All Quick Kits

A deterministic Quick Kit that grades whether an escalation arrives at somebody who can act on it, and whether their answer can change what happens. Returns REACHES SOMEONE, REACHES A QUEUE or REACHES NOBODY per path.

A deterministic Quick Kit that grades whether the verdicts you are still relying on are still good, by measuring each one's age against how fast the inputs it rests on turn over. Returns IN FORCE, AGED or VOID per verdict.

A deterministic Quick Kit that grades whether each break-glass path in your systems is accountable to a named person at the moment of use. Two dispositive answers and a five-part conjunction return ACCOUNTABLE, LOGGED ONLY or UNATTRIBUTABLE per control.

Work out which room you can actually enter before you spend a quarter finding out.

Find the pages nothing leads to.

You launched and almost nobody came.

Where did the week actually go? An hour counts as distribution only if what you made reached a person outside your company during that period — a post in drafts is building.

A 20-section AI acceptable-use policy + four appendices in one editable Word doc. SMB-ready. Built to be reviewed by your counsel.

Match your representment evidence to the reason code the bank filed and get SUBMIT-READY / STRENGTHEN / DON'T FIGHT — with a blown deadline or a missing decisive item overriding to DON'T FIGHT. Tells you which disputes to skip. One .xlsx. Not legal advice.

Vendor contracts renew themselves unless you give notice before term-end. Reads every contract on two tracks — the notice-deadline clock (ACT NOW / WINDOW OPEN / LOCKED IN) and a trap-severity score — with a window-closed gate. Catch the window before it closes. One .xlsx. Not legal advice.

FedEx and UPS refund late deliveries and billing errors — but only when you ask, inside a filing window most shippers never track. Screen your invoice shipment by shipment: the reason selects the deadline (late = 15 days, billing errors = 30) and whether the money-back guarantee matters. FILE THE CLAIM / WORTH A LOOK / LET IT GO, with worsen-only gates that drop expired or dead claims. A one-time tool you own, not a 30–50% commission service. Not legal advice.

Payment timing leaks cash three ways and most AP reviews catch one: a discount left on the table, a bill paid too early for nothing, and a discount already lost. Each invoice reads TAKE THE DISCOUNT / PAY ON TIME / PAYING TOO EARLY, headlined by real dollars. A worsen-only cash-buffer gate floors a TAKE to PAY ON TIME when your buffer is too thin to fund it. Totals your timing leak and names the biggest to fix first. One .xlsx. Not financial advice.

Generate a tailored AI policy + Excel tool register and data matrix by size & industry. Word + Excel + an offline builder. Roll it out this afternoon.

Compare human-hours vs AI for every team task — with real AI cost and setup cost — and get ✓ Automate / ⚠ Review / ✗ Skip per task.

Score A/B variants on positive reply rate (not vanity replies). 9 built-in AI prompt formulas. Aimed at the 15–25% top-quartile target.

One spreadsheet — pillars, calendar, a repurposing matrix that turns one piece into a week of platform-native posts, and 13 AI prompt blocks with an anti-slop Ship Check.

One-time .xlsx — list every tool, see paid vs used seats, flag duplicate categories, and get a keep / right-size / consolidate / cut verdict on each. Built-in example recovers $6,096/yr on a $16k stack.

For billable teams — agencies, studios, consultancies. See real utilization, the sellable bench, and a sell / hire / turn-away verdict. New Work Check before you say yes. Example team: 28 hrs/wk bench ≈ $205k/yr.

Rank clients by true profit after cost-to-serve. Find the busy-but-unprofitable accounts hiding in plain sight. Keep / reprice / fix / fire verdict per client. Example: $141.5k profit, $5,500/yr leaking, top 3 carry 86%.

True profit per SKU after returns — refunded margin, processing cost, and unrecovered stock. Find the listings that look great and quietly lose money. Keep / fix / drop verdict. Example: $28,514 lost (~30% of potential profit).

Decision kit with the math. Model a price change, see the customer loss you can absorb, and get a Raise / Hold & Test / Restructure verdict. Example: +10% raise nets +$1,200/mo even after losing 8% of customers.

Put a net dollar value on every AI tool you pay for — after subscription, amortized setup, and the oversight time most ROI math ignores — with a keep / expand / kill verdict. Example: a $1,380/mo stack nets +$320, +$1,330 after cutting two losers.

True margin on every discount — incremental vs cannibalized — with a keep / limit / kill verdict and the margin handed to full-price buyers. Example: a -$6,000 sitewide sale vs a +$6,200 new-customer code.

CAC, payback period, LTV, and LTV:CAC per acquisition channel — invest / hold / cut verdict plus the spend in cut channels. Example: referral 38:1 / 0.6mo vs influencer 0.77:1, blended CAC $212.

Grade each lead source on qualified-lead rate, cost per qualified lead, and ROAS — SCALE / FIX / CUT — with a fit gate that won't let you scale cheap junk volume however good its ROAS. Example: a ROAS-4.0 source at 8% fit gets FIX, not SCALE; $3,000 to reallocate.

Compute the max cost-per-lead before a source loses money — from your own client value and close rate — then read every paid source PROFITABLE / THIN / UNDERWATER against your line. Zero-close gate + 10-lead data floor. Example: a $14/lead source reads UNDERWATER at zero closes; $6,000/mo to reallocate.

Score your MQL and SQL definitions and your marketing-to-sales handoff on weighted criteria — TIGHT / LEAKY / BROKEN — where the weaker definition caps the score and a vague-definition gate forces BROKEN on anything that isn't measurable. One spreadsheet; your inputs, no baked-in benchmark.

Check every filename against a convention you define, get the corrected name for each file, and catch the rename that would overwrite another → CONFORMS / RENAME / COLLISION, with a collision gate that stops a clobbering rename. A malformed field shows as FIXME, never smuggled into a name. One spreadsheet, deterministic.

Join two lists that should agree on a match key and classify every row → RECONCILED / EXCEPTION / ORPHANED, with a tolerance that absorbs a one-cent rounding gap and a gate that won't call them reconciled while any row is unmatched or disagreeing. Bank vs ledger, invoices vs PO log, payroll vs timesheets. One spreadsheet.

Screen a bank or card feed before it reaches the ledger. Auto-categorize by your own keyword rules and run four anomaly checks → CLEAN / REVIEW / FLAG per row and a batch POST READY / REVIEW ROWS / HOLD, where one uncategorized row, bad date, bad amount, or duplicate holds the whole batch. No AI, deterministic. One spreadsheet.

Scrutinize an AI vendor's marketed claims before you sign, claim by claim. Mark each on verifiability + contract backing 0–3; the weaker axis sets the verdict (SUBSTANTIATED / GET IN WRITING / RED FLAG) and a high-stakes gate forces the whole vendor to WALK AWAY when an ROI or autonomy promise is both unproven and not in the contract. One .xlsx, deterministic. Grades the pitch, not people. Not legal advice.

Grade an AI-suggested price change before you publish it. Four checks — margin floor honored, elasticity sourced, competitive claim substantiated, no fabricated benchmark — return DEFENSIBLE / PRESSURE-TEST / DO NOT PUBLISH, with a gate that forces DO NOT PUBLISH on an invented benchmark or a below-floor price even when the margin math looks great. One .xlsx, deterministic. Grades the recommendation, not people; sets no price. Not financial or legal advice.

Judge every row in one list against the rows above it → UNIQUE / REVIEW / DUPLICATE, from an exact-key (email) match plus near-duplicate name/phone signals, with a CLEAN / NEEDS REVIEW / HAS DUPLICATES batch verdict. The first occurrence stays the keeper; it flags the copies and never merges. No AI, nothing uploaded.

A one-afternoon, role-based AI micro-brief for sales reps — five quizzed lessons (prospecting, outreach, discovery, objections, follow-up) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Three ship-this-week workflows. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for recruiters — five quizzed lessons (bias-checked JDs, honest outreach, lawful questions, interview prep, candidate comms) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Grades the recruiter's skill, never a candidate. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for bookkeepers — five quizzed lessons (categorizing, reconciliation prep, receipt capture, month-end flags, client notes) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. AI drafts; you keep every number. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for founders — five quizzed lessons (triage, voice-matched replies, delegation, scheduling, weekly roundup) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. AI drafts; it never sends. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for support reps — five quizzed lessons (ticket triage, on-brand replies, the honest escalation rule, KB & macro building, reply QA) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. AI drafts; a person is always available. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for executive assistants — five quizzed lessons (scheduling & calendar defense, travel, briefing prep, the exec's inbox, meeting prep & follow-up) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. AI drafts; you confirm and send. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for marketers — five quizzed lessons (campaign angles, on-brand copy, repurposing, channel-fit, honest measurement) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. AI drafts; you verify every claim and disclose #ad. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for agents — five quizzed lessons (Fair-Housing-checked listings, CMA narrative, marketing kit, lead follow-up, client comms) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Grades the agent, never a buyer. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for project managers — five quizzed lessons (status updates, meeting notes → action items, scope & change requests, risk & dependency logging, stakeholder comms) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Plus a team cohort dashboard where one REPEAT flips the team to RETRAIN. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for office managers & admins — five quizzed lessons (internal announcements, vendor & facilities coordination, meeting & event logistics, expense & document organization, onboarding & handbooks) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Plus a team cohort dashboard where one REPEAT flips the team to RETRAIN. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for operations managers — five quizzed lessons (SOPs that get followed, process docs & handoffs, vendor & supplier comms, scheduling & shift notes, incident & exception write-ups) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Plus a team cohort dashboard where one REPEAT flips the team to RETRAIN. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for financial advisors — five quizzed lessons (client meeting prep, plain-language explainers, review-letter & summary drafting, prospecting & client comms, verify & route for compliance) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Recommends nothing, scores no clients; routes every draft through firm review. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for freelancers & solopreneurs — five quizzed lessons (proposals that win, scope docs that prevent creep, client emails that keep trust, invoices & the polite chase, case studies & portfolio) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Plus a team cohort dashboard where one REPEAT flips the team to RETRAIN. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for HR generalists supporting existing staff — five quizzed lessons (policy plain-language rewrites, onboarding & handbook drafting, employee communications, PTO & benefits FAQ drafting, verify-before-you-publish) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Scores skills, not employees; not for any employment decision. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for nonprofit coordinators — five quizzed lessons (grant narrative drafting, donor thank-yous & appeals, volunteer & community comms, event & campaign copy, verify-before-you-send) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Scores skills, not people; no donor data. One .xlsx, deterministic.

A one-afternoon, role-based AI micro-brief for teachers & educators — five quizzed lessons (lesson outlines & objectives, rubric & assessment drafting, feedback & comment drafting, parent & guardian communication, verify-before-you-teach) scored CLEARED / REVISIT / REPEAT, with an advance gate where the weakest module gates the whole brief. Scores skills, not people; no student data. One .xlsx, deterministic.

Keep the AI skills you worked to build. Each skill carries a Leitner box and a last-reviewed date; the tracker returns FRESH / FADING / COLD from your own dates against the skill's expanding interval, with a critical-cold gate that escalates the week when an essential skill lapses. Fixed eval date, no AI. One .xlsx, deterministic.

Ranks unpaid invoices into Current / Remind / Chase now / Write-off review by amount, age, and risk — plus three escalating dunning emails. Example: $33,200 outstanding, $19,800 recoverable this week.

Puts a fully-loaded annual dollar figure on every recurring meeting, with a keep / trim / kill verdict and a value rating. Example: five meetings total $95,900/yr, $61,300 flagged to trim or kill.

Turns your speed-to-lead into a revenue number — extra customers and revenue faster response would capture, monthly and annual. The gap comes from your own contact-rate inputs, not a baked-in multiplier. Example: $40k/mo gap, $480k/yr.

Flags every SKU Dead / Slow / Healthy, totals the cash trapped in slow and dead stock, and estimates annual carrying cost — a per-SKU liquidation list, not a blended percentage. Example: $6,900 trapped, $1,725/yr carrying.

Puts a daily and total dollar figure on unfilled roles using the revenue-per-employee formula, then nets out the salary saved while vacant — an honest figure CFOs accept. Example: ~$1,615/day, $78,692 net across two roles.

Score a short-form hook before you post — a weighted rubric returning Ship / Tighten / Rework with an anti-clickbait cap — then log 3-second retention vs your own baseline, with no winner crowned under 1,000 views. One .xlsx.

Score an Instagram post's share-worthiness before you post — six weighted criteria (SEND-WORTHY / WEAK SIGNAL / WON'T TRAVEL) with a hard originality gate that floors watermarked reposts — then track sends & saves per reach vs your own baseline, with a thin-sample floor under 1,000 reach. One .xlsx.

Grade your link-in-bio — the router between your profile and your offer — on six weighted levers (GO LIVE / TIGHTEN / REWORK) with a focus gate that caps any page lacking a single primary action. Names the one lever to fix first. One .xlsx.

A customer's about to churn — save, pause, or let go? Three retained-margin paths from your own numbers, with a margin-floor gate that won't let you save a customer into a loss. Decide with the math, not a gut call. One .xlsx.

Grade whether your meeting's action items got handed off — owner, due date, acceptance, system of record, definition of done. An owner gate drops any unowned item; per item TRACKED / CHASE / DROPPED, rolled up to ALL TRACKED / GAPS / HANDOFF BROKEN. Grades the process, not people. One .xlsx.

Enter five numbers and project your AI spend forward across the budget year. Finds the month you blow the budget, returns ON BUDGET / TRIM NOW / BLOWOUT AHEAD with a runaway-growth gate, and gives the monthly cap to land back on budget. Deterministic, offline. One .xlsx.

Compute the fully-loaded cost per outcome for each AI workflow (tokens × runs × retry × growth ÷ outcomes) and band it PREDICTABLE / DRIFTING / TOKEN SHOCK, with a gate that forces TOKEN SHOCK when there's no usage cap and uncapped true-up. Portfolio Dashboard rolls up to the worst workflow. No baked-in per-token price. Deterministic, offline. One .xlsx.

Put a dollar figure on the AI “workslop” your team verifies and redoes — per team and org-wide, from your own numbers. Monthly and annual cost, a per-head verdict (CONTAINED / LEAKING / EPIDEMIC), and an org rollup that names the worst team. No baked-in per-employee stat. Editable thresholds, deterministic, offline. One .xlsx.

An 8-step agent at 85% per step succeeds end-to-end just 27% of the time. Reveals each workflow's true compounded success rate, catches quiet drift (observed vs. the chain math), and verdicts every agent STABLE / SHORTEN / CHECKPOINT with a fleet drift rate. Deterministic, offline. One .xlsx.

Go through a resume claim by claim — mark each claim's evidence and whether its source is reachable — and get VERIFIED / VERIFY FIRST / UNVERIFIABLE per claim, with a material-unreachable gate that holds the whole checklist on any core claim nobody can confirm. Scores the claim, not the candidate; every verdict routes to verification, never a reject. One .xlsx.

A deflection rate is easy to inflate — a bot that makes people give up "deflects" them on paper. Split each deflected bucket into genuine resolution vs hidden demand for REAL / SOFT / FALSE DEFLECTION and the real rate you can defend, with a hollow-deflection gate that catches a bot hiding demand instead of resolving it. Grades the metric claim, not people. One .xlsx.

Ranks your existing videos by impressions × CTR-gap × retention to find the few worth re-titling — Refresh / Leave / Retire against your own medians, with a conservative modeled estimate of impressions recovered. One .xlsx.

Grade a page's Core Web Vitals (LCP, INP, CLS) against published thresholds and estimate the revenue the gap is costing — GOOD / NEEDS WORK / POOR from your own field values, with the one metric to fix first. A technically sound page is a prerequisite for AI Overview inclusion. One .xlsx.

Grade your cart-recovery flow on the seven levers that drive recovered revenue — depth, timing, dynamic cart contents, discount discipline, mobile, deliverability, suppression — for a weighted 0-100 score and OPTIMIZED / UNDERPERFORMING / DORMANT, with a single-message gate that caps a one-email flow no matter how polished. Your marks, your numbers, no baked-in benchmark. One .xlsx.

Grade whether you can actually allow, throttle, or block the AI crawlers and scrapers hitting your site. Six weighted controls for a 0-100 score and READY / GAPS / EXPOSED, with an enforceability gate that reads EXPOSED when you can't enforce on non-compliant traffic and can't verify a real bot. Your marks, no baked-in benchmark. One .xlsx.

Surface every AI tool your team actually uses (amnesty, no blame) and triage which to pull into governance first. Per-tool SANCTIONED / REVIEW / PULL INTO GOVERNANCE with a dispositive gate: regulated data on a personal account makes the whole org UNGOVERNED. Structural, not scored. Grades the tools, never people. One .xlsx.

AI image generators now make visually perfect fake receipts priced ~$100 to slip under your auto-approval line — eyeballing is a dead control. Score your expense programs on six controls for CONTROLLED / SOFT SPOTS / EXPOSED, with a worsen-only two-trigger gate (no source-of-truth cross-check OR no sub-threshold monitoring → EXPOSED) that fires even at 76/100. Names the control to fix first; rolls up to ALL CONTROLLED / SOFT SPOTS PRESENT / EXPOSURE FOUND. A control self-assessment, not a fraud audit; grades the controls, never employees. One .xlsx.

The S-corp owner's two questions, answered from your own numbers: is the salary you pay yourself defensible to the IRS, and is the distribution even safe to pull? No hard-coded ratio — the 60/40 rule is folklore — so you supply the market wage for your role and it grades six weighted factors into DEFENSIBLE / THIN / RECLASSIFICATION RISK, with a worsen-only IRS-reclassification gate (zero salary, or salary below half your market wage) and a dispositive DO NOT DISTRIBUTE cash override when the draw breaches your tax reserve, working-capital floor, or S-corp proportionality — the sample's defensible 95 split still reads DO NOT DISTRIBUTE. One .xlsx. Not tax or legal advice.

Score an AI or SaaS vendor's security posture before you sign — SOC 2/ISO evidence, encryption, breach SLA, training stance, subprocessors, exit. Six weighted controls return SOLID / PRESS FOR PROOF / RED FLAG, with a disqualifier gate that forces RED FLAG when a vendor trains on your data with no opt-out or offers no exit path — even at 80/100. Grades the posture you assemble, never people. One .xlsx.

Scrutinize whether a vendor's claimed ISO/IEC 42001 evidence is real, accredited, and actually covers the AI system you're buying. Six 0/1/2 controls, a weakest-link verdict (ACCEPTED / VERIFY FIRST / REJECTED), and a dispositive gate that rejects evidence unconfirmable on both accreditation and scope. One .xlsx, deterministic. ISO does not certify — accredited bodies do; grades the evidence, never people.

When a buyer asks an AI which vendor is best and you don't come up, the sale happened without you. Run a fixed prompt battery across ChatGPT, Perplexity, Gemini, Google AI Mode, and Claude and score PRESENT / PARTIAL / ABSENT per engine via a presence-gated MIN, with the weakest engine named to fix first. Your observations, no API. One .xlsx.

Find the forms where leads silently die — broken delivery, dead thank-you pages, spam false-positives, unusable mobile forms, missing tracking. Grades your lead-capture plumbing CAPTURING / LEAKING / BLACK HOLE per form via MIN-as-headline, with a dispositive no-delivery gate. Your testing, your marks, no baked-in benchmark. One .xlsx.

Would a leaked key or a retry loop be stopped — or quietly bill you five figures overnight? Most platform budget limits are notify-only. Grade six runaway safeguards per account SAFEGUARDED / EXPOSED / RUNAWAY RISK via MIN-as-headline, with a dispositive no-hard-cutoff gate. Your setup, your marks, no benchmark. One .xlsx.

You declared a set of allowed values. Then two years happened. Paste a distinct-value query and this sorts every value into IN SET / VARIANT / OUT OF SET — telling a typo from a second status by row count, not spelling. At or above 5% of a field's rows on a variant, the field reads SET BROKEN even with zero out-of-set values. One .xlsx, three tabs, 362 live formulas.

A duplicate finder says two records look alike. This says whether you may merge them — five weighted identity signals, two disqualifiers, and a verdict of DISTINCT / SAME ENTITY / IDENTITY CONFLICT. Your declared key is weighted 30, not 100, because if it were enforced you wouldn't have candidate pairs. One .xlsx, three tabs, editable weights.

Every check your app makes, read off in three no-judgement observations — what it guards, whose computer it runs on, what it decides from — routing each to ENFORCED / TRUSTS THE BROWSER / FINE IN THE BROWSER. A server-side check that reads a browser-sent value still reads exposed. Rolls up to LINE HOLDS / LINE LEAKS / NO LINE and names the row to fix first. One .xlsx; grades the build, never a person.

Row-level security read off one row per table and per operation — because “RLS enabled” is a badge, not an answer. A policy that admits everyone still reads OPEN TABLE; a browser-reachable service-role key rewrites the whole matrix to PROJECT OPEN. Rolls up to TABLES LOCKED / GAPS IN THE POLICIES / PROJECT OPEN and names the row to fix first. One .xlsx; grades the config, never a person.

A login says who you are, never whether this record is yours — two different questions. One row per route, four observations, routing to AUTHORIZED / MEMBERSHIP IS ENOUGH / LOGGED-IN ONLY / NOBODY IS CHECKING. A signed-in-only route taking the record id from the request drops to the floor. Rolls up to PERMISSIONS HOLD / SIGNED IN IS DOING TOO MUCH / ANYONE CAN WALK IN. One .xlsx; grades the build, never a person.

Your checkout page working is not your money path working. One row per step — does money change hands, does the processor’s webhook trigger it or the browser landing on a page, where’s the amount from, would running it twice matter. Routes CONFIRMED / DISPLAY ONLY / TAKEN ON TRUST / NOT HANDLED. Rolls up to MONEY PATH HOLDS / PATH CAN BE FORGED / PATH BREAKS. One .xlsx; grades the flow, never a person.

Some keys are meant to ship in the page; some must never leave your server, and nothing about the string tells you which. One row per key: which kind, where it lives, whether it’s ever been reachable, whether it’s been rotated. Relocation is not remediation — a once-exposed secret reads ROTATE NOW wherever it now sits. Rolls up to KEYS HELD / KEYS MISPLACED / KEYS BURNED. One .xlsx; never asks for a key value.

Almost everything an app plugs into has a sandbox and a real one, and nobody wires them all in one sitting — so they drift. One row per service: which mode your work reaches, which your live app reaches, whether they share an account. Routes SEPARATED / NO SEPARATE MODES / PROD ON TEST / DEV ON LIVE. Rolls up to LINES SEPARATE / POINTING AT THE SANDBOX / WIRES CROSSED. One .xlsx; grades the wiring, never a person.

Every table holds rules — rows belong to someone, an email is unique, a price is money — and the only question is who enforces them, the table or you. One row per table read straight off your table editor. A records table with no owner column reads NOTHING TO ENFORCE AGAINST however clean the rest. Rolls up to MODEL HOLDS / YOU ARE THE CONSTRAINT / NOTHING TO BUILD ON. One .xlsx; sees no rows, grades the shape.

For the moment an AI tool hands you a change and the only button is Accept. It never judges the code — it asks the question you can answer: if this is wrong, can you get back? One row per pending change; on a schema or money change a restorable copy is required. Routes SAFE TO ACCEPT / NOTHING AT RISK / CHECKPOINT FIRST / DO NOT ACCEPT YET, rolling up to YOU CAN GET BACK / SAVE BEFORE YOU ACCEPT / ONE-WAY DOOR. One .xlsx.

The day you added a login you started holding things that belong to other people. This is an inventory of what you ended up with — it names no law and makes no legal determination. One row per field: is it a person’s information, does a feature use it, do uncontrolled copies exist, could you delete it. Deleting the row isn’t getting rid of the value if it’s also in a log. Rolls up to YOU CAN ACCOUNT FOR IT / MORE THAN YOU NEED TO HOLD / HOLDING IT FOREVER. One .xlsx; not legal advice.

Nine areas of a small app, two questions each: can you name it, and have you seen it yourself. It ranks GOING ON BELIEF below CANNOT EXPLAIN IT — a gap you admit is already on your list; a belief you never checked is the one you skip. Routes YOU CAN EXPLAIN IT / DOES NOT APPLY / CANNOT EXPLAIN IT / GOING ON BELIEF, rolling up to YOU KNOW YOUR OWN APP / YOU KNOW WHAT YOU DO NOT KNOW / GOING ON BELIEF. The line’s map — names no product. One .xlsx.