Meta-Prompt: Generate Custom System Prompts
A prompt that generates system prompts. Describe what you need an AI to do, and this meta-prompt produces a structured, production-ready system prompt following best practices.
Use cases
Operations & Workflow, Strategy & Planning
Platforms
Claude, GPT, Gemini, Model-Agnostic
Jump to a section
Workspace-ready resource
Copy the raw material, then check the setup, output contract, and failure modes.
You are a prompt engineer. Your job is to write system prompts for LLMs based on the user's requirements. When the user describes what they need an AI to do, produce a complete system prompt that follows this structure: ## Structure to follow 1. **Role** (1-2 sentences): Who the AI is and what it does. Be specific. "You are a financial analyst specialising in SaaS metrics" is better than "You are a helpful assistant." 2. **Core Principles** (3-5 bullet points): The non-negotiable rules that govern all behaviour. These are the constraints that prevent the most common failure modes for this role. 3. **Process** (numbered steps): How the AI should approach tasks. What it does first, second, third. Include a step for clarifying ambiguous inputs rather than guessing. 4. **Output Format**: The exact structure the AI should use when presenting results. Be prescriptive. If the output should have sections, name them. If it should be a specific length, state it. 5. **Constraints** (bullet points): What the AI must not do. Banned behaviours, banned phrases, scope boundaries. Be explicit about what is out of bounds. 6. **Self-Check** (3-5 checklist items): Questions the AI should ask itself before presenting output. These should be binary (yes/no) and specific to the role. ## Rules for writing system prompts - Use imperative, direct language. "Do X" not "You should consider doing X."- Be specific. "Keep responses under 200 words" not "Be concise."- Anticipate failure modes. If the model commonly does something wrong for this role, add a constraint preventing it.- Do not include pleasantries, motivational language, or unnecessary context in the system prompt. System prompts are instructions, not conversations.- Use markdown formatting (headers, bullets, bold) for readability.- The total system prompt should be 200-500 words. Long enough to be comprehensive. Short enough to leave room for the actual task. ## Process 1. Ask the user to describe: what the AI needs to do, who the audience is, what the most important quality criteria are, and any specific constraints or preferences.2. If any of these are unclear, ask one focused question before generating.3. Generate the system prompt following the structure above.4. After generating, briefly explain (in 2-3 sentences) the key design decisions: why you included certain constraints, what failure modes you anticipated, and what the user might want to customise. The user's request:{{describe what you need the AI to do}}Workspace translation
Turn this resource into an inspectable run.
Best next step
Run it once manually. If the same job appears twice, package it.
From resource to system
Use it once
Copy and adapt the prompt for a one-off run.
Make it reusable
Save the durable pattern, turn repeated use into a playbook, or attach the reasoning as project knowledge.
Decide after the run
Run it once manually. If the same job appears twice, package it.
Quality bar
Before using this, check the contract.
What input does this require?
What output should it produce?
Where can it fail?
What should a human review?
Recommended path
When to Use This
Use this when you need to create a system prompt for a new use case and do not want to start from a blank page. Describe the job in plain language, and the meta-prompt produces a structured, production-ready system prompt.
This is the "teach a man to fish" resource. Instead of searching for a pre-made system prompt that approximately fits your use case, you generate one that exactly fits it.
Especially useful for: building custom GPTs or Claude Projects, configuring AI tools for clients, setting up AI-powered workflows, creating role-specific chatbots, or any situation where you need a bespoke system prompt quickly.
Why It Works
The six-part structure prevents missing sections. Most hand-written system prompts are incomplete. They define a role but forget constraints. They add constraints but skip the output format. The prescribed structure ensures every system prompt covers: who the AI is, how it should behave, what it should produce, and how it should self-check.
"Anticipate failure modes" is the instruction that produces the best constraints. Rather than asking the model to write generic rules, this instruction pushes it to think about what goes wrong for this specific role. A customer support prompt gets constraints about empathy and escalation. A data analyst prompt gets constraints about accuracy and uncertainty. The constraints are tailored, not boilerplate.
The self-check section is often missing from system prompts. Most prompts are one-directional: do this, produce that. The self-check adds a feedback loop where the AI evaluates its own output before presenting. This consistently improves output quality across all use cases.
The 200-500 word target prevents two common mistakes. Too-short system prompts (under 100 words) lack the specificity to meaningfully constrain behaviour. Too-long system prompts (over 1000 words) dilute key instructions in noise. The target keeps prompts in the productive middle ground.
How to Customise
Add domain-specific context. If you primarily work in a specific field, add: "When generating system prompts for [your field], prioritise [specific quality criteria] and always include constraints about [common issues in your field]."
Adjust the structure. The six-part structure is a strong default. If your use cases consistently need additional sections (e.g. "Knowledge Sources" for research roles, or "Tone Guidelines" for writing roles), add them to the structure template.
Chain it with testing. After generating a system prompt, test it with 3-5 representative inputs. Then feed the results back: "Here is the system prompt you generated and the outputs it produced. Refine the prompt to fix [specific issues]." This creates a meta-prompt > test > refine loop.
Limitations
A meta-prompt is only as good as the description you provide. "Make me a prompt for writing" will produce a generic writing prompt. "Make me a system prompt for writing LinkedIn posts for B2B SaaS founders, contrarian tone, 150-250 words, with a hook in the first line and a question at the end" will produce something immediately useful.
The generated system prompt is a strong first draft, not a finished product. You should always review and adjust it before using it in production. Pay particular attention to the constraints (are they specific enough?) and the self-check (does it catch the failure modes you care about?).
Model Notes
Claude: Produces well-structured system prompts with thoughtful constraints. The design decision explanation is particularly useful. Claude tends to write slightly longer system prompts than the 500-word target — trim if needed.
GPT: Generates solid prompts but may over-explain in the system prompt itself (adding context that should be in the user prompt, not the system prompt). Review for conciseness.
Gemini: Follows the structure reliably. May produce blander constraints than Claude or GPT. Push for specificity: "Make the constraints highly specific to this role. Avoid generic rules like 'be helpful.'"
Related Resources
Browse PromptsSystem Prompt: Content Writer
A production-ready system prompt for configuring any LLM as a content writer with tone control, format awareness, and a built-in self-check.
Pattern / playbook seed
Content & Writing · Marketing & Growth
System Prompt: Research Analyst
A system prompt for configuring an LLM as a structured research analyst that separates facts from interpretation, scores confidence, and flags gaps clearly.
Pattern / playbook seed
Research & Analysis · Strategy & Planning
Framework: Prompt Audit Checklist
A 15-point checklist for evaluating any prompt before putting it into production. Catches the most common prompt failures: vague instructions, missing constraints, absent error handling, and untested edge cases.
Knowledge / rubric seed
Operations & Workflow · Strategy & Planning
Related Guides
Need this operationalized?
Turn the pattern into a workspace system.
Use MPV for the private workspace loop, or work with Encanta to turn operators, playbooks, context, and review flows into a team-ready implementation.