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.
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.
Set up a Claude project that reviews contracts against your checklist and produces a referenced summary, tested on three real contracts.
Build a project whose instructions define a review checklist (payment, termination, liability, IP, renewal), an output format with section references and quotes, and a rule that ambiguous clauses are quoted and listed for a lawyer. Test on three contracts; verify every reference.
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
Build five reusable prompts for one role's recurring tasks, each with variables, a reference run and a ten-case test set.
Choose one role (support, sales, marketing, ops). Identify its five most repeated writing tasks. For each, produce a prompt template with variables, a filled reference run, and a ten-case test set with rubrics and a recorded pass rate. Deliver as a folder someone in that role could use on Monday.
The four architectural decisions every agent forces and how to make them for a first production agent.
Agent frameworks differ in surface but force the same four decisions: how the loop ends, how tools fail, where state lives, and who approves side effects. This guide makes each decision for a first production agent and explains the trade-off.
Build anomaly detection on a daily metric as a n8n automation: post an alert when a daily metric moves outside its normal range, with the recent values attached.
Strip emails, phone numbers and order numbers from ticket text before it leaves your systems.
Support text carries personal data; a model call should see the problem, not the identity. Redact deterministically and keep a map to restore in the reply.
Deploy a help-desk AI agent safely by limiting it to your content and measuring resolution honestly.
Help-desk AI agents answer customers from your help centre and hand over to people when they cannot; done well they resolve the repetitive third of tickets, done carelessly they confidently mis-answer policy questions.
Build ticket auto-tag and first-response draft as a n8n automation: tag new tickets and attach a draft reply as an internal note for the agent to approve.
Trigger: Webhook from the help desk on new ticket.
Sample and score assistant-drafted replies weekly so drift is caught before customers notice it.
When: Every Friday.
1. Sample fairly
2. Score with reasons
Steps 4Tools Any assistant, Sent repliesChatGPTClaude
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