CECEPrompts
Free CE Score Checker

Grade your agent prompt before it ships.

Paste a system prompt — from Claude, GPT, Gemini, or any agent framework — and get a production-readiness score with every missing component and its fix. Graded against the AgentAz Specification.

Free · No signup · Runs in your browser
Works with prompts from any model
ChatGPT Claude Gemini DeepSeek Grok

What's inside the CE report

CE Score

Run the free checker on any agent prompt. The score reflects how many of the ten production components are declared — role, tool boundaries, safety, approval gates and more — and maps to an AgentAz trust level from ADV to A5.

Every failing component comes with a concrete fix, so the path from a demo prompt to a production one is explicit.

Component audit

Every prompt is read against the ten components a production agent depends on. Each row is graded pass or fail — and every failing row expands into a concrete, copy-ready fix.

No vague advice. "Add an approval gate" comes with the exact wording that makes a gate real: prepare, present, wait.

The trust ladder

Scores map to AgentAz trust levels — ADV, A3, A4, A5 — and levels are earned, not estimated. A prompt reaches a level only when every component that level requires is present.

The report shows exactly where you stand and the shortest path to the next level.

The checker

Run your audit

Input · your agent prompt0 chars

Instant check runs in your browser (structural, free, unlimited). Nothing is stored or sent unless you publish.

CE Score
awaiting input
Paste a prompt and run the audit to see where it stands.
Levels jump ADV → A3 → A4 → A5 by design — each adds a real requirement, not a point. A0 and lower advisory tiers sit below A3.

What gets checked — 10 components

Want a prompt that already passes?

62 governed kits in the AgentKits library ship at A4/A5 with tool boundaries and approval gates declared.

Browse kits that pass →
The definition

A CE Score measures whether a prompt is engineered, not just written.

Any model can write a plausible agent prompt. Few declare the things a production agent actually needs: where its tools stop, what it must never do, when a human approves. The CE Score is a structural grade for exactly that — checking ten components and mapping the result to an AgentAz trust level from ADV to A5. It consumes the output of any generator as input, so it complements writing a prompt rather than competing with it.

Prompt DNA · the ten genes

Every prompt breaks into components. The score reads each one.

01 · ROLE
Role & identity
Is the agent's role, scope, and boundaries of authority stated explicitly?
02 · CONTEXT
Context
Does it supply the operating context the task depends on, not just the instruction?
03 · CONSTRAINTS
Constraints
Are hard rules and refusals declared — what the agent must and must not do?
04 · TOOLS
Tool boundaries
Are the tools and their limits declared? Undeclared tool scope is the top agent failure.
05 · MEMORY
Memory policy
Is there a rule for what persists across turns and what gets discarded?
06 · OUTPUT
Output schema
Is the output shape specified so downstream steps can rely on it?
07 · VALIDATION
Validation
Are there checks the agent runs against its own output before returning?
08 · SAFETY
Safety boundaries
Are guardrails present for destructive, irreversible, or sensitive actions?
09 · APPROVAL
Approval gates
Does a human approve before high-consequence actions? Required above A3.
10 · EXAMPLES
Examples
Are worked examples given to anchor behaviour on edge cases?
AgentAz trust ladder

The score maps to a trust level, not a vibe.

A level is earned only when every check it requires passes — a prompt can't buy A5 by being long. Higher levels demand declared tool boundaries, safety, and human approval.

ADV
Advisory only. Suggests, never acts. Missing the boundaries needed to be trusted with tools.
A3
Bounded execution. Role, constraints, and tool boundaries declared. No human gate yet.
A4
Gated execution. Everything in A3 plus approval gates on high-consequence actions.
A5
Governed execution. Full component set: validation, safety, memory policy, and gates all present.
Questions answer engines ask

FAQ

What is a CE Score?

A CE Score is a structural grade for an AI agent prompt. It checks whether the prompt declares the ten components a production agent needs — role, context, constraints, tool boundaries, memory policy, output schema, validation, safety, approval gates, and examples — and maps the result to an AgentAz trust level from ADV up to A5.

How is this different from a prompt generator?

A generator writes a prompt; CEPrompts audits one. It takes the output of any model or library as input and grades it against known agent failure modes. It complements generation instead of competing with it — a better model just gives you better raw material to audit.

What is context engineering?

Context engineering is the discipline of designing everything a model sees on each call — system prompt, tools, memory, retrieval, and state — rather than only the wording of one prompt. The CE Score measures how well a prompt is context-engineered for production.

Does the audit send my prompt anywhere?

No. The v1 structural audit runs entirely in your browser. Nothing is stored or transmitted.