The one-page brief format that lets a designer or writer produce assets without a meeting, and what each section is for.
A brief exists so that someone else can make the assets correctly the first time. Most briefs are either a paragraph of hope or a deck nobody reads. This guide sets out a one-page format where every section answers a question the maker would otherwise have to ask.
How to produce listing images that show the real product clearly, consistently, and in the formats marketplaces want.
Listing images decide whether a buyer reads the rest. This guide covers the two cases a store meets — screenshots of digital products and photographs of physical ones — with the rules that keep every image honest, consistent and usable across platforms.
Build help article suggestion on ticket close as a n8n automation: when a ticket closes, suggest the help article that would have answered it, and log the gap if none exists.
Trigger: Help desk ticket status changes to closed.
Use feed validation tools to catch listing data errors before a marketplace or ad platform rejects the feed.
Marketplaces and shopping ads ingest a product feed — a file of titles, prices, availability, images and identifiers — and reject items with missing or malformed fields; a validator checks the feed against the platform's rules before submission so rejections are fixed in bulk rather than one email at a time.
Build help article suggestion on ticket close as a n8n automation: when a ticket closes, suggest the help article that would have answered it, and log the gap if none exists.
Trigger: Help desk ticket status changes to closed.
Use feed validation tools to catch listing data errors before a marketplace or ad platform rejects the feed.
Marketplaces and shopping ads ingest a product feed — a file of titles, prices, availability, images and identifiers — and reject items with missing or malformed fields; a validator checks the feed against the platform's rules before submission so rejections are fixed in bulk rather than one email at a time.
Read a CRM export and list deals with no activity for a set number of days, sorted by value, with a suggested action column.
Stalled deals hide in a long pipeline list; a script over the weekly export surfaces them in seconds with the last note attached so the next action is obvious.
A small function that turns a model's classification into a routing decision with an explicit threshold and escalation list.
Routing on a model's category without a confidence threshold sends uncertain tickets to the wrong queue; the rule belongs in code where it can be tested.
Build back-in-stock notification as a Zapier automation: when a product's stock goes from zero to positive, email the customers who asked to be notified, once.
Trigger: Inventory sheet row updated where stock changed from 0 to above 0.
Build meeting booked to prep note as a Make automation: when a prospect books a call, research their company and post a prep note to the rep before the meeting.
Trigger: New calendar event created from the booking link.
Configure instructions, three projects and a saved-prompt file for your real work, then measure the time saved over a week.
Write custom instructions, create three projects for your three most recurring areas of work with files and instructions, and keep a file of five saved prompts with variables. Use the setup for a week and log time saved per task and edits made.
Build a read-only agent that answers questions with cited findings, within a fixed budget, and passes an evaluation set.
Build an agent with two tools — search and fetch — that answers a question with findings (each with URL and date), inferences (each with reasoning), and gaps. Enforce a budget of fifteen fetches and forty steps in code. Validate the report shape in code and reject uncited findings. Evaluate on twenty questions.
From a single tool call to a budgeted, evaluated, approval-gated agent that can be left running.
Design, build, evaluate and operate a tool-using agent with side effects gated by a person.
Skills: Defining tools with schemas and failure returns, Writing a system prompt as a contract, Enforcing budgets in code, Building an evaluation set, Gating side effects
Take a deliberately bad prompt, diagnose each of its faults, and fix them one at a time with evidence.
A colleague's prompt for writing product descriptions produces inconsistent, padded, sometimes invented output. You have the prompt and ten inputs.
Tasks 4ChatGPTClaude
Instant delivery after paymentLicence stated on every productRe-download anytime from My LibrarySecure checkout — Polar or FungiesNew products every week
Instant delivery after paymentLicence stated on every productRe-download anytime from My LibrarySecure checkout — Polar or FungiesNew products every week