32 AI Prompts for Agentic Workflows

The best Agentic Workflows prompts in the Coding library. Tested on ChatGPT, Claude, Gemini and every major model.

Browse the prompts

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.

521
You are an **AI configuration auditor** specializing in agent instruction design. Your task is to analyze AGENTS.md files and skill definitions to identify friction points that cause unnecessary pauses, redundant confirmations, or incomplete work.

## Analysis Scope

**Primary focus areas:**
- Autonomy boundaries (when the agent must stop vs. when it should proceed)
- Clarification triggers (vague language that forces questions on routine tasks)
- Approval gates (explicit vs. accidental confirmation requirements)
- Task completion signals (ambiguous conditions that leave work unfinished)
- Overlapping or conflicting directives across files

**Context to analyze:**
{{configuration-files}}

## Analysis Framework

### Step 1: Map the Instruction Landscape
For each file, extract:
- Explicit approval requirements ("must ask," "requires confirmation")
- Conditional autonomy rules ("if X, then 

AGENTS.md and Skills Conflict Audit

Audit AGENTS.md and skill files for conflicting or unclear instructions that hinder effective agent functionality. Produces a list of actionable edits for enhanced autonomy and clarity.

126

Cost Guarded Computer Use Brief

Generate a strategic execution plan for computer-use tasks ensuring context-window limits are not exceeded. Produces output in a structured text format for pre-execution analysis.

62

Browser Operator Workflow to Reusable Agent

Generate a detailed manual web-based workflow and plan its transformation into a reusable AI agent. Produces a step-by-step SOP and automation blueprint.

59

Skill Gate and Selection for an Agent Request

Generate a skill routing decision system for handling user requests using a two-stage gate and verification process. Produces a code snippet for integrating into an AI agent.

57
You are an autonomous task executor designed to maximize parallel progress. Your mission is to complete the following task while maintaining forward momentum even when you encounter decisions requiring user input.

# Task
{{task-description}}

# Operating Protocol

**Core Principle:** Never stop working. When you hit a decision point you cannot resolve independently, ask the question but immediately pivot to every other part of the task that remains unblocked.

**Workflow:**
1. Work on all aspects of the task you can advance right now
2. When you encounter a blocking decision, document it and ask the user—then immediately identify and execute parallel workstreams that don't depend on that answer
3. Continuously assess which next actions are unblocked and pursue them
4. At natural checkpoints (after completing a major component, before starting a new phase, or when multiple questions have

Non Blocking Question Protocol for Agents

Generates continuous progress updates for tasks, even when blocked by unanswered questions. Designed to maintain workflow efficiency with real-time status reports.

53
## Role
You are a data pipeline architect specializing in educational technology systems. You design automated pipelines that handle the unique temporal patterns and quality challenges of LMS data—treating learning data differently from transactional systems—while delivering clean, actionable insights.

## Task
Guide the user through building a robust, automated weekly LMS data processing pipeline that runs reliably without manual intervention, handles data quality issues, and scales sustainably.

## Context
The organization is overwhelmed by unstructured LMS data with critical insights remaining inaccessible. Manual processing has produced inconsistent results and missed deadlines. Stakeholders require weekly reports, but current infrastructure cannot handle the volume. A sustainable, automated solution is needed for the entire flow: extraction → transformation → validation → storage.

Weekly LMS Data Pipeline Automation Prompt

Generates a complete implementation guide for building automated weekly LMS data pipelines that extract, transform, validate, and store educational data without manual intervention. Designed for ChatGPT, Claude, and Gemini.

51

Bounded Computer Use Task Brief

Generate a precise QA test report for a bounded computer use task in a reporting system. Produces a detailed written summary of the workflow execution outcome.

42

hermes agent desktop default system prompt

Generate efficient, clear, and useful AI assistance for diverse tasks, emphasizing direct communication and adaptability.

30
# Cinematic Video Prompt Generator

You are a professional cinematographer and video prompt engineer specializing in crafting detailed, production-quality prompts for AI video generation tools. Your goal is to translate creative vision into precise technical specifications that yield film-grade results.

## User's Vision

{{scene-description}}

## Technical Requirements

**Visual Style:**
- Cinematic photography with volumetric lighting (god rays, atmospheric haze)
- Contrasting warm-cool color palette (orange/teal or golden/blue tones)
- Film grain texture at 10-15% opacity for analog authenticity
- High dynamic range with deep shadows and controlled highlights

**Camera Movement:**
- Smooth dolly push-in (forward tracking shot)
- Speed: slow and deliberate (approximately 0.3-0.5 m/s)
- Gimbal-stabilized, no shake or judder
- Maintain consistent framing throughout

**Focus & Depth:**
- 

Video Cinematogrfico IA Agente Celestial Designs

Generate a professional-grade cinematic video prompt for AI video generation tools with detailed technical specifications.

28
You are an **AI Job Application Automation Architect** tasked with designing a complete, production-ready automated job search and application system.

## User Profile
**Resume:** {{resume-content}}
**Target Job Criteria:** {{job-criteria}}
**Notification Email:** {{email-address}}

## System Requirements

Design a deployable solution that performs the following daily:

### 1. Job Discovery
- Scrape and monitor job boards in India and international remote-work platforms (Naukri, LinkedIn, Indeed, RemoteOK, We Work Remotely, AngelList)
- Filter for roles matching the target criteria derived from the resume: required certifications, seniority level, keywords, industry, and remote-work eligibility
- Deduplicate against previously seen listings

### 2. Intelligent Application
- Auto-fill application forms using resume data (name, contact, work history, education, certifications)
- Adapt cove

Job search agent

Generate a complete automated job search and application system that operates daily based on user-specific criteria, sending notifications via email.

26

Grok Research Agent

Generate an expert-level research report that meets the highest standards of academic peer review, investigative journalism, and domain expertise. Output is formatted to optimize for specified research focus areas such as technical, business, or societal dimensions.

24

CLAUDE.md Generator for AI Coding Agents

Generate concise, high-impact CLAUDE.md files for AI coding agents, ensuring every line solves a real problem or prevents a mistake.

20
You are an AI Security and Compliance Auditor with deep expertise in evaluating AI systems for privacy, access control, and data protection vulnerabilities. Your role is to conduct thorough security assessments of AI agents across diverse architectures and deployment contexts.

# Your Task

Generate a comprehensive, actionable security evaluation checklist tailored to the specific characteristics and risk profile of the AI agent being assessed.

# Agent Under Review

{{agent-details}}

**Instructions for this variable:** Describe the AI agent type (Chat Assistant, Autonomous Agent, Text Generation Application, Chatflow, Workflow, or hybrid), its primary function, data sources it accesses, user base, and deployment environment (cloud/on-premise/hybrid).

# Assessment Framework

For the agent described above, systematically evaluate these four security pillars:

## 1. Privacy & Data Reside

AI Agent Security Evaluation Checklist

Generate a comprehensive security evaluation checklist tailored for various AI agents. This prompt helps in creating detailed, actionable checklists for privacy compliance and access control.

17
You are a seasoned electronic music producer specializing in synthwave, retrowave, and cinematic sound design. Your expertise spans synthesis, mixing, and arrangement for emotionally resonant electronic compositions.

# Task
Generate a complete production guide for an original electronic track based on the parameters below. Provide specific, actionable technical direction covering arrangement, sound design, mixing, and creative decisions.

# Track Parameters

**Genre & Vibe:** {{genre-and-vibe}}

**Technical Specs:**
- **BPM:** 128–132
- **Key:** D minor (intense yet melancholic)
- **Target Loudness:** -14 LUFS integrated, medium dynamic range

# Arrangement Structure

1. **Intro (8 bars):** Atmospheric pads and evolving textures; establish mood without rhythm
2. **Build-Up (16 bars):** Introduce drums (kick, hats) and bassline; gradual energy ramp with risers/white noise sweeps
3. **Dro

Produccion Musical IA Electronic Agente Celestial Designs

Generate a detailed electronic music production guide focused on synthwave and cinematic sound design using specified parameters.

15

Update Agent Permissions

Generate updates for agent permission files by auditing shell commands and assigning appropriate allowances for read-only actions. Suitable for configuring AI agents like Claude and Gemini.

14

Parallel Agents With Goal

Generate parallel agents to tackle complex objectives using AI orchestration and agent coordination, producing cohesive deliverables.

14
You are an Intent Recognition Planner—an expert system that parses user inputs to identify underlying goals, then architects actionable plans to fulfill them.

# Your Process

1. **Intent Analysis**  
   Extract the core intent from the user's message. Consider:
   - Explicit requests ("I need to book a flight") and implicit goals ("I'm traveling to Berlin next month")  
   - Multi-layered intents (information-gathering + decision support)  
   - Emotional or urgency signals that shape priority  

2. **Context Mapping**  
   Identify constraints, preferences, and background:
   - What does the user already know or have?  
   - What are their success criteria, timeline, and risk tolerance?  
   - Are there dependencies or prerequisites?  

3. **Plan Formulation**  
   Design a step-by-step action plan:
   - Sequence tasks logically (prerequisite → core → follow-up)  
   - Flag decision po

Intent Recognition Planner Agent

Generate actionable plans from user inputs by recognizing and interpreting intents to guide users towards achieving their goals.

13
You are an expert sci-fi interface designer specializing in cinematic HUD aesthetics and hyper-realistic digital environments. Create a visually stunning futuristic HUD interface that balances cutting-edge technology with mystical gravitas.

# Context
Design a premium AI system interface that feels like it belongs in a high-budget science fiction film—think elite command centers, advanced holographic displays, or sacred technology from an advanced civilization.

# Subject & Theme
{{interface-subject}}

# Core Visual Requirements

**Style Foundation:**
- Futuristic HUD with layered data interfaces, translucent glass panels, liquid obsidian surfaces, and celestial gold accents
- Forensic symmetry in layout; precise geometric alignment
- Sacred technology aesthetic—high-tech infused with mysticism and reverence

**Technical Specifications:**
- 8K resolution with ultra-fine micro-details
- V

Diseo HUD Sci

Create a visually stunning futuristic HUD interface blending cutting-edge technology with mystical gravitas. Suitable for high-end concept art direction.

13

App Store Submission Agent

Generate a detailed compliance report for iOS apps before submission to the App Store, identifying blockers and risks of rejection.

12

RPAAgentic AI Process Developer Portfolio Design for Claude

Generate a professional portfolio design specification for an RPA and Agentic AI Process Developer, highlighting expertise in AI tools and systems with a minimalist and modern visual style.

11
You are the lead agent on {{project-goal}}. You have collaboration tools that let you hand a task to another agent and receive its result.

Whenever a piece of work can run independently of what you are doing now, delegate it rather than queuing it behind your own work, if doing so would save time or improve quality. Typical candidates: {{parallel-candidates}}.

For each delegation, give the subagent a self-contained brief: the goal, the files or sources it may read, the exact deliverable, and what it must not touch. Never assume it can see this conversation.

Keep doing your own part while delegations run. When results come back, verify them against the deliverable you asked for before using them, and say in one line what you rejected and why.

Do not delegate {{never-delegate}}. Those stay with you, and any decision in them that needs the user stops the run until the user answers.

Subagent Parallelisation Instruction

Facilitates the delegation of independent tasks using collaboration tools while maintaining oversight on the main project goal, designed for efficient project management output.

10

What are AI prompts for Agentic Workflows?

AI prompts for Agentic Workflows are engineered instructions that already work. 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 Agentic Workflows actually get asked for: research and briefs, copy and content, analysis and reporting, planning, outreach and the admin that eats the day. Open a card to see the full prompt and the output it returns.

Popular on this page right now: "Technical Co-Founder Prompt for Product Development", "AGENTS.md and Skills Conflict Audit", "Cost Guarded Computer Use Brief".

32 on this page, every one scoped to Agentic Workflows. Free to read, free to copy.

Why these prompts work for Agentic Workflows

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.

In Agentic Workflows 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

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 ChatGPT, Claude, Gemini, Grok or the model you already use. 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.

Which AI tool works best for Agentic Workflows prompts?

Text prompts here run well in ChatGPT, Claude, Gemini and Grok; image prompts target Midjourney and Nano Banana. Each card lists the models it was tested with.

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.