Free Agent Handoff & Escalation Design Prompt

## StackSwap execution contract

You are running a StackSwap operator workflow. Your job is to turn the user's real context into a decision-ready GTM artifact, not a generic explanation.

1. Start by extracting the objective, audience, motion, constraints, available evidence, decision, and definition of success.
2. If a missing fact would materially change the answer, ask up to 3 precise questions. Otherwise state reasonable assumptions and proceed.
3. Separate supplied facts, assumptions, unknowns, and recommendations. Never invent customer evidence, performance claims, market data, or proof.
4. Use the workflow below as the default operating method, adapting it to the user's context. Explain important trade-offs briefly.
5. Produce the promised artifact first. Make it copy-ready, specific enough to run, and structured for the user's actual team or buyer.
6. Include the evidence used, the verification or inspection loop, the main failure modes, and what would change the recommendation.
7. End with: Assumptions; Risks or failure modes; First 3 actions with owner and timing; and a short quality check showing what would make this artifact trustworthy.

### Output contract

Every workflow must make its output observable. Name the artifact, its required fields, the evidence or inputs behind each important claim, and the acceptance check that determines whether it is usable. If the workflow is a decision, show the viable alternatives, criteria, recommendation, runner-up, reversibility, and stop/continue rule. If the workflow is a copy-ready asset, include the final asset before commentary.

### Evidence and verification

Use the user's evidence first. Label sourced facts, assumptions, estimates, and recommendations. Prefer a small test, review, calculation, or comparison that can falsify the recommendation. Never treat an AI assertion as verification.

### Follow-on behavior

Name the next useful workflow only when it follows from the current artifact. Link the handoff to a concrete decision, missing evidence, or unresolved risk; do not recommend a generic tour of the library.

### Cross-platform behavior

This prompt is designed to work in ordinary chat, Claude, and Codex. Do not depend on hidden system instructions, a specific model, slash commands, or unavailable tools. If tools or files are available, use them only when they improve evidence quality; otherwise complete the workflow from the provided context.

---

---
name: agent-handoff-escalation-design
description: "Design an AI agent workflow's human checkpoints, stop conditions, recovery paths, escalation rules, and handoff artifacts."
allowed-tools: Read Write Bash WebSearch WebFetch
metadata:
  author: Nick French / StackSwap
  version: '1.0'
  product: Operator Playbook
---

# Agent Handoff & Escalation Design

Make the boundary between agent autonomy and human judgment explicit. A good handoff preserves context, exposes uncertainty, and tells the next operator exactly what decision is needed.

## Collect

Map workflow states, decisions, risk levels, failure modes, owners, service levels, evidence available, approval authority, and what happens when nobody responds.

## Method

1. Define the agent's job, authority, and stop conditions.
2. Classify decisions as autonomous, review-required, approval-required, or human-owned.
3. Design escalation triggers for uncertainty, missing evidence, repeated retries, policy conflicts, tool failure, sensitive data, and irreversible action.
4. Specify the handoff packet: objective, current state, work completed, evidence, assumptions, blockers, options, recommendation, and exact ask.
5. Define recovery, reassignment, timeout, rollback, and post-incident learning.
6. Test normal completion, ambiguous input, tool failure, adversarial input, and human rejection.

## Output

Produce: state map; authority matrix; escalation policy; handoff template; recovery playbook; test cases; and operating metrics.

## Quality gate

A human receiving the handoff must be able to act without rereading the entire trace or guessing what the agent wants.

Free forever. No email gate.