---
name: agent-workflow-design
description: Design reliable AI agent workflows with goals, state, tools, permissions, memory, handoffs, human approval, retries, timeouts, logging, evaluation, and security boundaries. Use when building agents, multi-step AI automation, tool-using assistants, background AI workers, autonomous workflows, or human-in-the-loop agent systems.
title: agent-workflow-design
canonical_url: https://skilld.dev/gh/imawais-engineer/skills/agent-workflow-design
last_updated: 2026-11-14T09:15:25.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [agents/openai.yaml](https://skilld.dev/api/skills-raw/imawais-engineer/skills/agent-workflow-design/agents/openai.yaml).
>
> If the user asked to install this Skill, run `npx skilld install imawais-engineer/skills/agent-workflow-design`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/agent-workflow-design`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/imawais-engineer/skills/agent-workflow-design) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/agent-workflow-design`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/agent-workflow-design --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/agent-workflow-design --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Agent Workflow Design

## Principle

Use an agent only when a deterministic workflow is not enough. Design the agent as a controlled state machine with explicit tools, permissions, stop conditions, and human approval points.

## Agent Design Workflow

1. Define the objective and success criteria.
2. Decide whether an agent is justified or whether a normal service/job is safer.
3. Define the workflow states, transitions, and stop conditions.
4. Define tools and the exact actions each tool may perform.
5. Define required user approvals before external side effects.
6. Define memory and persistence: what is stored, for how long, and why.
7. Define retries, timeouts, cancellation, fallback, and escalation.
8. Define logs, audit trail, cost tracking, and observability.
9. Define evals for successful, failed, unsafe, and ambiguous runs.

## Tool And Permission Rules

- Give each tool the smallest useful permission.
- Make external side effects explicit: sending messages, changing records, charging money, deploying, deleting, publishing, or contacting users.
- Require approval for high-impact or irreversible actions.
- Make tool calls idempotent when practical.
- Validate tool inputs and outputs.
- Store enough run state to resume or explain the workflow.

## Human-In-The-Loop

Add review gates for:

- Destructive operations
- Financial actions
- Security-sensitive changes
- Customer-facing messages
- Legal/compliance outputs
- Bulk updates
- Low-confidence decisions

## Implementation Order

1. Build the non-agent app workflow first when possible.
2. Add the simplest agent loop that completes the core task.
3. Add tool boundaries and approvals.
4. Add persistence, run history, and visibility.
5. Add auth, rate limits, audit logs, and abuse controls before stable release.
6. Add evals and replayable test cases.

## Done Check

Agent workflow work is done when the agent has a bounded goal, controlled tools, visible state, tested failure behavior, approval gates, auditability, and verification plus validation.
