Skip to main content
Specado
Spec-First Prompts · Git-native

The Declarative Standard for LLM Workflows.

Define, test, and run your AI prompts with a simple, portable YAML or JSON spec. Go from idea to production without the boilerplate and framework lock-in.

spec.yaml
apiVersion: v1
kind: PromptFlow
metadata:
  name: lead-qualifier
runtime:
  model: gpt-4o
sop:
- role: system
  prompt: |
    Qualify this lead based on their inquiry.
    Respond with QUALIFIED or NOT_QUALIFIED.
tests:
- name: "is-qualified"
  input:
    lead_email: "I'm interested in your enterprise solution"
  assert:
  - type: contains
    value: "QUALIFIED"
exports:
- format: langgraph
  output: ./lead_qualifier.py

Tired of Fragile, Untestable AI Code?

Scattered Logic

Prompt strings, API keys, and model parameters are spread all over your codebase.

"Guess-and-Check" Testing

Reliably testing LLM outputs is a nightmare, making CI/CD impossible.

Framework Lock-in

Building with one agentic framework means a total rewrite if you want to switch.

The Solution

“Specado centralizes your entire LLM workflow—prompts, models, and tests—into a single, elegant spec.yaml or spec.json file. It's version-controllable, human-readable, and machine-executable.”

How It Works

Visually walk through the core developer loop in three simple steps.

1. Define

Create a clean, version-controlled spec.yaml file with prompts and tests.

spec.yaml
apiVersion: v1
kind: PromptFlow
metadata:
  name: lead-qualifier
runtime:
  model: gpt-4o
sop:
- role: system
  prompt: "Qualify this lead..."
tests:
- name: "is-qualified"
  assert:
  - type: contains
    value: "QUALIFIED"

2. Test

Run your prompts through validation with the CLI and get instant feedback.

terminal
$ specctl test ./spec.yaml
✔ is-qualified (152ms)


Passed: 1, Failed: 0

3. Integrate

Import into any Python or Node.js project with a simple, clean API.

integration.py
import specado


result = specado.run(
    './spec.yaml',
    inputs={'lead_email': '...'}
)
print(result.output)
The Ejection Seat

Start Simple. Scale Anywhere. Never Get Locked In.

Specado is the perfect starting point. When your project needs the power of a full agentic framework, don't rewrite—export. A single command transforms your spec into a native LangGraph or CrewAI project.

Specado
Specado
LG
CA
LangGraph / CrewAI
terminal
$ specctl export --format langgraph
No vendor lock-in, ever

Core Benefits

Built for developers who demand reliability, performance, and flexibility.

✅Test-Driven Development for Prompts
Embed assertions directly in your spec for rock-solid CI/CD.
🚀Blazing Fast & Safe
A high-performance Rust core means speed and memory safety you can rely on.
🐍Polyglot Power
Use the same spec and engine from Python, Node.js, or the CLI.
✨Superior DevEx
Get rich, location-aware error messages that pinpoint issues in your spec down to the line and column.

Ready to Build Better AI?

python
$pip install specado
node.js
$npm install specado
rust
$cargo install specado