AI Agents

Agents you configure.
Not agents you code.

Name it, write the system prompt, pick a model, attach tools and knowledge. Save, and the next request uses it — no redeploy, no release train.

Start free trialExplore a live demo

14 days free · No credit card · Bring your own model keys

What an agent is

Four fields and a name.

That is the whole definition. Change any of it in the dashboard and it takes effect on the next message, not the next deploy.

System prompt

Describe the behaviour you want in plain language and set the temperature. No prompt-assembly code in your repository.

System prompt
Temperature0.7

Model

GPT-4o, Claude, Gemini, Llama, Mistral, Groq. The model is a dropdown on the agent, not a dependency in your build.

Claude Sonnet
Claude Sonnet
GPT-4o
Gemini 2.5 Pro
Llama 4

Tools

Register an MCP server and the agent discovers what it can call. No hand-written function schemas to keep in sync.

DB
API
CRM
MCP

Knowledge

Attach PDFs, FAQs and crawled pages. Retrieval runs on every message, so replies come from your material.

Knowledge
PDFpolicy.pdf
PDFmanual.pdf
FAQFAQs · 24 entries

Where it runs

Configure once. Answer in four places.

The same agent serves your backend, your website, your team's internal chat and the playground you tested it in. One definition, four surfaces.

REST API

POST to /v1/chat/stream with the agent name. History, retries, streaming and token accounting are already handled.

POST
curl api.sentientone.ai
  /v1/chat/stream \
  -H "x-api-key: sk-so-•••"
  -d '{"agent":"support"}'

Website widget

One script tag puts the same agent in front of your visitors, styled to sit inside your own design.

Team workspace

Colleagues ask the agent internally, each with their own login and their own private history.

ABC
Workspace
Q3 numbers?
Up 32% on Q2 — handbook, p.4

Dashboard playground

Try a prompt, swap the model, read the trace — before a single customer sees the answer.

Config

Chat

TestReplyTraced

What teams say

“Every time you want to add AI to your app, you end up writing a ton of code — managing API keys, handling conversation history, engineering prompts, counting tokens. And then six months later a better model comes out and you have to refactor everything. SentientOne just removes all of that.”
Daniel Marsh · CTO

Pricing

Plans for every team size.
Fourteen-day trial, cancel anytime.

Starter

$19/month

For developers putting the first AI feature into a product.

Start free trial

1 agent · 10k requests/mo

  • 1 MCP server per agent
  • Knowledge — 100 credits †
  • Embeddable chat widget
  • Analytics · 30 requests/min
  • 14-day logs & chat history
  • Community support
  • Streamable HTTP endpoint
  • AI Workspace (team chat)

Pro

Most popular
$49/month

For teams running AI in production and watching the numbers.

Start free trial

5 agents · 50k requests/mo

  • 2 MCP servers per agent
  • Knowledge — 300 credits †
  • Full tracing, cost & token analytics
  • Streamable HTTP endpoint
  • AI Workspace (team chat)
  • Extra seats at $9/member
  • 90-day logs · 50 requests/min
  • Email support, 48h response

Enterprise

Custom

For organisations with compliance, scale or data-residency rules.

Talk to us

Unlimited agents & requests

  • Unlimited MCP servers & knowledge
  • Self-hosted / single-tenant option
  • Custom rate limits & log retention
  • SSO and organisational support
  • Security review assistance
  • Dedicated SLA & onboarding

Prices in USD. Every plan includes bring-your-own model keys, the agent chat interface, and a 14-day trial. † 1 credit = 1 FAQ · 5 credits = 1 document.

Get started

Configure an agent. Ship the feature.

Fourteen days free, your own model keys, and nothing to install before the first reply streams back.

  • Create the agent
  • Copy your API key
  • POST a message
  • Read the trace
Start free trialSee pricing

14 days free · No credit card required