Task Prioritisation & Budget Control
Explicitly score, order, and budget sub-tasks so the agent spends resources where they produce the most value.
This page is the complete instruction page for one pattern called "Task Prioritisation & Budget Control." It explains the problem this pattern solves, the idea behind the solution, when you should (and should not) use it, and what happens afterward — both the good effects and the costs.
This matters because building AI agents is not just about making them clever. It is also about making them safe and predictable. Following a well-tested pattern like this one helps avoid common mistakes, and shows you exactly which safety rules and regulations it connects to, listed under "Standards Mesh" on this page.
Context
Agents doing many things at once (inbox triage, research, monitoring) need to allocate attention. Without explicit prioritisation, they round-robin or get stuck on low-value work.
Problem
Implicit prioritisation produces low-value busyness.
Forces
- Thoroughness vs focus
- User-perceived progress vs actual value
Solution
Score candidate tasks on impact × urgency × cost, with weights reflecting user or organisational preference. Maintain a ranked queue; execute in order; re-score on new information. Track and cap cumulative token/$ budget per goal.
Applicability
- Agents juggling multiple concurrent tasks
- Email, Slack, monitoring agents
- Research assistants
Anti-Patterns
- First-come-first-served queuing
- No budget ceiling
Consequences
- +Resource efficiency
- +Explicit tradeoffs exposed to user
- −Scoring function needs tuning