Human Escalation Operator
Define exactly when an agent must stop and hand to a person.
2,142 engineered scaffolds across 26 categories. Pick a category, drill into a subcategory, then open one straight into the engine.
Define exactly when an agent must stop and hand to a person.
Decide which steps to automate and which must stay human.
Rules for agents to manage their own context memory during long-running tasks.
Defines the psychological and technical profile of an agent to ensure consistent tool usage.
Standardizes how agents document their 'Chain of Thought' and cite sources/tools.
Build a routing step that classifies an incoming request and dispatches it to a specialised downstream prompt, tool set and model tier.
Design a retrieval tool that writes passages to a filesystem and returns paths, plus an analyst subagent prompt that reads one passage at a time.
Set up a generate-evaluate-revise loop with explicit criteria, feedback format and stopping conditions.
Express a multi-step workflow as typed events between steps, with branching, loops, shared state and a validated event graph.
Specify an agent turn format that interleaves an explicit reasoning trace with tool actions and observations, so plans can be tracked and repaired.
Define how retrieved nodes are filtered and reordered before synthesis, and constrain the synthesiser to the surviving evidence.
Write the system instructions for a retrieval agent that plans queries, searches, analyses evidence, synthesises with citations and refuses to answer from memory.
Wire a bounded generator-validator loop inside a pipeline so malformed output is fed back for correction before continuing downstream.
Defines how an agent packages its current state when transferring a task to a different agent.
Cut agent run cost while holding output quality.
Decide what an agent remembers, for how long and why.
Assess an automation opportunity on payback, flexibility and labour impact.
Build a coordinator that delegates by transferring control to specialist sub-agents chosen from their descriptions.
Design handoffs between agents with a single owner at every step.
Design a central orchestrator that decomposes an unpredictable task at runtime, dispatches worker prompts and synthesises their returns.
Run independent agents concurrently into distinct state keys, then gather them in a following synthesis step without race conditions.
Collapse a long prompt chain into fewer, stronger steps.
Design a retrieval pipeline that favours precision over volume.
Configure a shared-context turn-taking team whose stop conditions combine a keyword signal, an external stop and a hard cap.
Decide what each agent shares on the common channel and how messages are attributed so long histories stay legible and bounded.
Design a supervisor that routes work to specialist agents using structured next-agent decisions and receives control back after each turn.
Define tool schemas an agent cannot misuse.
Design a multi-branch pipeline where a decision component routes inputs to type-specific processing paths that later rejoin.
Chain agents in a fixed order where each writes its result to a named state key that the next step reads, with validation gating.
Analyzes recruitment funnel metrics to identify bottlenecks and improve conversion from application to hire.
Draft automated replenishment triggers based on individual consumption cycles.