# PromptRails - The orchestration platform for production AI agents

Source: https://0.0.0.0:8080/

---

WE BUILD THE RAILS · YOU SHIP THE AGENTSOPEN SOURCE → PRODUCTION · 2026

# Ship the  
agent. Skip  
the plumbing.

Promptrails is the control plane for AI agents in production —prompts, orchestration, tracing, guardrails, cost, across 14 LLM providers. One contract. No lock-in.

[Start building →](https://app.promptrails.ai/?utm_source=website&utm_medium=cta&utm_campaign=signup&utm_content=hero)[$pip install promptrailsnpm install @promptrails/sdkgo get github.com/promptrails/go-sdk](/docs/quickstart)

What you replace

Prompt registryPromptLayer · Pezzo

Gateway / routerOpenRouter · Portkey

TracingLangfuse · LangSmith

GuardrailsGuardrails AI · NeMo

EvalsBraintrust · Patronus

Approval queue(homegrown)

01 / AI ENGINEERS

### Build agents, not plumbing.

One SDK, 14 providers, versioned prompts, full tracing — Python, JS, or Go.

[Read the docs →](/docs/introduction)

02 / PRODUCT TEAMS

### Iterate on prompts, no deploy.

Promote, A/B, roll back from the dashboard. Evals + scores in the same loop.

[See versioning →](/docs/prompt-versioning)

03 / ENG LEADERS

### Cost & latency, by span.

Per-agent rollups, p99 dashboards, scanner verdicts. Decide what ships, with data.

[View metrics →](/docs/tracing)

04 / ENTERPRISES

### SSO. Audit. BYO cloud.

Roles, audit log, encrypted credentials, DPA on request. SOC 2 in progress.

[Talk to us →](/contact)

03 / Platform

## Six tools.  
_One contract._

Most teams ship an agent by gluing six SaaS tools together. We replaced the glue with a single SDK and a single trace.

/ 01

### Agents.

Five execution strategies — simple, chain, multi-agent, workflow, composite — composed from versioned prompts and tools.

Agent.execute()

/ 02

### Prompts.

Jinja2 templates with input/output schemas. Promote, roll back, A/B without a deploy.

Prompt.latest("classify")

/ 03

### Tracing.

OTel-style distributed traces with 14 span kinds. Every LLM call, tool, and guardrail captured.

span.kind = "llm.chat"

/ 04

### Guardrails.

14 scanners. PII, toxicity, prompt injection, jailbreak. Block, redact, or log.

guardrails: \["pii"\]

/ 05

### Cost.

Per-execution and per-span cost across providers. Workspace and per-agent rollups.

cost\_usd: 0.0042

/ 06

### MCP tools.

First-class Model Context Protocol. Connect APIs, data sources, remote MCP servers.

tools: \[mcp.server("sql")\]

14

LLM PROVIDERS

— ONE API

70+

INTEGRATIONS

— DBs, vector, SaaS

p99 < 18ms

GATEWAY OVERHEAD

— measured weekly

38%

AVG COST CUT

— from routing alone

04 / Topology

## One graph.  
Every span.

Every run is a tree of spans — calls, tools, guardrails, retrievals — with cost, latency, and the full prompt + response captured at each node.

01Drill into any span — input, output, model, tokens

02Compare prompt versions head-to-head

03Filter by cost, latency, scanner verdict, score

04Export to your existing OTel collector

EXEC GRAPH · CHAIN STRATEGY

INPUTAGENTCLASSIFYgpt-4.1TOOL · sqlRESOLVEsonnetGUARD · piiGUARD · toxOUTPUTscored · 0.0042 

05 / SDK

## Wherever  
you write code.

[](https://github.com/promptrails/python-sdk "Python on GitHub")

Python

$ pip install promptrails

[](https://github.com/promptrails/javascript-sdk "JavaScript on GitHub")

JavaScript

$ npm i @promptrails/sdk

[](https://github.com/promptrails/go-sdk "Go on GitHub")

Go

$ go get promptrails.ai/sdk

[](https://github.com/promptrails/cli "CLI on GitHub")

CLI

$ brew install promptrails/tap/cli

[](/docs/mcp-server "MCP server docs")

MCP server

$ claude mcp add promptrails

[](https://github.com/promptrails/vscode-extension "VSCode ext on GitHub")

VSCode ext

$ code --install-extension promptrails

06 / DASHBOARD · MULTI-PAGE · PIN-PROTECTABLE · BACKED BY YOUR AGENTS

app.promptrails.ai

P

Production

Go to...⌘K

ProductionStudio

### Studio

Tab-based explorer for agents, prompts, data sources, and tools.

AGENTS

PROMPTS

DATA SOURCES

MCP TOOLS

Customer Support Botv3

active

Type

multi\_agent

System prompt

You are a customer support agent for {{ company.name }}. Be concise; defer to the @billing\_lookup tool for invoice questions.

Model

gpt-4o

Temp

0.3

Tools

2 attached

07 / Field reports

> “We deleted four internal services the day we shipped Promptrails. Tracing alone paid for it inside a month — turns out half our prompts were calling GPT-5 when Haiku was fine.”

Cardash

Kenneth

09 / Get on it

## 5 min  
from _pip install promptrailsnpm i @promptrails/sdkgo get promptrails.ai/sdk_  
to traced agent in production.

[Start building →](https://app.promptrails.ai/?utm_source=website&utm_medium=cta&utm_campaign=signup&utm_content=final_cta)[Read the docs](/docs/introduction)