Prompt Optimization

What breaks when prompts live in code

Most teams start with prompts as strings in source files. It works until it doesn't - and then it breaks in ways that are hard to diagnose and even harder to fix quickly.

What you get

A prompt registry that your whole team can use - with the versioning, deployment controls, and runtime SDK your engineering team expects.

• →Store and version prompts in a central registry - full change history with author and timestamp
• →Deploy prompt updates to production without a code deployment or redeployment
• →Roll back to any previous prompt version with one click - no code changes required
• →Run A/B tests between prompt variants with configurable traffic splits in production
• →Pull the active prompt at runtime via the SDK - cached with sub-5ms overhead
• →Define input variables and preview rendered prompts in the built-in playground
• →Track which prompt version is active in each environment (dev, staging, production)
• →Add team members with role-based access - control who can edit, review, and deploy
• →Link prompt versions to eval run results - see quality scores before promoting to production
• →Organize prompts by project, model, use case, and team with tags and search

How it works

Prompts are stored in Respan as named, versioned objects. Your application fetches the active version at runtime via the SDK - a cached call under 5ms. When you publish a new version in the dashboard, the cache TTL expires and the new version is served automatically. No code change, no deployment, no downtime.

import openai
from respan import RespanClient

respan = RespanClient(api_key="YOUR_RESPAN_KEY")
openai_client = openai.OpenAI(api_key="sk-...")

# Before: hardcoded prompt in your code
# system_prompt = "You are a helpful customer support agent..."

# After: pull the active version from Respan at runtime
prompt = respan.prompts.get("customer-support-system")

# Variables are filled in at call time
rendered = prompt.render(
    product_name="Acme Pro",
    tone="friendly"
)

response = openai_client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": rendered},
        {"role": "user", "content": user_message},
    ]
)

# The prompt is cached locally with a 60s TTL.
# When you publish a new version in the dashboard,
# the next cache miss fetches it automatically.

Who uses this and how

Works with your stack

Prompts in code vs Respan Prompt Optimization

Frequently asked questions