AI Tooling Cost Management
Context Scoping
Summary
An AI tool request is limited to the minimum context required for the task.
Standards
std-ai-context-scoping-01AI tool requests SHOULD contain only context relevant and reasonably necessary to complete the task.std-ai-context-scoping-02Broad, whole-repository context SHOULD be reserved for cases where narrower, targeted context has already failed.
Implements These Principles
Session Management
Summary
A new AI tool session is used for each unrelated task, and long-running sessions are reset or summarised before their context grows unbounded.
Standards
std-ai-session-management-01A new AI tool session SHOULD be started when switching to an unrelated task if the existing session history is no longer relevant.std-ai-session-management-02Developers SHOULD periodically reset or summarise long-running sessions to prevent unbounded context accumulation.
Implements These Principles
Model Selection & Reasoning
Summary
Model choice and reasoning effort are proportionate to the task's complexity.
Standards
std-ai-model-selection-reasoning-01AI tools SHOULD use automatic or cost-aware model selection by default.std-ai-model-selection-reasoning-02Maximum reasoning effort or extended-thinking modes SHOULD be reserved for genuinely complex or ambiguous tasks.
Implements These Principles
Custom Instructions & Tooling
Summary
Custom instructions contain only reusable context, and tools not required by the project remain disabled.
Standards
std-ai-custom-instructions-tooling-01Organisation-wide and project-level custom instructions SHOULD contain only context that applies across the requests that receive them.std-ai-custom-instructions-tooling-02Organisation-wide and project-level custom instructions SHOULD remain stable between requests to benefit from provider-side caching and avoid repeated cost.std-ai-custom-instructions-tooling-03Tools, extensions, or integrations not required for the current project SHOULD be disabled because their definitions may be included in every request regardless of use.
Implements These Principles
Cost Monitoring & Pricing
Summary
AI tooling cost and usage are monitored and attributed, and responsible personnel reassess practices after material vendor pricing changes.
Standards
std-ai-cost-monitoring-pricing-01Cost or usage attributable to AI tooling SHOULD be monitored.std-ai-cost-monitoring-pricing-02Cost or usage attributable to AI tooling SHOULD be attributed.std-ai-cost-monitoring-pricing-03AI tooling cost estimates SHOULD use current vendor billing and pricing models.std-ai-cost-monitoring-pricing-04Personnel responsible for AI tooling adoption MUST reassess usage practices after a material change to a vendor's billing or pricing model.
Implements These Principles
Cost Optimisation Review
Summary
Teams periodically re-measure cost-optimisation practices in their own context.
Standards
std-ai-cost-optimisation-review-01Teams SHOULD periodically measure the effect of AI cost-optimisation practices on their AI tool usage and cost.std-ai-cost-optimisation-review-02Teams SHOULD evaluate each cost-optimisation practice in their own context because its effectiveness may vary by model, workload, and codebase.