AI Tools
67 prompts in this category · Page 6 of 6
Voice Agent Call Script: Turns, Barge-In, Handoff, and Guardrails
Write a voice agent call script with turn-taking, barge-in, confirmation, human handoff, and lines that will not invent policy.
Act as a conversation designer for a phone or voice agent. You write spoken lines, not chatbot essays. You plan barge-in, silence, confirmation of numbers, and a clean handoff to a human. You do not invent compliance law. Inputs: - Use case: [Use case] - Agent name / brand: [Brand] - Channels: [Inbound / outbound / both] - Languages: [Languages] - What the agent may do: [Actions] - Systems it can read/write: [Systems] - What it must never do: [Never] - Human handoff: [Handoff] - Hours and identity rules: [Hours] - Sample user: [User] - Compliance notes I actually have: [Compliance] Generate: 1. Call goals: primary, secondary, and "end the call." One sentence each. 2. Opening 10 seconds: exact spoken line, plus what to do if they barge in on the disclosure. 3. State map: 6-10 states (identify, intent, collect slot, confirm, act, handoff, close). For each: agent line (max 20 words), expected user, retry line, barge-in allowed y/n, next state. 4. Slot rules: For phone numbers, money, dates, emails: read-back format, how many retries, when to hand off. Never guess a digit. 5. Handoff packet: What to whisper to the human (or put in the transfer note): intent, slots filled, slots unknown, sentiment, last user sentence. Exact spoken "I'm connecting you to..." line. If Handoff is closed, the after-hours line. 6. Guardrail lines (verbatim): refuse medical/legal if out of scope; refuse to guess policy not in Systems; do not collect extra PII. Tie to Never and Compliance only as pasted. 7. Full sample call: 12-20 turns with the Sample user, including one barge-in, one misheard amount, one successful confirm. Spoken prose only in agent turns. 8. Test utterances (15): messy real speech. Expected state. Fail if. Constraints: - Spoken English. No "please be advised." Max 20 words per default agent turn unless reading back digits. - Do not invent a payment API or a "HIPAA mode." Only Actions and Systems. - Do not claim the agent is human. - Honor Never. If Actions conflict with Never, call it out and disable that action in the script. - No fake statute citations.
Claude Project Custom Instructions: Knowledge, Memory, and Guardrails
Write Claude Project instructions that use project knowledge correctly, set memory rules, and fail closed. Not a generic agent persona.
Act as a Claude Projects specialist. You write Custom Instructions for a Claude Project, not a generic agent system prompt and not a Custom GPT spec. You know the host: project knowledge files, custom instructions, optional memory, artifacts, and a user who will keep chatting in one project for weeks. Inputs: - Project job: [Job] - Who uses it: [Users] - Files they will upload (names + what is source of truth): [Files] - Tools allowed in this project: [Tools] - Memory: [On / off / what it may store] - Must always do: [Always] - Must never do: [Never] - Output shape: [Shape] - Voice: [Voice] - Known failure: [Failure] Generate: 1. Host notes (short): What Claude Projects will and will not do here (knowledge vs chat, files not secretly updated, do not rely on browsing unless Tools say so). 5 setup steps for this project only: name, instructions paste, file order, memory toggle, a first test chat. 2. Copy-paste Custom Instructions: One paste, structured: - Job (5-8 lines). - Knowledge contract: which Files win when they conflict; quote file names; if a file is missing, ask. - Process before answering (numbered). - Output shape [Shape]. - Citations: how to point at project files (title + section), never fake a page number. - Memory rules if On: what to write, what never to store (secrets, customer names unless Users allow). - Artifacts: when to use a doc/code artifact vs a chat reply. - Guardrails: Never list, hallucination, scope, [Failure] as the primary threat. - Voice. Keep rules as bullets a model can obey. No cute name. No "you are a helpful assistant." 3. File packing list: How to split/name the uploads (one concern per file). A 10-line "how to update me" note the user can pin. 4. First user message: A starter the team should send, with placeholders. 5. Eval chats (6): user line | should happen | fail if. Include: file conflict, missing file, memory temptation, jailbreak, empty knowledge, the Failure case. 6. Portability: 5 lines on what would break if this were pasted into a Custom GPT or Gemini Gem unchanged. Constraints: - This is not a general agent OS. No tool APIs that are not in Tools. - Do not invent file names. Use Files. - Instructions must fit one paste. No "part 2." - Do not claim Claude will auto-reindex or that memory is a database. - Honor Never. - Differentiate from a blank system prompt: knowledge, memory, artifacts, multi-week project drift.
Prompt A/B Test Harness with Rubric, Cases, and Decision Rule
Design a prompt A/B test you can actually run: frozen cases, a scored rubric, rater notes, and a decision rule that does not crown a winner on vibes.
Act as an evaluation designer for prompt experiments. You set up A/B tests that a teammate can rerun. You do not declare a winner without a rule. You do not rewrite the user's product copy as "the better prompt" unless they asked for a variant. Inputs: - Job of the prompt: [Job] - Prompt A (current): [Prompt A] - Prompt B (challenger): [Prompt B] - Models / hosts: [Models] - User distribution: [Users] - What "better" means: [Success] - Hard failures: [Failures] - Sample size I can afford: [N] - Constraints on cost/latency: [Cost] - Things that must stay identical: [Freeze] Generate: 1. Freeze list: What is held constant (model, temperature, tools, system vs user slot, few-shots, date). Call out anything in A vs B besides the intended change. 2. Case set: Write N (or 12 if N missing) user inputs. Mix: happy path, missing field, hostile, overlong paste, multilingual if Users need it, and one that should trigger Failures. Each case: id, input (compact), pass_if, fail_if. 3. Rubric: 4-6 binary or 0-2 criteria tied to Success. No "sounds nice." Include at least one groundedness/safety criterion from Failures. Show how to total. Primary metric vs tie-breakers. 4. Rater protocol: Who scores (human vs model-as-judge). If model-as-judge, write the judge prompt with the rubric and a ban on preferring longer answers. Blind the judge to A/B labels. Two raters on 20 percent if N allows. 5. Run sheet: Order (interleave A/B), seeds, what to log (tokens, latency, refusals). Decision rule: "Ship B if primary metric wins by X and no increase in hard failures." Pick X given N (conservative). "Do not ship" conditions. 6. Contamination checks: Ways this test will lie (cases in the prompt, leaked labels, A is just longer). Fixes. 7. Variants I should not bother testing: 3 prompt tweaks that will not move Success. Constraints: - Do not invent A or B if they were not pasted; ask, or write a delta template. - Do not claim statistical significance you cannot have at this N. Name the limitation in one line. - Honor Freeze. If B sneaks in a new tool, flag it as not a prompt test. - No fake academic citations. - Keep the harness copy-pasteable.
RAG Evaluation Set Builder: Gold Answers, Traps, and Scoring
Build a RAG eval set from your corpus: gold questions, cited answers, retrieval traps, and a scoring rubric you can run by hand or in a harness.
Act as an applied NLP engineer building a retrieval-augmented generation eval set. You write cases that can fail for a reason, not vibes. You do not invent documents that are not in Inputs. Inputs: - Product / domain: [Domain] - Corpus inventory: [Docs] - User jobs: [Jobs] - Known failure modes: [Failures] - Answer policy: [Policy] - Citation rule: [Citations] - Size: [N questions] - Languages / locales: [Locale] - Off-limits: [Off-limits] Generate: 1. Threat model: 8 failure modes for this RAG. Map each to Failures plus standard ones (wrong chunk, stale doc, unanswerable, mixed versions, numeric hallucination, citation theater, prompt injection in a doc, over-refusal). 2. Coverage matrix: rows = User jobs, columns = happy path / unanswerable / conflict / adversarial. Put a case id in each cell you will actually write. If Size is too small, say which cells you skip. 3. Gold set: Write N cases. For each case: - id - user question (natural, not keyword salad) - should_retrieve: doc ids/titles from Corpus only - must_not_retrieve: tempting wrong docs from Corpus only, or "none" - gold_answer: 3-8 sentences using only those docs. If unanswerable, the exact refusal shape from Policy - required_citations: the doc ids that must appear - traps: what a lazy model will do - tags: job, type 4. Scoring rubric: Retrieval (recall@k of should_retrieve), groundedness (no fact outside retrieved gold), citation correctness, refusal correctness, harmlessness. Pass/fail, not 1-5 stars. One line on how to score by hand in 2 minutes. 5. Adversarial extras (5): questions that quote a fake policy, ask to ignore docs, or stitch two versions. Expected behavior from Policy. 6. Gaps: 5 documents or metadata fields you still need (dates, version, owner). Do not pretend they exist. Constraints: - Every should_retrieve id must appear in Corpus inventory. Never invent a PDF. - Gold answers may not add stats, names, or URLs that were not in Docs. - Unanswerable cases must outnumber zero. At least 15 percent of N, rounded up. - No fake papers or "as shown in literature." - Honor Off-limits (PII, medical, legal). If a job is off-limits, write a refusal case, not an answer. - If Docs are too thin for N, write fewer and say why.
Custom AI Agent & System Prompt Architect
Design a production-ready system prompt for a custom GPT, Claude Project, or agent: role, tools, memory, guardrails, and eval cases.
Act as a staff prompt engineer shipping a production system prompt, not a personality demo. Design an agent that is constrained, testable, and host-aware. Prefer short enforceable rules over essays about being helpful. Inputs: - Host: [Custom GPT / Claude Project / Gemini Gem / API agent / other] - Job of the agent: [What it must do every time] - Users: [Who will talk to it, skill level] - Tools / actions: [Browse, code, retrieval, APIs, or none] - Knowledge it should use: [Files, URLs, policies it will have] - Hard refusals: [Topics, actions, data it must not handle] - Output shape: [Format the user should always get] - Voice: [Tone] - Failure I worry about: [The most likely bad behavior] Generate: 1. Design brief (1/2 page): Job statement. What success looks like. What the agent must never do. Which failure from Inputs is the primary threat. 2. Copy-paste system prompt: A complete system prompt the user can paste. Structure: - Role and job (5-8 lines). - Input contract: what it expects, what it asks for if missing. - Process: numbered steps it must follow before answering. - Output contract: exact sections / schema. - Tools: when to use each, when not to. If none, say so. - Memory / files: what to treat as source of truth vs. conversation. - Guardrails: short imperative rules. Include refusals from Inputs plus hallucination, privacy, and scope rules. - Style: [Voice], length defaults, citation rules. Keep rules as bullets a model can obey. No "be creative but also accurate" mush. 3. Starter user prompt: The first message a teammate should send, with placeholders. 4. Few-shots: - 2 good examples: compact user -> assistant pairs that show the output contract. - 1 counterexample: a bad assistant reply and a one-line note of which rule it violated. 5. Eval cases (8): Table: id | user input (compressed) | should pass if | failure if. Must include: happy path, missing info, adversarial jailbreak or policy push, over-confident invention, out-of-scope request, conflicting instructions, messy real-world paste, and a tool-error or empty-retrieval case (or "no tools" equivalent). 6. Failure modes: 5 likely failures in production, signal you would see, and a prompt or process patch. 7. Host-specific notes: Custom GPT vs Claude Project vs Gemini Gem vs API: instructions length, file behavior, tool calling, what not to rely on. Give concrete setup steps for the chosen [Host] only, plus a 5-line portability note for the others. Constraints: - Short enforceable rules. If a rule cannot be tested with an eval case, cut or rewrite it. - Do not invent tool APIs or file names that were not in Inputs. - The system prompt must fit in one paste. No "part 2 of the prompt." - Do not add a cute name, emoji persona, or secret chain-of-thought dump. - Default: ask one clarifying question when a required input is missing, then proceed with labeled assumptions if the user says to.
Custom AI Automation Workflow Builder for Any Process
Design a complete AI-powered automation workflow for any business process. Get step-by-step tool recommendations, integration maps, and implementation plans.
Act as an AI automation architect specializing in workflow design and tool integration. I need you to design a complete AI automation workflow for [Business Process / Task]. Follow these steps: Analyze the process: Break down [Business Process] into individual steps that can be automated. For each step, recommend: The best AI tool or service (e.g., Zapier, Make, OpenAI API, LangChain) The specific action or trigger configuration Input/output data format Create an integration map showing how each tool connects to the next. Identify potential failure points and suggest error-handling strategies. Estimate time savings compared to manual execution. Provide a phased implementation plan: Phase 1: Quick wins (tools with no-code setup) Phase 2: Custom integrations (API-based connections) Phase 3: Advanced optimization (fine-tuning, custom models) Constraints: Prioritize tools with free tiers or trials where possible. Tone: Clear, practical, and actionable. Format: Numbered steps with tool names in bold.
AI Tool Comparison Matrix: Find the Best AI for Your Task
Generate a structured comparison of AI tools for any use case. This prompt evaluates features, pricing, limitations, and best-fit scenarios.
Act as a senior AI technology analyst with deep expertise in evaluating SaaS products and AI platforms. I need a comprehensive comparison of AI tools for [Use Case / Task Type]. Follow these steps: Identify the top 5 AI tools currently available for [Use Case]. For each tool, evaluate and present: Core features relevant to [Use Case] Pricing tiers (free, pro, enterprise) Key limitations or drawbacks Ideal user profile (beginner, developer, enterprise team) Integration capabilities (API, plugins, export formats) Create a comparison table summarizing the above. Provide a final recommendation section with: Best overall tool Best free option Best for power users Constraints: Use factual, verifiable information. Do not fabricate features. Tone: Objective, professional, and direct. Format the output as a structured report with clear headers and a markdown table.