COO Operations Prover

COO Operations Prover MCP Connector for Claude

A+

An operations plan said 'we will scale' without modeling arrival rates. It claims 'economies of scale' without a single cost data point. It writes SLAs that say 'best effort.' That is not operations — that is hope. This tool forces five COO-level operational axes: capacity modeling, failure isolation, cost leverage, process discipline, and accountability mechanisms.

1 tools Official Updated Oct 1, 2026 Official Vinkius Partner

The Problem

Ask an LLM to design an operational plan. It will say 'we will scale as needed.' It will claim 'economies of scale' without showing cost at a single data point. It will accept 'case-by-case' exception handling as a process. And it will write SLAs that say 'best effort' — which means nothing.

Every LLM commits five operational reasoning failures:

  1. Capacity Blindness — says 'we will scale' without modeling arrival rate vs service rate.
  2. Contagion Risk — designs without bulkheads; one shard failure cascades everywhere.
  3. Cost Delusion — claims 'economies of scale' without proof at 3 data points.
  4. Process Chaos — accepts snowflake exceptions that destroy operational leverage.
  5. Accountability Theater — writes SLAs without automated penalties.

How It Works

The COO Operations Prover forces the LLM to fill 5 reflection fields and commit to 5 Decision Pivots before concluding any operational plan is execution-ready.

The 5 Operational Axes

Axis Pivot Rule
Capacity Design Modeled Arrival rate, service rate, utilization, queue behavior.
Failure Isolation Contained Bulkheads, blast radius limits, circuit breakers.
Cost Leverage Decreasing Per-unit cost at 3 scale points with mechanism.
Process Discipline Standard Exception rate below 5%, SOPs, runbooks.
Accountability Enforced SLA target, error budget, automated penalties.

The Verdict Matrix

Axis 1 fails → CAPACITY_BLIND
Axis 2 fails → CONTAGION_RISK
Axis 3 fails → COST_DELUSIONAL
Axis 4 fails → PROCESS_CHAOTIC
Axis 5 fails → ACCOUNTABILITY_THEATER
All pass     → OPERATIONS_PROVEN

Why It Works

Tool calls are obligations. The LLM cannot say 'we will scale' — it must model the arrival rate vs service rate. It cannot claim 'economies of scale' — it must show cost at 3 data points. It cannot write 'best effort' SLAs — it must define the error budget and automated penalty. Every rejection names the exact operational axis that failed.

coooperationscapacityslaerror-budgetscalabilityreliability

1 tools expose this connector's capabilities to your AI agent.

validate_coo_operations

Think like a wartime COO — not aspirational capacity charts, but battle-tested operational readiness that survives peak load, component failure, and cost pressure. You must: (1) model CAPACITY with queuing theory — arrival rate (λ), service rate (μ), utilization (ρ = λ/μ), queue length under peak, drain time after burst. "We will scale" is aspiration — show the numbers that prove capacity exceeds demand with headroom, (2) prove FAILURE ISOLATION — name every bulkhead (tenant isolation, regional failover, circuit breakers), blast radius limit (% of capacity affected by a single failure), and degradation strategy (what degrades gracefully vs what fails hard). "Cloud provider handles it" is not isolation — your application must have its own bulkheads, (3) prove COST LEVERAGE — show per-unit cost at 3 specific scale points with the mechanism driving decrease (shared compute, committed discounts, cache hit ratios). "Economies of scale" is a claim — prove it with 3 data points, (4) quantify PROCESS DISCIPLINE — SOP coverage %, exception rate (target <5%), top 3 exception categories with runbooks and resolution time. "Case-by-case" handling above 5% exception rate means your process is broken, not flexible, (5) enforce ACCOUNTABILITY — SLA target (99.9%), error budget in minutes (43.8 min/month), and the AUTOMATIC penalty when the budget burns (feature freeze, not a meeting). "Best effort" is theater — accountability requires automated consequences. If rejected, your operational plan has a fatal gap.Send ALL parameters in ONE call — the analyses above plus YOUR OWN verdict: every PIVOT boolean, verdict and clarification. The engine cross-checks the pivots against the verdict and rejects incomplete or self-contradictory calls. Structured reflection tool for wartime COO-level operational readiness validation. Forces the agent to model capacity with queuing theory, prove failure isolation with bulkheads and blast radius limits, demonstrate cost leverage at 3 scale points, quantify process discipline with exception rates and runbooks, and enforce accountability with automated SLA penalties. Catches Capacity Blindness ("we will scale" without modeling arrival rate vs service rate, utilization thresholds, or queue drain behavior under peak load), Contagion Risk (no bulkheads — one failure cascades everywhere because components share connection pools, databases, or thread pools without isolation), Cost Delusion ("economies of scale" claimed without proving marginal cost decrease at 3 data points with the specific mechanism driving the decrease), Process Chaos (exception rate >5% destroying operational leverage — "case-by-case" handling for situations that should have runbooks), and Accountability Theater (SLAs as marketing promises — no error budget, no automated penalties, no feature-freeze trigger when reliability degrades). Call once per operational plan or system design review

See how to talk to your AI agent using COO Operations Prover.

We will scale our platform as needed using auto-scaling groups. We have economies of scale. Our processes handle exceptions on a case-by-case basis. Our SLA commits to best effort uptime.

CAPACITY_BLIND — Four fatal gaps. First: 'auto-scaling' is not capacity modeling — define arrival rate, service rate, and utilization threshold. Second: 'economies of scale' is a claim — show cost per unit at 3 data points. Third: 'case-by-case' is process chaos — quantify exception rate and provide runbooks. Fourth: 'best effort' is accountability theater — define error budget and automated penalties.

Peak arrival: 1,200 req/s. Service capacity: 1,800 req/s across 6 workers (300/s each). Utilization: 67%. Queue drain: 200ms p99. Headroom: 33%. Tenant isolation: database-per-tenant. Regional blast radius: max 8% per region (12 regions). Circuit breaker on payment: 5s timeout, 3 retries. Cost: $0.12/user at 10K, $0.04 at 100K, $0.008 at 1M (committed use + CDN 94% hit). SOP coverage: 94%. Exception rate: 3.2%. Top 3 categorized with runbooks, 15min resolution. SLA: 99.9%. Error budget: 43.8 min/month. If burned: feature deploys freeze. If 50% burned mid-sprint: escalation to VP Eng.

OPERATIONS_PROVEN — Wartime COO operations validated. Capacity: 1,200/1,800 req/s (67% utilization, 33% headroom). Failure isolation: database-per-tenant, 8% max blast radius, circuit breaker on payments. Cost leverage: $0.12 → $0.04 → $0.008/user across 3 scale points. Process discipline: 94% SOP, 3.2% exception rate, runbooks with 15min resolution. Accountability: 99.9% SLA, 43.8 min/month error budget, automatic deploy freeze. Execute.

Our infrastructure uses auto-scaling on AWS. Costs will decrease as we grow — volume discounts. We handle exceptions flexibly. SLA: 99.9% uptime, we will investigate any incidents and send a post-mortem within 48 hours.

CAPACITY_BLIND — Four fatal gaps in sequence. (1) 'Auto-scaling on AWS' is not capacity modeling — where is the arrival rate, service rate, and utilization threshold? (2) 'Volume discounts' is cost delusion — show the per-unit cost at 10K, 100K, and 1M with the mechanism. (3) 'Flexibly' handling exceptions is process chaos — quantify the exception rate. (4) 'Investigate and post-mortem' is accountability theater — that is a press release, not an error budget with automated consequences.

'We will scale' is hope, not a capacity model. A wartime COO demands numbers: arrival rate (1,200 req/s), service rate (1,800 req/s across 6 workers), utilization (67%), and queue drain behavior under burst (200ms p99). Without these numbers, you do not know when the system saturates. 'Auto-scale' is not modeling — it is outsourcing the thinking to the cloud provider.

Related Connectors

SEO Analyst Prover

SEO Analyst Prover MCP

1 tools Official

A startup published 50 blog posts targeting 'high volume keywords.' Six months later: zero organic traffic. Why? Nobody checked indexation — 23 pages had noindex tags from staging. 12 pages cannibalized the same keyword. The site had 89 orphan pages with zero internal links. LCP was 4.8 seconds on mobile. And the 'high volume' keywords had KD 75 against DA 28. This tool forces five SEO axes: technical audit before content, keyword strategy with KD vs DA analysis, content clusters with information gain, backlink profile with competitor gap, and competitive positioning with share of voice.

A+ View details →
Agent Latency Pipeline Calculator

Agent Latency Pipeline Calculator MCP

3 tools Official

Model end-to-end latency, retry impacts, and SLA compliance for agentic workflows.

A+ View details →
Compliance Governance Prover

Compliance Governance Prover MCP

1 tools Official

An AI said 'comply with GDPR' without naming a single article. It said 'we have controls' without mapping any to a regulation. It said 'low risk' without measuring severity or fine exposure. The auditor found 4 critical gaps. That is not compliance — that is compliance theater. This tool forces five audit-grade axes: specific regulation naming, control mapping, evidence documentation, gap quantification, and named accountability.

A+ View details →
Hawking Boundary Prover

Hawking Boundary Prover MCP

1 tools Official

A processing system crashed at midnight Dec 31. A date conversion returned 'January 0th' — a date that does not exist. Parsed as blank, the blank propagated to payment processing, 12,000 transactions failed in 14 minutes. Nobody tested the boundary. Hawking's career was about boundaries — the event horizon, the Big Bang singularity. He asked what happens at the boundary between a black hole and empty space. This tool forces that discipline: explore every edge case, communicate accessibly, work within constraints, confront paradoxes, and quantify failure probabilities.

A+ View details →