Operator Agent Skills

The Economics of Intelligence

Source-grounded pack with Audit Intelligence Harness, Engineer Intelligence Routing, and Intelligence Allocation Plan, plus 1 more.

Use this pack when

Choose this pack when the work touches The Economics of Intelligence and you need a bounded workflow with explicit inputs, a defined output, and human review gates.

Included workflows

Choose the job in front of you.

4 source-grounded skills. Load one workflow at a time.

Audit Intelligence Harness

Use this workflow when an AI workflow or agent must be replayed and audited for ownership, verified inputs, state, permissions, model routing, human review, exceptions, fallbacks, logging, learning, and cost per accepted outcome before scaling.

Output Return an intelligence harness audit with replaysample, executiontrace, ownershipandstate, permissionsandreview, rulevsrunfindings, acceptedoutputeconomics, learningloop, riskpriorities, and scaledecision.

Engineer Intelligence Routing

Use this workflow when an operator must tier AI tasks by value and risk and define default models, prompts, context, tools, quality bars, latency budgets, review, escalation, fallback, logging, and learning rules.

Output Return an intelligence routing specification with tasktiers, qualityandlatencybars, defaultroutes, promptcontextandtools, permissionsandreview, fallbackandstoprules, loggingschema, and learningcadence.

Intelligence Allocation Plan

Use this workflow when leaders must allocate premium models, commodity models, deterministic systems, human expertise, review capacity, and infrastructure across an AI workflow portfolio to improve economics and strategic learning.

Output Return an intelligence allocation plan with portfolioinventory, premiumandcommodityroutes, humanexpertiseallocation, bindingconstraints, scenarios, capacitymoves, strategiclearning, decisionrights, and reviewthresholds.

Intelligence Cost Curve Map

Use this workflow when an AI workflow needs task-level economics across model quality, latency, accepted outputs, human review, retries, downstream correction, scale effects, and physical capacity constraints rather than blended token or vendor cost.

Output Return an intelligence cost curve with economicunit, tasksegments, routecosts, qualitylatencytradeoffs, costperacceptedoutcome, volumesensitivity, reviewandcorrectioncost, physicalconstraints, and decisionthresholds.

Human review

Keep consequential decisions explicit.

These workflows structure analysis and artifacts; they do not authorize autonomous external, personnel, financial, legal, security, or other high-impact action.

Source and files

Grounded in the complete The Economics of Intelligence series.

10 source essays · 4 usable skills · reviewed Jul 2026

Choose your reading rhythm.

Start with a weekly briefing, add daily notes, or hear only when a durable essay or library update is ready.

You've successfully subscribed to Antoine Buteau
Great! Next, complete checkout to get full access to all premium content.
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.