Sign in Publish

Instructions for AI: prompts, contexts, output schemas and guardrails

Text to give the model to tell it what to do, how to answer and what to refuse.

contextetech

AI context to anonymize personal data in English text

AI context that replaces personal data in English text (names, emails, phones, addresses, SSNs, medical record numbers) with tags before sharing it.

InstructionFew-shot3 example(s) 22 days
contextetech

RAG prompt: check that an answer is supported by the sources

Checks a draft answer sentence by sentence against the retrieved passages and flags unsupported claims, as JSON.

Instruction2 variable(s) 15 hr
contextetech

RAG prompt: rewrite a chat question into search queries

Turns the last message of a conversation into a standalone search query plus three variants, before retrieval.

Instruction2 variable(s) 15 hr
contextetech

Guardrail: mask API keys and passwords

Guardrail that masks API keys, tokens, passwords, private keys and connection strings before a text, file or export is sent to an AI. Rules, 14 test cases…

InstructionOther 2 days
contextetech

AI prompt for an Amazon or Shopify product listing

Prompt to write a product listing for Amazon or Shopify in English: title, 5 bullet points and description, from raw product specs.

Instruction4 variable(s) 2 days
contextetech

JSON schema: classify a support ticket

JSON Schema to classify a support ticket: category, priority, sentiment, one-sentence summary and next action for the support team.

Instruction5 field(s) 2 days
contextetech

JSON schema: extract a resume

JSON Schema to extract a resume with an LLM: experience, skills, education and certifications. Leaves out age, photo and other protected data.

Instruction7 field(s) 2 days
contextetech

JSON schema: extract a U.S. invoice

JSON Schema to extract a U.S. invoice with an LLM: vendor, invoice number, dates, line items, subtotal, sales tax and total in USD.

Instruction9 field(s) 2 days
contextetech

Guardrail: mask U.S. personal data (SSN, phone, card)

Guardrail that masks U.S. personal data in AI assistant replies: SSNs, +1 phone numbers, personal emails and card numbers. Rules, 12 tests, code.

InstructionPersonal data 2 days

What is an instruction for AI?

An instruction is the text you give the model when you use it, without retraining it: a prompt, a context with examples, a schema that sets the answer format or a guardrail that says what it must refuse. It is the simplest and cheapest way to adapt an AI.