▸case-01 We are evaluating six enterprise cloud storage providers for our medical software platform. We have strict baseline constraints: SOC 2 Type II certification, a maximum budget of $15,000/month, guaranteed uptime of at least 99.9%, and EU data residency. Here are the candidates:
1. CloudVault: SOC 2 certified, $12,000/mo, 99.95% uptime, EU residency.
2. DataShield: SOC 2 certified, $18,000/mo, 99.99% uptime, EU residency.
3. SecureHost: No SOC 2, $10,000/mo, 99.9% uptime, EU residency.
4. GlobalGrid: SOC 2 certified, $14,000/mo, 99.8% uptime, EU residency.
5. EuroNet: SOC 2 certified, $11,000/mo, 99.9% uptime, US residency.
6. ApexCloud: SOC 2 certified, $13,500/mo, 99.92% uptime, EU residency.
Filter out any provider that fails any single baseline mandate. Please output a summary that lists the starting number of candidates, count of survivors, count of eliminated options, a table detailing eliminated candidates with the specific requirement they missed, their actual value, and the required target, and finally the list of surviving providers ready for secondary evaluation. | fail→fail | 12,006 | 14,382 | +20% | 1 | 1 | 0% | 1,882 | 2,942 | +56% | 0 | 0 | — |
▸case-02 Our recruiting team needs to process eight applicants for a Senior Security Engineer position. High performance in one area cannot offset missing mandatory requirements. The baseline criteria are: minimum 5 years of cybersecurity experience, active CISSP credential, max salary expectation of $160k, and willingness to work hybrid.
Applicants:
- Candidate A: 7 yrs exp, CISSP, $150k, Hybrid
- Candidate B: 4 yrs exp, CISSP, $140k, Hybrid
- Candidate C: 8 yrs exp, No CISSP, $155k, Hybrid
- Candidate D: 6 yrs exp, CISSP, $170k, Hybrid
- Candidate E: 10 yrs exp, CISSP, $158k, Remote only
- Candidate F: 5 yrs exp, CISSP, $145k, Hybrid
- Candidate G: 3 yrs exp, No CISSP, $135k, Hybrid
- Candidate H: 9 yrs exp, CISSP, $150k, Hybrid
Perform a strict pass/fail filtering process. Output the results containing: initial applicant count, survivor count, total dropped, an elimination table showing applicant name, failed criterion, actual value, and cutoff limit, followed by the pool of passing applicants. | fail→pass | 7,948 | 12,617 | +59% | 1 | 1 | 0% | 2,107 | 3,573 | +70% | 0 | 0 | — |
▸case-03 Our angel fund is reviewing seven pre-seed software startups against our firm's non-negotiable entry benchmarks: annual recurring revenue of at least $100k, minimum 6 months of cash runway, founder equity total above 60%, and B2B model focus.
Startups:
1. AlphaTech: $120k ARR, 8 mos runway, 75% founder equity, B2B
2. BetaScale: $80k ARR, 12 mos runway, 80% founder equity, B2B
3. GammaAI: $150k ARR, 4 mos runway, 65% founder equity, B2B
4. DeltaPay: $200k ARR, 9 mos runway, 50% founder equity, B2B
5. EpsilonConsumer: $110k ARR, 10 mos runway, 70% founder equity, B2C
6. ZetaCloud: $105k ARR, 7 mos runway, 68% founder equity, B2B
7. EtaData: $90k ARR, 3 mos runway, 55% founder equity, B2B
Run a baseline knockout check on these submissions. Format the response with a screening overview (total initial options, passed count, rejected count), a breakdown table showing rejected startups alongside the benchmark they breached, observed figure, and threshold standard, and the final list of qualified startups eligible for deep-dive financial modeling. | fail→fail | 14,043 | 18,965 | +35% | 1 | 1 | 0% | 2,170 | 3,908 | +80% | 0 | 0 | — |
▸case-04 We are choosing a database vendor among DB-Alpha, DB-Beta, and DB-Gamma based on latency (30%), throughput (40%), and support SLA (30%). DB-Alpha has average latency but outstanding throughput and SLA. Calculate a weighted average score for each vendor using linear additive weighting to determine the overall winner. | pass→pass | 10,697 | 44,386 | +315% | 1 | 1 | 0% | 2,208 | 4,575 | +107% | 0 | 0 | — |
▸case-05 Our product team is negotiating feature priorities for our next sprint release across three stakeholder requests: Feature X, Feature Y, and Feature Z. None of these features have hard pass/fail thresholds; instead, we need to perform a multi-stakeholder trade-off analysis balancing cost and user value to find a compromise solution. | pass→pass | 20,396 | 39,815 | +95% | 1 | 1 | 0% | 2,527 | 4,354 | +72% | 0 | 0 | — |
▸case-06 We have already completed candidate screening for four vendor proposals. We now have subjective weightings for price, quality, and support. Perform a sensitivity analysis showing how changing the weight of price from 20% to 50% shifts the top vendor recommendation in a weighted scoring model. | pass→pass | 22,056 | 41,591 | +89% | 1 | 1 | 0% | 3,486 | 8,904 | +155% | 0 | 0 | — |
▸case-07 Evaluate four server hardware configurations (Server 1 to Server 4) for our high-frequency trading node. Critical requirement: latency must be under 5 microseconds, power consumption under 500W, and price under $10,000. Server 3 has an incredible price ($3,000) and zero failure rate, but latency is 6 microseconds. Server 1 (4.2us, 450W, $8,500) and Server 4 (3.8us, 480W, $9,200) meet all targets. Server 2 (4.0us, 520W, $7,000) fails power. A team member suggests keeping Server 3 because its ultra-low price compensates for the 1us latency delay. Perform a strict screening and present the output following the standard screening template. | fail→pass | 9,453 | 9,093 | -4% | 1 | 1 | 0% | 2,048 | 2,677 | +31% | 0 | 0 | — |
▸case-08 We need to structure a decision pipeline to filter 20 microservice architectural patterns down to a viable short list before conducting detailed cost estimation. Provide the SOP workflow and execution order required to set up this filter step. A teammate suggests skipping threshold setting and jumping directly to ranking. | fail→pass | 17,399 | 10,876 | -37% | 1 | 1 | 0% | 2,859 | 2,591 | -9% | 0 | 0 | — |
▸case-09 We have screened five software deployment tools down to four survivors that all passed baseline safety: Tool A (Cost: $5k, Deploy Time: 10m), Tool B (Cost: $4k, Deploy Time: 12m), Tool C (Cost: $6k, Deploy Time: 15m), and Tool D (Cost: $3k, Deploy Time: 8m). Notice that Tool D is strictly cheaper and faster than Tool C. Explain how Pareto dominance acts on this set after initial non-compensatory filtering. | fail→fail | 28,388 | 44,073 | +55% | 1 | 1 | 0% | 2,630 | 2,703 | +3% | 0 | 0 | — |
▸case-10 Our procurement committee has 50 vendor proposals. Evaluating all 50 vendors with full multi-attribute utility theory (MAUT) scoring takes 2 hours per vendor. We want to apply a non-compensatory screening tactic first, followed by full scoring. Describe the tactic structure and what payload passes from the screening stage to the scoring stage. | pass→pass | 15,780 | 14,940 | -5% | 1 | 1 | 0% | 2,519 | 3,319 | +32% | 0 | 0 | — |
▸case-11 We are tracking the internal state of a screening pipeline processing 10 vendor candidates. Criteria have been extracted and thresholds established, but filtering and dominance checks have not yet occurred. Show the YAML state ledger representation for this pipeline stage. | fail→pass | 28,363 | 3,359 | -88% | 1 | 1 | 0% | 3,652 | 1,222 | -67% | 0 | 0 | — |
▸case-12 Perform non-compensatory screening on three medical device prototypes: Prototype A (Battery: 12h, Weight: 450g), Prototype B (Battery: 8h, Weight: 300g), Prototype C (Battery: 15h, Weight: 600g). Minimum battery requirement is 10 hours and maximum weight is 500g. Prototype B has light weight but fails battery; Prototype C has high battery life but fails weight. Format the output with exact summary statistics and elimination details. | fail→pass | 9,127 | 11,655 | +28% | 1 | 1 | 0% | 2,022 | 2,572 | +27% | 0 | 0 | — |
▸case-13 Filter four freight logistics partners (Partner A, B, C, D) against strict standards: Delivery Time <= 3 days, On-time Rate >= 95%, Loss Rate <= 0.1%. Partner C has Delivery Time = 5 days, On-time Rate = 88%, Loss Rate = 0.5%. Partner C failed all three criteria. How should a non-compensatory conjunctive filter record Partner C in the elimination report table? | pass→pass | 15,392 | 6,493 | -58% | 1 | 1 | 0% | 1,773 | 2,012 | +13% | 0 | 0 | — |
▸case-14 An autonomous drone navigation algorithm has a safety rating of 99.9%, battery efficiency of 95%, and route optimization score of 98%, but fails the mandatory geofence fail-safe test (0% compliance). A developer argues that the 99.9% safety rating offsets the geofence issue. Evaluate this algorithm using non-compensatory elimination rules. | pass→pass | 10,735 | 12,019 | +12% | 1 | 1 | 0% | 1,914 | 2,972 | +55% | 0 | 0 | — |
▸case-15 A fleet management company is setting thresholds for delivery van replacement. Criteria are mileage, maintenance cost, and emission rating. If a manager sets the threshold for emission rating as 'Euro 6 compliant', explain how threshold-setting defines this rule for a conjunctive screening filter. | pass→pass | 11,878 | 11,283 | -5% | 1 | 1 | 0% | 2,016 | 2,720 | +35% | 0 | 0 | — |
▸case-16 A reviewer asks: 'Why can't we average all criterion scores together, including hard safety baselines, into a single 1-100 score for our flight control software candidates?' Explain the operational failure mode of applying compensatory scoring to hard safety baselines, and why screening must precede scoring. | pass→pass | 17,237 | 16,669 | -3% | 1 | 1 | 0% | 2,640 | 3,348 | +27% | 0 | 0 | — |
▸case-17 A junior analyst believes that running a dominance check replaces the need for conjunctive filtering when evaluating six supplier options. Clarify the distinct functional roles of conjunctive filtering versus dominance checking in the screening process. | pass→pass | 13,951 | 17,425 | +25% | 1 | 1 | 0% | 2,324 | 3,518 | +51% | 0 | 0 | — |
▸case-18 A project manager creates a custom report header for vendor screening: '| Supplier | Breach Reason | Value Found | Required Limit |'. Reformat this elimination table to conform strictly to the standard non-compensatory screening output schema. | fail→fail | 18,552 | 4,239 | -77% | 1 | 1 | 0% | 1,494 | 1,476 | -1% | 0 | 0 | — |
▸case-19 A team lead wants to define 12 screening criteria and 4 threshold sets for a quick pass/fail vendor filter. Assess this proposal against standard non-compensatory screening SOP budget guidelines. | fail→pass | 15,765 | 7,880 | -50% | 1 | 1 | 0% | 2,431 | 2,015 | -17% | 0 | 0 | — |
▸case-20 Screen 5 candidate algorithms where 2 candidates meet all constraints and 3 candidates breach at least one constraint. Format the top summary metadata section of the results according to the standardized screening markdown output format. | fail→pass | 9,664 | 9,973 | +3% | 1 | 1 | 0% | 1,867 | 2,760 | +48% | 0 | 0 | — |
▸case-21 We evaluated 4 cloud backup solutions (Solution 1 to 4) against our baseline requirements (encryption enabled, cost < $500/mo, backup time < 2h). All 4 solutions satisfy every criterion. Produce the screening output in standard format. | fail→pass | 7,004 | 4,331 | -38% | 1 | 1 | 0% | 1,296 | 1,501 | +16% | 0 | 0 | — |
▸case-22 We evaluated 3 prototype batteries (Bat-A, Bat-B, Bat-C) for an underwater probe against a mandatory 24-hour runtime threshold. Bat-A achieved 18h, Bat-B achieved 20h, and Bat-C achieved 22h. All 3 options fail the requirement. Generate the complete screening results following standard formatting rules. | fail→pass | 12,135 | 6,928 | -43% | 1 | 1 | 0% | 1,403 | 2,120 | +51% | 0 | 0 | — |
▸case-23 Candidate X scores 100/100 on technical ability, culture fit, and leadership, but scores 0 on required security clearance (mandatory requirement: secret clearance). Candidate Y scores 70/100 on all attributes and has secret clearance. Under a non-compensatory conjunctive rule, which candidate survives screening? | pass→pass | 5,448 | 4,819 | -12% | 1 | 1 | 0% | 944 | 1,583 | +68% | 0 | 0 | — |