Search

30 results for “instructions” (members search the full text)

• PromptBuilderClaudeClaude Project Instructions StarterProject instructions work best when they explain how to treat uploaded material, including what to do when the answer is missing.
• PromptBuilderChatGPTDraft Instructions for a Custom GPTThe sections mirror what makes custom assistants reliable.
• PromptBuilderChatGPTHelpdesk Assistant Custom GPT InstructionsSpelling out what the GPT must not do and when it escalates is what makes a support bot safe to use.
• Q&AStarterAny assistantCan an AI assistant be tricked by hidden instructions in emails or web pages?Yes. If an assistant reads emails, web pages or documents, hidden text in them can try to give it new instructions, which is called prompt injection.
• Q&AStarterAny assistantWhy does AI keep ignoring my instructions?AI ignores instructions most often because they are buried, contradictory, too many at once, or phrased as a vague wish instead of a clear rule.
• Q&AStarterAny assistantWhy does the AI ignore my instructions and how do I fix it?Instructions get ignored when they are buried, contradictory, too numerous or phrased vaguely, or when the chat is long and early rules have faded.
• Q&AStarterAny assistantHow do I stop an AI agent from looping forever?Stop loops with hard limits in your code, not just instructions in the prompt.
• Q&AStarterClaudeHow do I use Claude Projects to stop repeating myself?Claude Projects let you group related chats with shared instructions and reference files, so you do not have to paste the same background each time.
• Q&AStarterAny assistantWhat are custom GPTs, Gems and projects, and which should I use?They are ways to save instructions and reference files so an assistant behaves consistently for a specific purpose.
• Q&AStarterAny assistantWhat is prompt injection and should I worry about it?Prompt injection is when text an AI reads, such as a web page, email or document, contains hidden instructions that try to make it misbehave, for example by leaking data or taking unwanted actions.
• Q&AStarterChatGPTWhy does ChatGPT give short, lazy answers or leave parts out?ChatGPT gives short or incomplete answers when your request is vague about length, when the task is very large, or when a long chat has crowded out your original instructions.
• GuideStarterChatGPTGetting Started with ChatGPT: A Practical First WeekSet up ChatGPT from OpenAI, learn its main features such as custom instructions, memory and custom GPTs, and build useful habits in your first week.
• PromptStarterLlamaShort Commit Message WriterShort, tightly constrained prompts like this work well with smaller local models that can lose focus in long instructions.
• PromptBuilderClaudeStructured Prompt With Tagged SectionsTagged sections keep different kinds of information clearly separated, which helps most assistants avoid mixing instructions with source text.
• GuideStarterAny assistantHow AI Assistants Actually Work (Without the Jargon)A plain-English tour of what happens when you type a message to an AI assistant, and why that explains both its strengths and its odd mistakes.
• GuideBuilderAny assistantHow to Write a System Prompt That Actually HoldsLearn the structure of a strong system prompt, how to set role, rules and format, and how to test it so your assistant or bot behaves consistently.
• GuideProAny assistantGiving Agents Tools Safely: Permissions, Limits and ApprovalsHow to design agent tools with least privilege, spending caps, confirmation steps and audit logs so a mistake stays small and reversible.
• GuideProAny assistantPrompt Injection Explained: The Attack Every AI Builder Should KnowWhat prompt injection is, how it hits chatbots and agents through documents and web pages, and layered defenses that reduce the risk.
• GuideBuilderAny assistantLong Chats, Forgetting and Memory: How to Keep AI on TrackWhy assistants lose details in long conversations, and how to use summaries, fresh chats, projects and memory features to keep context sharp.
• GuideStarterAny assistantHow AI Agents Work - The Loop, Tools and MemoryA clear mental model of an AI agent: the loop it runs, the tools it uses, what counts as memory, and where things go wrong.
• GuideProAny assistantDefending Against Prompt Injection in Your AI AppsThere is no single fix for prompt injection, but layered defenses work. Learn the practical controls: privilege limits, approvals, isolation and testing.
• GuideStarterAny assistantWhy AI Answers Are Inconsistent and What to Do About ItThe same question can get different answers. Learn the causes, from randomness to context to model changes, and practical ways to get steadier results.
• Q&AStarterAny assistantHow do I write a good system prompt?A good system prompt states the assistant's role, what it should and should not do, its tone, the output format, and what to do when it is unsure.
• Q&AStarterChatGPTWhy did ChatGPT forget what I said earlier in the conversation?ChatGPT forgets earlier details because it can only work with the text that currently fits in its context window, and in long chats older material gets trimmed, summarized or simply drowned out by newer text.
• Q&AStarterAny assistantWhy does AI give different answers to the same question each time?AI answers vary because models choose words with some randomness, so the same prompt can produce different wording or even different conclusions.
• AgentStarterChatGPTChatGPT Intake and Routing AgentA custom-GPT style front door that asks the right questions, decides where a request should go and hands over a clean summary without promising anything.
• AgentBuilderDeepSeekDeepSeek Local-Model Short-Prompt CoderA compact coding assistant prompt for open-weight models run locally, built for small context and short answers with one task at a time.
• AgentBuilderGrokGrok Live Briefing Bot StarterA small Python command-line bot that asks Grok for a briefing on a changing topic and prints confirmed, unconfirmed and not-found items.
• AgentBuilderPerplexityPerplexity Cited Answer Bot StarterA small Python command-line bot that asks Perplexity's Agent API for a cited answer and prints the search results it returned.
• AgentStarterGeminiPersonal Study TutorTeaches a topic by asking you questions, explaining gaps simply and quizzing you, rather than just handing over answers.