact module that produced a figure.
  • Guides Pair public guides with internal SOPs so training points at one narrative spine.
  • Platform framing How tenancy and public chrome split when SEO and auth walls must coexist.
  • Terms of use Stable legal URL when client-facing calculator links depart the marketing host.
  • Privacy policy Maps subprocessors and flows; keep language consistent with how you split marketing and tenancy.

Operator toolkits

Checklists and scripts you can lift into runbooks, vendor RFPs, or board appendices.

AI governance patterns for desk teams; not a statement on model safety in general.

Three-minute mental model

RMFU is one surface for reading (brief + pulse), remembering (library + drills), and stress-testing (risk, macro, scenarios). Sign in to reach your tenant desk; this public site is the story, not the datastore.

Open the full guided tour → (recommended instead of this short blurb).

Use Open desk when you already have access — you will authenticate at the gate like any other protected route.

Sign in

Live calculators vs. marketing

After sign-in, /tools hosts shareable one-page calculators (NPV, payback, Kelly, and more). This public tools hub explains what exists for crawlers and prospects.

Open desk

Why drills matter

Bookmarks decay. RMFU uses short, spaced repetitions so vocabulary and frameworks stay retrievable when you are in front of a committee or a live tape — not only when you are reading alone.

Nudge inputs

Edit fields, then Apply & refresh (or use on the card). Same payload as the public demo API.

Last response JSON

app/engines/tools/service.py

Leading lines of the real module (marketing excerpt).

"""Operator pocket tools — small pure functions used by /tools.

Each function returns a dict with the inputs echoed back, the result, and a
short interpretation sentence (in casual exec tone).
"""
from __future__ import annotations

from dataclasses import dataclass
import math
from typing import Iterable


# -------- IRR / NPV ---------------------------------------------------------

def npv(rate: float, cashflows: list[float]) -> float:
    return sum(cf / ((1 + rate) ** t) for t, cf in enumerate(cashflows))


def npv_rate_sensitivity(rate: float, cashflows: list[float], bump: float = 0.01) -> dict:
    """±bump hurdle NPV and approximate $ / 1% change in NPV (last period scale)."""
    base = npv(rate, cashflows)
    up = npv(rate + bump, cashflows)