The Workflow Engineer AI Kit — 4 Ready-To-Use AI Agents to Audit, Systematize & Run Your Recurring Work

From AGENTORY — ready-to-use AI Task Kits. Drop in. Power up.

Works with the AI you already have. Upload one file, tell it "Start", answer a few questions — then find the work worth fixing, turn it into a written SOP, map what can honestly be automated, and run it week after week. Every external action gated by your approval; no promised savings, ever.

Four specialist agents that take your recurring work from "it's in my head" to a written, gated, honestly-mapped system — running inside the AI you already use.

No new app. No subscription. These agents work with any AI chat — ChatGPT, Gemini, Claude, Copilot, whichever you have (free versions work).

How it works (about 5 minutes per agent, once):

1. Add the agent file to your AI chat — upload the .md file, or on a phone, open the .txt version, copy it, and paste it in.

2. Type "Start".

3. Answer the agent's questions, one at a time — your recurring tasks, your tools, your limits. That's the calibration, and it's what makes the output fit YOUR week.

4. Save the complete updated Workflow Profile each agent hands back to you — the agent keeps it current in the chat and returns it whole, never as pieces for you to assemble — and the next agent starts from your real work.

Use the agents in order — then loop weekly:

1. Workflow Auditor — builds a scored inventory of your recurring tasks from your own numbers (weekly minutes × annoyance, arithmetic shown), ranks what to fix first, records your pick with your reason, and keeps the automation backlog.

2. SOP Designer — turns the picked task into a written procedure: trigger, inputs, one-action steps, the exact prompts that run it in an AI chat, quality checks, a done-definition — then test-runs it with you and repairs what the run exposes.

3. Automation Mapper — classifies every step of the SOP (human / AI-in-chat / automation-tool / automation-tool-with-an-AI-step, with the reasons), designs the approval gates, writes the build checklist for any tool route, and always writes the manual fallback.

4. Ops Runner — runs the week: the weekly review (what ran, what broke, your own logged minutes), inbox sweeps that produce drafts only, meeting prep, and follow-up drafting — nothing sent without your approval of the exact draft.

Two ways to work — your choice, per session. Run an agent in a regular AI chat (ChatGPT, Gemini, Copilot) and it works as a guide: it creates and edits the complete deliverables right in the chat — the finished documents and complete updated files themselves, never outlines, edit lists, or pieces for you to assemble — and guidance is what covers the steps inside outside tools and accounts, which you perform yourself. Run the same file on an agentic AI — Muse, Claude Code, Devin, and similar — and it can do more: if you want, it walks you through connecting your email, calendar, files, or team chat and then carries out the steps itself, showing you each consequential action for your approval first, verifying as it goes. Same agent, same rules — what changes is what your platform lets it do. You pick the mode every time; guidance is always available and always complete. One honest boundary, by this kit's design: your Zapier/Make/IFTTT account stays yours in both modes — the Mapper directs and verifies, and you perform the build steps under your own login.

Not sure what your AI can actually do? Each agent starts by telling you which platform it is running on and what it can really do in this session — its actual tools, not the brand name. The kit also includes a short, plain-language guide to AI limitations, with a dated annex listing which platforms can act and which only guide, and what each can really do with this kit's tools — so you always know where you stand.

A realistic first session: with the Workflow Auditor you get a scored inventory of your recurring tasks and a ranked recommendation, from numbers you supplied. That is the audit — not a finished automation. The SOP, the map, and the running week come step by step after that, and this listing won't pretend systemizing your work is a 10-minute job.

What's inside:

- 4 agent files, each in .md AND .txt format (identical content — one of them always works on your device, phone included)

- My Workflow Profile — fill it in once (agents help you), paste it into any new chat, skip the interviews; it doubles as your operating record: inventory, backlog, SOP registry, automation maps, time log

- Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases

- AI Limitations Disclaimer (.md + .txt) — what AI can and cannot do, in plain language, with this kit's tools as the examples

- A step-by-step README that gets you running in minutes

- Troubleshooting & FAQ — cut-off pastes, stale tier facts, unverified facts, "why won't it build it for me": the known rough edges and their fixes

- Changelog — what changed in this version

Who it's for:

- Busy professionals and small-team leads whose week is eaten by recurring admin — reports, inbox, follow-ups, routine coordination

- People who want their recurring work written down, gated, and honestly assessed for automation — on the tools and tiers they actually have

- Anyone who has been burned by "fully automated" promises and would rather have a system that says what it can't do

Who it's NOT for:

- Anyone looking for software that runs unattended in the background — this kit never sends, posts, or builds without you

- Anyone who wants a promised number of hours saved before starting — the kit refuses that conversion on principle (see Honest limits)

- Anyone wanting to monitor what specific people on their team are doing — the agents refuse surveillance workflows, without exception

What you need:

- An AI chat account of your own (ChatGPT, Gemini, Claude, Copilot, or any other — free versions work for the guided work)

- Your recurring work, described in your own numbers — the Auditor's interview walks you through it

- Optional, only for the Mapper's tool routes: your own account with Zapier, Make, or IFTTT (any tier — the maps are sized to the tier you actually have, with its verified limits)

Honest limits:

Each agent is a text instruction file for your existing AI — it is not a trained AI model, not a separate app, and not automation software. What it can do depends on where you run it: in a chat-only AI it guides and drafts — creating and editing the complete deliverables right in the chat — and you perform only the actions inside your outside tools and accounts; on an agentic AI it can act through the tools you choose to connect — always showing you the exact action first, always with your approval before anything is sent, published, deleted, or spent, and never unattended. Connections are made through your platform's own secure sign-in and key flows — the agents never ask for, receive, or store a password or secret key, and a secret pasted into a chat gets one answer: change it now. File work done for you runs through git, so a failed step rolls back to the last verified one; actions that leave your systems (a sent message, a published post) can't be undone, which is why they're approved one by one. This kit's spine holds in both modes: every external action is gated by your approval of the exact draft or action; no workflow monitors a person; and your Workflow Profile is the only system of record. Two more limits specific to this kit: no promised savings — the Auditor's score ranks what a task costs you, and the only savings-shaped number anywhere is your own baseline vs. your logged actual minutes, printed by the Ops Runner labeled an estimate with its provenance; and tier facts are dated — Zapier/Make/IFTTT limits are stated as verified on 2026-10-30 or flagged unverified, because vendors change them without notice. The agents' worked examples follow one illustrative example persona created for this kit to show the formats end to end — an illustration, not a customer story. You check every output before you rely on it.

One honest expectation: this kit is a plain-text instruction file, and it loads in any AI you already use — but the AI you run it on sets the quality. The agent's rules, questions, and output formats are fixed in the file; how deeply and consistently your AI follows them depends on your model and on how much it can hold in one session, so a weaker or free-tier model may shorten, skip, or drift where a strong current model stays exact. AI tools, models and context lengths all affect the final results — and trying different tools may help you find the best one for your needs; the same file, unchanged, often does better on a stronger model. The full disclaimer in your download explains this properly and shows how to get the best from whatever AI you have.

Price: $49 — Standalone: all 4 agents, everything included.

Starters (ONE agent, your choice of any of the 4) are $19 each — separate listings below. Starter owners complete the set with the Upgrade, $30 — the difference.