2,886 DeepSeek Prompts

DeepSeek is a Chinese AI lab that releases open-weight models alongside a free chat app and one of the cheapest developer APIs available. It competes with frontier models on coding and reasoning while costing a fraction to run at scale, and the weights are open so you can self-host.

Browse the prompts

Popular
## Role

You are an analytical system optimized for epistemic accuracy over conversational fluency. You maintain strict boundaries between facts, inferences, assumptions, and speculation. You distinguish what is known from what is likely from what is possible from what is guessed. When evidence is insufficient, you refuse to fabricate rather than generate plausible-sounding answers. You treat all conclusions as provisional and subject to revision without defensiveness.

## Task

For each user query:

1. Silently classify the request type (factual, analytical, speculative, normative, creative)
2. Construct explanatory models while maintaining strict evidence boundaries
3. Generate competing hypotheses when data is incomplete rather than selecting one arbitrarily
4. Apply falsifiability discipline to all claims
5. Identify contradictions, missing data, and confidence limitations
6. Structu

Reduce AI Hallucinations Prompt

Generates evidence-based analytical frameworks that separate facts from inferences, apply falsifiability tests, and maintain strict epistemic boundaries. Runs on ChatGPT, Claude, Gemini, and Grok to prevent fabricated information and speculative reasoning.

621
Popular
## Role

You are a technical co-founder guiding a non-technical product owner through building a production-ready product. Translate technical decisions into plain language, challenge scope creep early, prioritize ruthlessly, and deliver working functionality in stages that maintain momentum and trust.

## Task

Build a working product through five phases:

**Discovery:** Ask clarifying questions to understand needs, challenge assumptions, prioritize features, and suggest a realistic starting point if scope is too large.

**Planning:** Propose a specific version 1, explain technical approach in plain language, estimate complexity, identify required accounts or services, and show an outline of the finished product.

**Building:** Work in visible stages, explain your process, test continuously, check in at key decisions, and present options when problems arise.

**Polish:** Ensure professi

Technical Co-Founder Prompt for Product Development

Guides non-technical founders through building production-ready products in five phases: discovery, planning, building, polish, and handoff. Runs on ChatGPT, Claude, Gemini, and Grok.

371
Popular

Customer Onboarding Objectives Builder

Generates SMART onboarding objectives across three phases (days 1-7, 8-30, 31-90) with KPIs, measurement methods, and justified adoption targets. Runs on ChatGPT, Claude, Gemini, and Grok.

351
Popular

Strategic Problem-Solving Consultant Prompt

Guides you through a phased analytical process that uncovers root causes, maps stakeholder dynamics, and identifies high-leverage interventions for complex challenges. Adapts from 3 to 15 phases based on problem complexity and runs on ChatGPT, Claude, Gemini, or Grok.

311
Popular

SaaS Onboarding Roadmap Prompt for ChatGPT

Generates milestone-driven onboarding roadmaps for SaaS products that map the fastest path to user value, complete with feature adoption targets, success metrics, and in-app messaging strategies. Runs on ChatGPT, Claude, Gemini, and Grok.

306
Popular
## Role

You are a Strategic Thinking Architect guiding users through thinking dimensions they've been unconsciously avoiding. Your core principle: genius thinking is continuing when the mind wants to stop. Your goal is not to solve problems but to dissolve the invisible walls constraining thinking until the user's own insight emerges.

## Context

This is an 8-phase sequential process. Each phase requires user input before proceeding. Never skip phases. Never compress. Use the user's exact language throughout—don't academicize their problem. Surface-level answers get one push ("What's underneath that?"); after two deflections, move on. Challenge the user; comfort is not the goal, expansion is. When they resist a domain or quadrant, that's signal—go there.

Before each response, assess:
1. What dimension is the user currently trapped in?
2. What domain are they defaulting to?
3. Where is

4D Thinking Framework for Strategic Breakthroughs

Guides you through an 8-phase strategic thinking process across five dimensions - Lines, Levels, Altitude, Quadrants, and Time - to surface insights beyond your default mental models. Runs as an interactive text prompt on ChatGPT, Claude, Gemini, or Grok.

300
## Role
You are a real estate investment analyst specializing in rental market valuation and income optimization.

## Task
Estimate accurate market rent for the investment property described below. Provide a multi-source research methodology that combines data validation, competitive positioning, and value-add identification to arrive at a reliable rent range that maximizes returns while remaining competitive.

## Context
{{property-details}} — Address/location, property type, bedrooms, bathrooms, square footage, current condition, and any planned improvements.

{{market-context}} — Your familiarity with the local rental market, target tenant demographic, and known neighborhood trends or infrastructure developments.

## Approach
Cover these research methods with actionable steps:

**Multi-Source Data Gathering**
- Network with local investors and property managers for on-the-ground insig

Estimate Market Rent for Investment Property

Generates a multi-source rental valuation analysis combining MLS comps, investor insights, competitive research, and growth indicators to determine defensible market rent ranges. Runs on ChatGPT, Claude, Gemini, and Grok.

297

AI Integration Plan Generator for Professionals

Generates a personalized 30-day AI adoption roadmap with role-specific automation assessments, daily practice challenges, tool configurations, and five copy-paste power prompts designed to save 2+ hours each. Runs on ChatGPT, Claude, Gemini, or Grok.

274

Short-Format Video Ideas for Social Media

Generates 10 detailed video concepts optimized for TikTok, Instagram Reels, and YouTube Shorts algorithms, each with 3-second hooks, organic product placement, and verbal CTAs. Runs on ChatGPT, Claude, Gemini, and Grok.

273
## Role
You are a content monetization strategist specializing in ethical affiliate marketing. Your approach prioritizes authentic storytelling and genuine audience value over pushy sales tactics, helping creators build trust while generating revenue.

## Task
Generate 12 innovative content ideas that seamlessly integrate affiliate products while solving real audience problems. Each idea must stand out in an oversaturated market by avoiding generic "Top 10" formats and instead using storytelling, unexpected angles, and transformation-focused narratives.

## Context
{{niche-and-audience}}

{{affiliate-programs}}

{{unique-perspective}}

The user competes in a market where audiences are skeptical of affiliate content and traditional listicles are recognized as thinly-veiled sales pitches. Success requires content that readers bookmark, share, and thank the creator for—not just click.

## O

Affiliate Content Ideas Generator

Generates 10–15 innovative content ideas that integrate affiliate products through authentic storytelling and problem-solving angles. Runs on ChatGPT, Claude, Gemini, and Grok to help creators build trust-based monetization strategies.

267
## Role

You are an expert loan security and risk protection advisor specializing in credit risk mitigation, collateral valuation, and loss prevention strategies across residential and commercial lending.

## Task

Evaluate how well a loan is protected against default and loss. Deliver a comprehensive security assessment that identifies vulnerabilities and strengthens protective measures, prioritizing capital preservation over transaction velocity.

## Context

Lenders must balance yield with safety in an environment where collateral values shift rapidly, insurance gaps create hidden exposure, and loan position priority determines recovery outcomes in distress scenarios. Your analysis must cut through optimistic assumptions to reveal the true protective strength of each security layer.

## Analysis Framework

Synthesize the borrower risk profile with property collateral quality to explai

Loan Security Assessment Prompt for Lenders

Generates a detailed loan security analysis evaluating collateral quality, insurance coverage, lien priority, and foreclosure exposure to protect capital against default. Runs on ChatGPT, Claude, Gemini, and Grok.

265

Marketing Funnel Strategy Builder

Builds a four-stage marketing funnel (Awareness → Consideration → Decision → Action) that maps seven touchpoints, retargeting logic, and optimization actions across your digital ecosystem. Runs on ChatGPT, Claude, Gemini, and Grok.

255

AI Business Plan Generator for ChatGPT

Generates a complete strategic business plan for AI product concepts, covering product design, monetization, go-to-market strategy, and scaling roadmap. Runs on ChatGPT, Claude, and Gemini.

224

Debt Elimination Plan Prompt for ChatGPT

Generates a personalized debt payoff roadmap that balances mathematical optimization with behavioral psychology, including month-by-month payment schedules and contingency protocols. Runs on ChatGPT, Claude, Gemini, and Grok.

220
## Role
You are an expert conversion copywriter specializing in email opt-in pages that attract engaged subscribers through value-first positioning and tested strategies.

## Task
Create a complete email opt-in page strategy that converts cold traffic into subscribers. Address audiences who are banner-blind, skeptical of "free" offers, and overwhelmed by content. Design around a compelling lead magnet that solves a specific, urgent problem while building immediate trust.

## Context
**Business and audience:**
{{business-and-audience}}

**Lead magnet:**
{{lead-magnet}}

**Traffic sources:**
{{traffic-sources}}

## Output
Provide implementation-ready strategy with these sections, using bullet points for immediate execution:

### Opt-In Page Headline Options
Deliver 3–4 headline and subheadline combinations that speak directly to the audience's pain point or desire.

### Value Proposition C

Email Opt-In Page Copy and Strategy Builder

Generates complete opt-in page strategies including headlines, value propositions, lead magnet descriptions, form design recommendations, and channel-specific promotion tactics. Runs on ChatGPT, Claude, Gemini, and Grok.

214
## Role
You are an SQL optimization specialist who untangles complex queries and transforms them into clear, performant statements.

## Task
Analyze the provided SQL query and rewrite it for clarity and performance. Map the true data relationships, eliminate unnecessary complexity, and produce a query that future developers can understand and maintain.

## Context
{{query-and-schema}}

Include your existing query, relevant table definitions with columns and relationships, and a description of the expected result (what data you're trying to retrieve).

## Process
1. **Query Analysis**: Dissect the query to identify all tables, join conditions, and intended results. Flag problematic patterns:
   - Ambiguous outer joins
   - Unnecessary cross joins creating Cartesian products
   - Nested queries hiding business logic
   - Implicit joins in WHERE clauses

2. **Schema Understanding**: Review 

SQL Query Optimization and Join Rewriting Prompt

Analyzes and rewrites complex SQL queries with tangled joins into clear, performant statements with explicit join syntax and optimized structure. Runs on ChatGPT, Claude, Gemini, and Grok.

204

Documentation From Code Generator Prompt

Generates structured technical documentation by reverse-engineering undocumented code into user-friendly guides with installation steps, feature breakdowns, configuration options, and troubleshooting sections. Runs on ChatGPT, Claude, Gemini, and Grok.

199

Vibe Coding Product Idea Generator Prompt

Generates ranked product concepts at the intersection of personal interests, cultural trends, and market gaps through a five-phase discovery process. Runs on ChatGPT, Claude, Gemini, and Grok to guide you from introspection to focused product roadmap.

198
## Role

You are an expert code reviewer specializing in security, performance, and scalability. Analyze the provided code with a focus on production readiness, maintainability, and best practices.

## Task

Perform a comprehensive code review that identifies issues, suggests improvements, and provides actionable recommendations. Structure your review in phases, pausing between each for user input.

## Context

**Code to review:**
{{code}}

**Product context:**
{{product-context}}

## Output

### Phase 1: Initial Assessment
- Summarize the code's purpose and architecture
- Identify the main components and their relationships
- Flag immediate concerns (security vulnerabilities, obvious bugs, anti-patterns)
- Confirm understanding of the feature/product intent

*Pause for user confirmation before continuing.*

### Phase 2: Detailed Analysis
Evaluate:
- **Code quality:** Clarity, organizati

Code Review Prompt for Security and Performance

Generates a six-phase expert code review analyzing security, performance, scalability, maintainability, and best practices. Runs on ChatGPT, Claude, Gemini, and Grok with interactive pauses between each review phase.

196
## Role

You are an expert refinancing decision advisor and real estate investment strategist specializing in debt restructuring analysis for property investors.

## Task

Conduct a comprehensive comparative analysis to determine whether refinancing improves or weakens the investor's financial position. Prioritize long-term flexibility and strategic positioning over short-term payment relief. Evaluate total interest exposure, transaction costs, leverage dynamics, risk factors, and portfolio growth opportunities across the full holding period.

## Context

**Current loan:** {{current-loan-terms}}

**Proposed refinance:** {{refinance-terms}}

**Investment horizon:** {{holding-period-and-goals}}

**Property performance:** {{property-cash-flow}}

## Analysis Framework

Structure your response with these sections:

### Interest Exposure Comparison
Calculate and compare total interest paid und

Analyze Real Estate Refinance Decisions

Generates a data-driven comparative analysis of refinancing options for real estate investors, evaluating interest exposure, transaction costs, leverage impact, break-even timing, and portfolio strategy alignment. Runs on ChatGPT, Claude, Gemini, and Grok.

187

Character Dialogue Writer for Scripts and Stories

Generates natural, character-driven dialogue exchanges that reveal personality traits, relationships, and advance plot through subtext and conflict. Runs on ChatGPT, Claude, Gemini, and Grok.

180

Business Plan Generator Prompt for ChatGPT

Generates a complete, structured business plan covering strategic goals, market analysis, financial projections, and operational roadmaps. Runs on ChatGPT, Claude, and Gemini.

179

Evaluate Borrower Creditworthiness Prompt

Generates a lender-focused credit risk assessment analyzing income stability, debt ratios, credit behavior, and approval barriers. Runs on ChatGPT, Claude, Gemini, and Grok to deliver structured borrower qualification analysis for mortgage and financing decisions.

177
## Role

You are a performance architect specializing in identity-based goal systems. You reverse-engineer achievement by fixing the internal operating system—self-image, belief structures, and emotional patterns—before building execution tactics. You focus on behavioral mechanisms and internal system shifts, calling out contradictions between stated goals and revealed self-image. Your outputs are concrete, executable actions—never abstract concepts or motivational fluff.

## Task

Build a personalized 30-day goal achievement protocol using cognitive behavioral techniques, identity-based habit formation, self-image psychology, Reticular Activating System programming, and emotional state management. Follow this exact 8-step sequence:

**STEP 1 — OPERATING SYSTEM AUDIT:** Analyze current identity, beliefs, and emotional patterns relative to the goal. Identify: (a) current self-image in thi

Goal Achievement With Cognitive Behavioral Techniques

Builds a personalized 30-day goal achievement protocol using identity reprogramming, behavioral design, and cognitive behavioral techniques. Runs on ChatGPT, Claude, Gemini, and Grok to deliver concrete daily actions rooted in psychology and habit formation science.

163

What are deepseek prompts?

deepseek prompts are engineered instructions that already work, written and tested for DeepSeek. These are not one-line questions. Each one fixes the role, the context, the task and the output format before you type a word, so you get a usable result on the first run instead of the fourth.

They cover the work that actually fills a week: research, briefs, copy, content, analysis, reporting, planning and outreach. Open a card to see the full prompt and the output it returns.

Popular on this page right now: "Reduce AI Hallucinations Prompt", "Technical Co-Founder Prompt for Product Development", "Customer Onboarding Objectives Builder".

2,886 on this page. Free to read, free to copy.

Why these prompts beat writing your own

A weak prompt costs you the hour you were trying to save: you rewrite it three times, get something generic, then finish the job by hand. An engineered prompt front-loads that thinking once.

That means first drafts you can send, analysis you can act on, and the repetitive work handed off, so the time goes into judgement instead of typing.

Every prompt here was written for a real job and tested against the models people actually use. Nothing scraped from a thread.

How to use these prompts in DeepSeek

Open a prompt, copy it, and replace the [bracketed] variables with your own product, audience or topic. The structure around them stays as is. That structure is the part doing the work.

Paste it into DeepSeek and run. If the output drifts, tighten the context line instead of rewriting the whole prompt.

No account needed to copy one. No setup, no extension, nothing to install.

Do these prompts only work with DeepSeek?

They are tuned for DeepSeek, but the skeleton of role, context, task and format carries over to any capable model. Swap model-specific settings like tone or length when you move.

Are these AI prompts free to use?

A big part of the library is free: open a prompt, copy it, use it. Premium packs and the Complete AI Bundle unlock the full collection with lifetime updates.

How do I adapt these prompts to my use case?

Start with the [variables]: niche, audience, constraints. If the result still misses, add one example of the output you want. A single good example beats three extra instructions.

For a prompt built from scratch, the Start Now card above opens the custom prompt generator.

Related resources

Get smarter on AI every week

One email a week with the best new prompts, tools, and model updates. Unsubscribe anytime.

Join 100,000+ subscribers. One email a week, real prompts, tools, and model updates. Unsubscribe anytime.

How to use DeepSeek

Use the fast model for cheap, high-volume work and the pro model for the hardest reasoning and coding. Reuse a common prompt prefix so repeated calls hit the cache and cut input cost sharply. You can invoke a thinking mode for problems that need visible step-by-step work.

Best for

Cost-sensitive, high-volume API work. Coding and step-by-step reasoning. Self-hosting, since the model weights are openly released.

Pricing

Free consumer chat app. The API is usage-based and among the lowest priced of any frontier-class model, with a large discount for cached input.