Knowledge
Your documents,
not the open internet.
Upload PDFs, curate FAQs, crawl your site. Retrieval runs before the model does, and each reply names the page it came from.
14 days free · No credit card · Bring your own model keys
Getting content in
Whatever your knowledge already lives in. Nothing to reformat first.
Documents, curated answers and live web pages all land in one index your agents query on every request. Parsing and chunking happen for you.
Documents
Drop in PDFs, contracts, manuals and exported wikis. Text, tables and headings are parsed and split for retrieval.
FAQs
Write the answer you want given, once. Edit the entry and every agent uses the new wording on the next reply.
Web crawling
Point us at a URL. We follow the site, index the pages, and re-crawl on the schedule you set.
Per-agent libraries
Support, sales and HR each read their own shelf. No agent answers from content it should not have seen.
Scoped sources
What changes
Grounded replies, with the receipt attached.
The same index feeds your widget, your API and your team's workspace — and every answer can say exactly where it came from.
Cited sources
Each reply lists the document, FAQ or URL behind it, down to the page. Auditable without asking anyone.
Refunds are processed within 30 days[1] of the original purchase[2].
Grounded API
Retrieval happens server-side before the model runs. You send a question, not a hand-stuffed context window.
{
"answer": "Refund within 30 days",
"source": "policy.pdf#p12"
}Widget answers
Your site chatbot quotes your refund policy, rather than a plausible guess at what your refund policy might be.
Team workspace
Colleagues ask the handbook a question instead of searching the shared drive for the version that is current.
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.”
Pricing
Plans for every team size.
Fourteen-day trial, cancel anytime.
Starter
For developers putting the first AI feature into a product.
Start free trial1 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 popularFor teams running AI in production and watching the numbers.
Start free trial5 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
For organisations with compliance, scale or data-residency rules.
Talk to usUnlimited 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
Upload one document. Ask it a question.
The whole loop — upload, index, answer, cite — takes a few minutes on the free trial. Start with the file your team already argues about.
- Create an agent
- Add a PDF, FAQ or URL
- Ask a question
- Check the citation
14 days free · No credit card required