Results for “agent-routing”

Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort, when choosing how to escalate a failed attempt, or when asked which model or effort a task should get. Grounded in a 2026-07 calibration, a 2026-08 coding-cost study, a 2026-09 seeded-bug repair battery, a 2026-10 Haiku 5.5 ladder priced per spawn, and a 2026-10 retry-versus-escalation ladder on 295 SWE-bench Verified tasks; Managed Agents API specifics are operational, not calibrated.

The English summary is being prepared. Showing the original description.

Author the Salesforce Configuration Workbook — the structured, reviewable handoff document an admin uses to execute a feature across Objects/Fields, Page Layouts, Profiles/PSGs, Sharing, Validation, Automation, List Views, Reports, Integrations, and Data. Triggers: 'salesforce configuration workbook', 'admin handoff document', 'implementation workbook'. NOT for object design itself (use admin/custom-field-creation, admin/lookup-and-relationship-design, agents/object-designer/AGENT.md), NOT for permission set design (use admin/permission-set-architecture, agents/permission-set-architect/AGENT.md), NOT for Flow construction (use skills/flow/* and agents/flow-builder/AGENT.md), and NOT for the deployment manifest (use skills/devops/metadata-api-retrieve-deploy). More triggers: workbook row schema, recommended_agent, recommended_skills, row_id, source_req_id, RTM linkage block, not-in-scope-this-release, descope ledger, version-lock the workbook, check_workbook.py.

The English summary is being prepared. Showing the original description.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

The English summary is being prepared. Showing the original description.

Detects task agent and complexity tier at Phase 0 orient. Invoked first in every workflow. Provider adapters select any model/runtime policy. NOT for runtime agent routing inside a single skill (see orchestration-rules.md).

The English summary is being prepared. Showing the original description.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

The English summary is being prepared. Showing the original description.

Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.

The English summary is being prepared. Showing the original description.