# thinkhard.si

> Free, private tools for writing better prompts for AI, which US federal agencies have called SI, super intelligence, since a September 2026 executive order. Check and fix a prompt, start from 319 prompt templates in the repository, make AI drafts sound human, check the facts in an answer, hide private details before pasting, compare models and see what AI will cost. Everything runs in the browser; prompts go straight from the visitor's browser to the AI company with their own key and never reach thinkhard.si.

## Tools

- [Compare AI models side by side on your own prompt](https://thinkhard.si/arena/): Run one prompt on up to six models at once, from Claude and GPT to Gemini. See each answer with its speed and cost, then vote blind or let an AI judge.
- [Copy AI answers without asterisks: paste ChatGPT into Word, Docs, Slack](https://thinkhard.si/copy-cleaner/): Paste a ChatGPT, Claude or Gemini answer and copy it clean into Word, Google Docs, Outlook, Gmail, Slack or Teams: real headings, lists and tables, no stray asterisks or ### marks. Free, in your browser.
- [Custom instructions generator for ChatGPT, Claude, Gemini and Copilot](https://thinkhard.si/custom-instructions/): Answer a few questions and get standing instructions so ChatGPT, Claude, Gemini or Copilot answers the way you work: your role, your tone, honest answers and no AI filler. Free, with where to paste them.
- [Version Compare: what changed between versions](https://thinkhard.si/diff/): Compare two versions of a prompt word by word, and see what the change does to length, token cost, structure and the score out of 10. Free, private, in your browser.
- [Fact-check an AI answer: free checklist of claims](https://thinkhard.si/fact-check/): Paste a ChatGPT or Claude answer and get every number, quote, source and date to verify, riskiest first, with a search link for each. Free and private.
- [Free AI prompt checker: grade any prompt out of 10](https://thinkhard.si/grader/): Paste a prompt for ChatGPT or Claude and get a score out of 10 on ten checks, with a plain question for each gap. Free and private, with no sign-up.
- [Prompt injection tester: will your system prompt leak?](https://thinkhard.si/injection/): See if people can trick your chatbot. Scan its instructions for weak spots, then try harmless attacks on up to three models and see exactly what leaks. Free.
- [Prompt Tester: test a prompt on real examples, free](https://thinkhard.si/lab/): Test every version of a prompt on your own examples across Claude, GPT, Gemini and more. Checks and an AI judge score each answer and show what each change broke.
- [My Prompts: save every version of your prompts](https://thinkhard.si/library/): Save prompts from any thinkhard.si tool with full version history. Compare versions, roll back and open any prompt in another tool. Stays in your browser.
- [Free AI prompt generator: build a prompt for ChatGPT, Claude or Gemini](https://thinkhard.si/prompt-builder/): Answer a few plain questions and get a well-built prompt for ChatGPT, Claude, Gemini or Copilot, laid out the way each model reads best and scored live on ten checks. Free, no sign-up.
- [Does it sound like AI? Free checker for AI slop and writing tells](https://thinkhard.si/robot-speak/): Paste a draft and see what makes it read as AI-written: long dashes, filler, buzzwords and stock openers. Fix them in one click. Free, runs in your browser.
- [Anonymize text before ChatGPT: free, in your browser](https://thinkhard.si/safe-paste/): Swap names, emails, phone and account numbers for placeholders before you paste into ChatGPT or Claude, then put them back in the answer. Nothing is uploaded.
- [LLM cost calculator: what an AI feature costs a month](https://thinkhard.si/tokens/): Pick a task and how often it runs, and see the monthly cost on every major model, with caching and batch discounts. Free, no API key needed.

## Start here

- [AI glossary in plain English: tokens, keys, prompts](https://thinkhard.si/glossary/): Plain-English definitions of the AI words people meet at work: API key, token, system prompt, context window, prompt caching, evals, hallucination and more.
- [Learn to prompt AI well: guides, blog and use cases](https://thinkhard.si/learn/): Free guides, weekly posts, use cases by team and industry, a plain-English glossary and an AI price index, for anyone who uses AI at work.
- [LLM API pricing comparison: price per million tokens](https://thinkhard.si/prices/): Input, output and cached-input prices per million tokens for Claude, GPT, Gemini, DeepSeek, Mistral and Grok, with the date each price was last checked.
- [Start here: which prompt tool do you need?](https://thinkhard.si/start/): Pick what you want to do and land on the free thinkhard.si tool that does it: templates, a prompt grader, a cost calculator, model comparison and more.

## For developers: the REST API and the MCP server

- [Free prompt library MCP server, no sign-in needed](https://thinkhard.si/developers/): Add https://thinkhard.si/mcp to Claude, ChatGPT, Cursor or VS Code to search 319 work prompts, grade a prompt out of 10 and price an AI feature. No key.
- [thinkhard.si API: REST, MCP, Claude API and OpenAI examples](https://thinkhard.si/developers/api/): A free REST API with an OpenAPI spec, and the MCP server: search and fetch 319 tested prompts, grade a prompt and price an AI feature from curl, Python, JavaScript, the Claude API or the OpenAI API. No key.
- [MCP playground: test a public MCP server online](https://thinkhard.si/developers/playground/): Connect to a free public MCP server with no key, list its tools and prompts, call any tool and see the JSON-RPC request and answer. Copy the call as code.
- [MCP tools reference with curl examples](https://thinkhard.si/developers/tools/): Each tool on the thinkhard.si MCP server with its parameters, the fields it returns, a tools/call request you can paste into curl and the answer it gives.
- [MCP server docs as Markdown](https://thinkhard.si/developers/mcp.md): Setup, every tool with its parameters and output fields, example calls and limits, in one Markdown file.
- [REST API, OpenAPI 3.1](https://thinkhard.si/api/v1/openapi.json): The same tools as plain JSON at https://thinkhard.si/api/v1: search and fetch prompts, grade a prompt, price an AI feature. No key, CORS open.

## Guides

- [Using AI at work safely: a practical risk checklist](https://thinkhard.si/guides/ai-at-work-risk-checklist/): What AI should and should not do in a business: confidential and personal data, invented facts, approvals, prompt injection, disclosure and human review.
- [AI words to avoid: what makes writing sound like AI](https://thinkhard.si/guides/ai-words-to-avoid/): The words and habits that make a draft read as AI-written, from delve and seamless to filler openers and lists of three, with plain swaps and a prompt that stops them.
- [How to anonymize text before you paste it into ChatGPT or Claude](https://thinkhard.si/guides/anonymize-text-for-chatgpt/): Replace names, emails, account numbers and other identifying details with consistent placeholders before you paste into ChatGPT or Claude, then put them back.
- [What is an API key? Why AI tools ask for yours](https://thinkhard.si/guides/api-keys/): An API key lets software use an AI model on your account. What it is, why tools ask for yours, what it costs in practice, free options and how to keep it safe.
- [How to write a prompt: brief AI like a new hire](https://thinkhard.si/guides/brief-ai-like-a-new-hire/): Write prompts the way you would brief a capable new colleague: context, goal, audience, material, format, limits and what good looks like, with office examples.
- [ChatGPT, Claude or Gemini for work: how to choose](https://thinkhard.si/guides/chatgpt-claude-gemini-for-work/): Which of ChatGPT, Claude and Gemini to use for which work task, what each offers as of October 21, 2026, and a one-hour test on your own work.
- [Choosing an AI model for business: cost, quality, speed](https://thinkhard.si/guides/choosing-an-ai-model-for-business/): Pick an AI model for business tasks in plain language: cost, quality and speed, real prices per 1,000 tasks, and the cheapest model that passes your tests.
- [Prompting Claude vs GPT vs Gemini: what differs](https://thinkhard.si/guides/claude-gpt-gemini/): What Anthropic, OpenAI and Google each recommend for prompt layout, what they share, and one prompt laid out three ways. Conventions checked October 10, 2026.
- [Extract data from invoices and PDFs with AI](https://thinkhard.si/guides/extract-data-from-documents/): Get reliable JSON or tables out of invoices, PDFs and contracts: a field sheet, schema-enforced output, blanks instead of guesses, checks in code and spot checks.
- [How to fact-check an AI answer before you use it](https://thinkhard.si/guides/fact-check-ai-answers/): A step-by-step way to fact-check a ChatGPT or Claude answer: list every claim, check the riskiest first against the original source, and open every link and quote.
- [How to test a prompt before you ship it](https://thinkhard.si/guides/how-to-test-prompts/): Test a prompt without writing code: real test cases, exact checks, an AI judge you can trust, and a regression check each time the prompt or model changes.
- [How to write a system prompt for a chatbot or assistant](https://thinkhard.si/guides/how-to-write-a-system-prompt/): A system prompt is the standing brief a chatbot reads before every message. The seven parts it needs, a support assistant rewritten, and how to test it.
- [What an LLM call really costs: tokens and caching](https://thinkhard.si/guides/llm-cost/): How tokens are billed, the formula for input, output and cached tokens, a worked example at current list prices, and how to pick the cheapest model that passes.
- [MCP servers for people who don't code: a plain guide](https://thinkhard.si/guides/mcp-servers-for-non-developers/): What an MCP server is, how to add one to Claude or ChatGPT without writing code, what to check before you trust one, and the kinds that help most at work.
- [How to measure an AI feature after launch](https://thinkhard.si/guides/measure-an-ai-feature/): What to measure once an AI feature is live: pass rate on a test set, escalations, user corrections, cost per completed task and response time.
- [Prompt engineering for beginners: the 15-minute version](https://thinkhard.si/guides/prompt-engineering-for-beginners/): Prompt engineering for people at work in fifteen minutes: the five things every prompt needs, one task rewritten, how to fix a weak answer and what to stop doing.
- [Prompt injection explained: stop system prompt leaks](https://thinkhard.si/guides/prompt-injection/): What prompt injection and system prompt leakage are, why secrets never belong in a prompt, and the layered defenses that limit the damage when an attack works.
- [AI prompts for customer support that follow policy](https://thinkhard.si/guides/prompts-for-customer-support/): A playbook for support teams using AI: replies that follow policy, triage, macros, tone and escalation, no invented refunds, and testing on real tickets first.
- [Sales and marketing prompts that don’t sound like AI](https://thinkhard.si/guides/prompts-for-sales-and-marketing/): Get outreach and marketing copy from AI that sounds like you: feed it real facts, voice samples and banned phrases, ask for variants, and check every claim.
- [How to reduce AI hallucinations at work](https://thinkhard.si/guides/reduce-ai-hallucinations/): Practical ways to reduce AI hallucinations: give the model its sources, allow “I don’t know”, ask for quotes, check citations, and test on questions with no answer.
- [Rolling out AI prompts to a team: a shared library](https://thinkhard.si/guides/rolling-out-prompts-to-a-team/): Turn good prompts into shared templates a team can trust: an owner, version numbers, review, one library, tests before every change, and when to retire one.
- [SI vs AI: what the super intelligence rename means at work](https://thinkhard.si/guides/si-vs-ai/): SI, short for super intelligence, is what US federal agencies have called AI since an executive order of September 29, 2026. What changed, what did not, and what to do at work.
- [The ten checks of a well-written prompt](https://thinkhard.si/guides/ten-tests/): Task, purpose, material, scope, form, limits, standard, reference, doubt and fit: what each test asks, a weak and a fixed example, and how the score works.
- [What a one-line prompt scores: 319 work tasks, graded](https://thinkhard.si/guides/what-a-one-line-prompt-scores/): We scored 319 everyday work requests as one-line prompts. 249 scored 1 out of 10. Two short additions lift the average from 1.2 to 5.7. The data, and how to rate your own prompt.

## Blog

- [AI for DCF valuation: what to delegate, what to check](https://thinkhard.si/blog/ai-dcf-valuation/): Where a language model helps a DCF valuation (reading filings, attacking the story, drafting the memo) and why it must never do the arithmetic or supply inputs.
- [Do you need an AI tool, or just a better prompt?](https://thinkhard.si/blog/ai-tool-or-better-prompt/): Many AI tools for small teams are a prompt, a model and a text box. When a good prompt and an API key are enough, and when a product is worth paying for.
- [Why your AI writes like a brochure, and how to stop it](https://thinkhard.si/blog/ai-writes-like-a-brochure/): AI drafts sound like ad copy when the prompt names a tone and gives no facts. Five changes to a prompt, shown before and after, that make it write plainly.
- [How to choose an LLM: the cheapest model that passes](https://thinkhard.si/blog/cheapest-model-that-passes/): Stop asking which AI model is best. Define the bar your task must clear, test models from every price tier, and pick the cheapest that passes at your volume.
- [“Make it better” is the most expensive prompt you write](https://thinkhard.si/blog/make-it-better/): Vague prompts like “make it better” cost hours of rework, not tokens. What a good AI brief contains, with a before and after your team can copy and reuse.
- [Prompts are the new standard operating procedures](https://thinkhard.si/blog/prompts-are-sops/): The prompts that answer customers and route tickets are company procedures. Give each an owner, a version, a test suite and a review date, like any SOP.
- [What a support chatbot costs at 10,000 chats a day](https://thinkhard.si/blog/support-chatbot-cost/): Worked numbers for an AI support chatbot at 10,000 conversations a day: tokens per conversation, caching and batch, at list prices checked October 20, 2026.
- [Chatbot system prompt: write it like a contract](https://thinkhard.si/blog/system-prompt-contract/): A support chatbot speaks for your company. Write its system prompt like a contract: scope, sources of truth, refusals, escalation and prompt injection defenses.
- [Why AI answers change every time, and when it matters](https://thinkhard.si/blog/why-ai-answers-change/): Why the same prompt gives different AI answers, why temperature 0 will not fix it, and how to test on many cases and repeated runs instead of one good answer.

## Use cases

- [Agency and consulting AI prompts: proposals to reports](https://thinkhard.si/use-cases/agencies-and-consulting/): How marketing agencies and consulting firms use AI prompts for proposals, research synthesis, client reports, copy and meeting notes, with client data rules.
- [AI for banks and insurers: claims, letters, policy](https://thinkhard.si/use-cases/banking-and-insurance/): How bank, credit union and insurance teams use AI prompts for procedure Q&A, complaint letters, claims mail and document intake, with compliance guardrails.
- [How to use AI in customer support, with prompts](https://thinkhard.si/use-cases/customer-support/): How support teams use AI prompts for reply drafts, ticket triage, escalations, macros and help articles, tested on real tickets and priced at your volume.
- [AI prompts for ecommerce: product pages and support](https://thinkhard.si/use-cases/ecommerce-and-retail/): How online stores and retailers use AI prompts for product listings, SEO, support replies, review responses and supplier emails, priced at catalog scale.
- [How to use AI in teaching and training, with prompts](https://thinkhard.si/use-cases/education-and-training/): How schools, colleges and workplace training teams use AI prompts for quizzes, rubrics, lesson plans and family emails, with FERPA and COPPA guardrails.
- [How to use AI in finance and accounting teams](https://thinkhard.si/use-cases/finance-and-accounting/): How FP&A, accounting and investment teams use AI prompts for variance commentary, the close, audit requests and DCF memos, with every number kept traceable.
- [AI prompts for healthcare admin: letters and prior auth](https://thinkhard.si/use-cases/healthcare-administration/): How practice and hospital admin teams use AI prompts for patient letters, prior authorization drafts, scheduling messages and policy Q&A, with HIPAA guardrails.
- [How to use AI in HR and recruiting, with prompts](https://thinkhard.si/use-cases/hr-and-recruiting/): How HR and recruiting teams use AI prompts for job posts, structured interviews, feedback, onboarding and policy FAQs, with people making every decision.
- [How to use AI for legal and compliance work](https://thinkhard.si/use-cases/legal-and-compliance/): How in-house legal and compliance teams use AI prompts for playbook reviews, NDA triage, clause summaries and policy Q&A, with counsel making every call.
- [How to use AI in marketing: ads, SEO and content](https://thinkhard.si/use-cases/marketing/): How marketing teams use AI prompts for ad variants, SEO titles, landing pages, repurposed content and campaign readouts, with claim checks and real costs.
- [AI prompts for nonprofits: grants, donors, reports](https://thinkhard.si/use-cases/nonprofits/): How small nonprofit teams use AI prompts for grant narratives, donor letters, impact reports and board summaries, without inventing outcomes or exposing donors.
- [How to use AI in operations: SOPs to suppliers](https://thinkhard.si/use-cases/operations/): How operations teams use AI prompts for SOPs, supplier emails, action items, RACI charts, inbox triage and document extraction, with nothing made up.
- [How to use AI in product and engineering teams](https://thinkhard.si/use-cases/product-and-engineering/): How product managers and developers use AI prompts for specs, research, release notes and code review, and how to test, price and attack an AI feature.
- [AI prompts for real estate agents: listings and leads](https://thinkhard.si/use-cases/real-estate/): How agents, brokerages and property managers use AI prompts for listing copy, lead replies, market updates and tenant notices, with fair housing guardrails.
- [AI prompts for SaaS startups: support, product and code](https://thinkhard.si/use-cases/saas-and-startups/): How SaaS companies and startups use AI prompts for support, specs, code review, sales and in-product AI features, tested, priced and attacked before launch.
- [How to use AI in sales: prospecting, calls and RFPs](https://thinkhard.si/use-cases/sales/): How sales teams use AI prompts to prepare for discovery calls, write first touches and follow-ups, recap calls and answer RFPs from approved content only.

## Prompt templates

- [Free prompt packs for work seasons](https://thinkhard.si/packs/): Free prompt packs for the busy seasons at work, such as performance reviews and report cards: every prompt in full, in the order the work happens, with no sign-up.
- [Performance review season: 11 AI prompts for managers](https://thinkhard.si/packs/hr-review-season/): Free prompts for review season: prepare 1:1s, write reviews and self-assessments from real notes, plan pay within budget and handle the hard conversations.
- [Report card season: 9 AI prompts for teachers](https://thinkhard.si/packs/report-card-season/): Free prompts for teachers at report card time: rubrics, feedback on writing, report card comments from your notes, parent emails and plans for next term.
- [319 free AI prompts for work: ChatGPT, Claude, Gemini](https://thinkhard.si/templates/): Copy-ready prompts for ChatGPT, Claude, Gemini or Copilot: emails, meetings, HR, sales, finance and more. Each is scored out of 10 and has blanks to fill.
- [Prompt templates for coding agents and Claude Code: 11 free](https://thinkhard.si/templates/coding-agents/): 11 free prompt templates for coding agents. Briefs for coding agents with a check they can run, plus design docs and pull request write-ups.
- [AI prompts for customer service replies: 20 free](https://thinkhard.si/templates/customer-service/): 20 free AI prompts for customer service and support. Replies, triage, onboarding and reviews that stick to your policy and never invent a refund.
- [AI prompts for work emails and meetings: 29 free](https://thinkhard.si/templates/email-and-meetings/): 29 free AI prompts for work emails and meetings. Inbox replies, meeting notes, follow-ups and slides for the work that fills the week.
- [AI prompts for Excel and data analysis: 17 free](https://thinkhard.si/templates/excel-and-data/): 17 free AI prompts for Excel, spreadsheets and data. Formulas, macros, survey themes with real counts and honest explanations of what the numbers show.
- [AI prompts for accounting and finance teams: 16 free](https://thinkhard.si/templates/finance-and-accounting/): 16 free AI prompts for accounting and finance teams. Variance notes, budgets, cash forecasts and payment reminders that keep every number traceable.
- [AI prompts for HR and recruiters: 20 free templates](https://thinkhard.si/templates/hr/): 20 free AI prompts for HR and recruiters. Job posts, interview plans, feedback and policies written fairly, with a person making every decision.
- [AI image prompts for product photos and headshots: 8 free](https://thinkhard.si/templates/image-and-video/): 8 free AI image and video prompts for work. Scene descriptions for image and video models, from product shots to headshots and flyers.
- [AI prompts for job seekers: 14 free templates](https://thinkhard.si/templates/job-search/): 14 free AI prompts for your job search and career. Resumes, interviews, raises and next steps in your own career, using only what you actually did.
- [AI prompts for contracts and legal documents: 11 free](https://thinkhard.si/templates/legal/): 11 free AI prompts for contracts, policies and compliance. Contracts, policies and rules in plain English, ready for review by a lawyer. Never legal advice.
- [AI prompts for managers and team leads: 18 free](https://thinkhard.si/templates/managers/): 18 free AI prompts for managers and team leads. Meeting prep, feedback, decision memos and updates that say what changed and what you need.
- [AI prompts for marketing plans and campaigns: 26 free](https://thinkhard.si/templates/marketing/): 26 free AI prompts for marketing plans, emails and campaigns. Posts, emails, campaigns and plans that bring in customers, built from real facts instead of…
- [AI prompts for operations managers: 14 free](https://thinkhard.si/templates/operations/): 14 free AI prompts for operations managers. Procedures, suppliers, schedules and inspections that keep the day-to-day running. Each is scored out of 10.
- [AI prompts for product managers: 10 free](https://thinkhard.si/templates/product-managers/): 10 free AI prompts for product managers. Interview synthesis, specs, roadmaps and pricing grounded in evidence. Each is scored out of 10.
- [AI prompts for project managers: 12 free templates](https://thinkhard.si/templates/project-management/): 12 free AI prompts for project managers. Plans, status updates, risks and launches that keep a project on track and its sponsors informed.
- [AI prompts for research and long documents: 12 free](https://thinkhard.si/templates/research/): 12 free AI prompts for research and long documents. Get up to speed, read long documents and turn sources into answers you can check.
- [AI prompts for sales emails and prospecting: 18 free](https://thinkhard.si/templates/sales/): 18 free AI prompts for sales emails, calls and proposals. Outreach, proposals, call reviews and account plans that sell on the buyer's own words.
- [AI prompts for small business owners: 19 free](https://thinkhard.si/templates/small-business/): 19 free AI prompts for small business owners. Plans, pricing, listings, reviews and client emails for owners who do everything themselves.
- [10 system prompt examples for custom GPTs and chatbots](https://thinkhard.si/templates/system-prompts/): 10 free system prompt examples for custom GPTs, Projects and chatbots. Instructions for custom GPTs, Claude Projects, Gems, chatbots and tool-using agents.
- [AI prompts for teachers and trainers: 15 free](https://thinkhard.si/templates/teachers/): 15 free AI prompts for teachers and trainers. Lesson plans, feedback, parent emails and onboarding material that teach one thing at a time.
- [AI prompts for writing and editing: 19 free](https://thinkhard.si/templates/writing-and-editing/): 19 free AI prompts for writing and editing. Edits that keep your voice, summaries that keep the numbers, rewrites that keep the meaning.

## About

- [About thinkhard.si, and why it exists](https://thinkhard.si/about/): thinkhard.si is an independent set of free, private tools for people who write prompts for a living. Here is why it exists and the principles it follows.
- [What’s new](https://thinkhard.si/changelog/): Every change to the thinkhard.si prompt tools, newest first: new tools, fixes, price updates and what is being built next.
- [Contact](https://thinkhard.si/contact/): Write to thinkhard.si about a bug, a wrong price, a tool you wish existed, your data or a partnership. Every message is read by the person who builds the site.
- [Pricing: free prompt tools, Pro and Team plans](https://thinkhard.si/pricing/): Every thinkhard.si tool is free with your own API key. Pro and Team plans for regression runs, prompt CI and shared workspaces are planned: join the waitlist.
- [Privacy policy](https://thinkhard.si/privacy/): thinkhard.si tools run in your browser. Your prompts, API keys and results never reach us unless you turn on sync; we keep only anonymous daily counts. Here is exactly what goes where.
- [Terms of use](https://thinkhard.si/terms/): The terms for using the free thinkhard.si prompt tools: your API keys and costs, what grades and scores mean, acceptable use, and who to contact.