96
Agent instructions — decision matrix
A structured decision matrix for agent instructions, structuring it as a decision-ready comparison.
Template library
2,142 engineered scaffolds across 26 categories. Pick a category, drill into a subcategory, then open one straight into the engine.
- 2,142
- templates
- 26
- categories
- 156
- subcategories
96
Agent instructions — proof-first brief
A structured proof-first brief for agent instructions, leading with the sharpest proof point first.
96
Agent instructions — quick-win sequence
A structured quick-win sequence for agent instructions, sequencing the work from quick wins to deeper changes.
96
Agent instructions — repeatable checklist
A structured repeatable checklist for agent instructions, building a checklist the team can rerun weekly.
96
Agent instructions — skim-proof draft
A structured skim-proof draft for agent instructions, writing for a sceptical reader who skims.
96
Agent instructions — trade-off analysis
A structured trade-off analysis for agent instructions, framing every trade-off against cost and effort.
96
Evaluation — decision matrix
A structured decision matrix for evaluation, structuring it as a decision-ready comparison.
96
Evaluation — proof-first brief
A structured proof-first brief for evaluation, leading with the sharpest proof point first.
96
Evaluation — quick-win sequence
A structured quick-win sequence for evaluation, sequencing the work from quick wins to deeper changes.
96
Evaluation — repeatable checklist
A structured repeatable checklist for evaluation, building a checklist the team can rerun weekly.
96
Evaluation — skim-proof draft
A structured skim-proof draft for evaluation, writing for a sceptical reader who skims.
96
Evaluation — trade-off analysis
A structured trade-off analysis for evaluation, framing every trade-off against cost and effort.
96
Guardrails — decision matrix
A structured decision matrix for guardrails, structuring it as a decision-ready comparison.
96
Guardrails — proof-first brief
A structured proof-first brief for guardrails, leading with the sharpest proof point first.
96
Guardrails — quick-win sequence
A structured quick-win sequence for guardrails, sequencing the work from quick wins to deeper changes.
96
Guardrails — skim-proof draft
A structured skim-proof draft for guardrails, writing for a sceptical reader who skims.
96
Human Escalation Operator
Define exactly when an agent must stop and hand to a person.
96
Support agent system prompt
Base system prompt for a customer support agent.
96
Tool & function calling — decision matrix
A structured decision matrix for tool & function calling, structuring it as a decision-ready comparison.
96
Tool & function calling — proof-first brief
A structured proof-first brief for tool & function calling, leading with the sharpest proof point first.
96
Tool & function calling — quick-win sequence
A structured quick-win sequence for tool & function calling, sequencing the work from quick wins to deeper changes.
96
Tool & function calling — skim-proof draft
A structured skim-proof draft for tool & function calling, writing for a sceptical reader who skims.
96
Workflow Automation Audit
Decide which steps to automate and which must stay human.
95
Agent Context Window Compression and Pruning Policy
Rules for agents to manage their own context memory during long-running tasks.
95
Agent Persona and Tool-Affinity Profile Generator
Defines the psychological and technical profile of an agent to ensure consistent tool usage.
95
Agent-to-Human Escalation and Clarification Schema
Operational rules for when and how an agent should pause and request human intervention.
95
Agentic Reasoning Trace and Evidence Attribution Policy
Standardizes how agents document their 'Chain of Thought' and cite sources/tools.
95
Agentic Sandbox Operating Guidelines and Safety Perimeter
Establishes a hardened execution environment for agents with filesystem and network access.
95
Classification Router for Heterogeneous Requests
Build a routing step that classifies an incoming request and dispatches it to a specialised downstream prompt, tool set and model tier.
95
Context-Offloading Retrieval Tool and Analyst Subagent
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.
95
Evaluator-Optimizer Refinement Loop
Set up a generate-evaluate-revise loop with explicit criteria, feedback format and stopping conditions.
95
Event-Driven Step Chain Specification
Express a multi-step workflow as typed events between steps, with branching, loops, shared state and a validated event graph.
95
Industrial Hygiene Exposure Estimator
Assesses potential chemical or physical agent exposure levels based on process parameters.
95
Interleaved Reasoning and Action Trace Template
Specify an agent turn format that interleaves an explicit reasoning trace with tool actions and observations, so plans can be tracked and repaired.
95
MCP Tool Listing Definition and Namespacing
Author server-exposed tool definitions for a protocol tool listing, with namespaced names, display titles and validating input schemas.
95
Metadata Filtering and Auto-Labelling Strategy
Design ingestion-time metadata labelling and query-time filters that narrow the search space before semantic matching.
95
Multi-Tool Dependency Graph and Execution Planner
Instructions for an agent to sequence interdependent tool calls efficiently.
95
Parallel and Compositional Call Planning Schemas
Design declarations that make independent actions callable in parallel and dependent actions chainable, then validate the resulting call plan.
95
Postprocessing and Response Synthesis Contract
Define how retrieved nodes are filtered and reordered before synthesis, and constrain the synthesiser to the surviving evidence.
95
Query Rewriting Stage for Retrieval
Insert a rewriting step that converts conversational user questions into retrieval-optimised query forms without losing constraints.
95
Retrieval Agent Workflow Instructions with Injection Defence
Write the system instructions for a retrieval agent that plans queries, searches, analyses evidence, synthesises with citations and refuses to answer from memory.
95
Retriever Routing over Heterogeneous Indexes
Specify a router that selects one or more candidate retrievers per query based on retriever metadata and query shape.
95
Self-Correcting Generation Loop with Validator
Wire a bounded generator-validator loop inside a pipeline so malformed output is fed back for correction before continuing downstream.
95
State-Aware Agent Handoff and Payload Specification
Defines how an agent packages its current state when transferring a task to a different agent.
95
Strict-Mode Function Schema Author
Produce a strict-mode-compliant function definition whose JSON Schema forbids extra properties and marks every field required.
94
Agent Cost Controller
Cut agent run cost while holding output quality.
94
Agent Evaluation Operator
Build an evaluation suite that catches regressions before users do.
94
Agent Identity and Environment Preamble Writer
Generate the opening identity/environment block of an agent prompt so the model knows who it is, where it runs and what it may assume.