rtrvr.ai
Log inBook DemoAdd to Chrome
Log in
Menu
Add to ChromeBook a demo

From the team

Blog

What we ship, how it performs,
and practical ways to put rtrvr to work.

How prefix caching cut our browser-agent token bill by 90%

Research

How prefix caching cut our browser-agent token bill by 90%

The cache boundary, measurements, and implementation choices that made long browser runs materially cheaper.

Read article
The self-improving action layer we are building

Product

The self-improving action layer we are building

A concrete roadmap for turning successful browser work into reusable actions without losing review and control.

Read article
From 500 event attendees to 10 prospects

Proof

From 500 event attendees to 10 prospects

How a browser-based enrichment workflow researched an attendee list, kept its sources, and prepared the best matches for review.

Read article
Websites need headless agents, not chatbots

Research

Websites need headless agents, not chatbots

Browser agents are a compatibility layer. The durable interface is a site-side agent that exposes intent handoff, knowledge, auth, tools, payments, and policy.

Read article
A cheaper browser agent: let DeepSeek write the plan as code

Research

A cheaper browser agent: let DeepSeek write the plan as code

What changed when we replaced repeated tool selection with a compact program executed against a text-first browser state.

Read article
Navigation Was Never the Moat: Why Agents Make the Sell Side Bigger, Not Smaller

Research

Navigation Was Never the Moat: Why Agents Make the Sell Side Bigger, Not Smaller

Models will soon navigate any website perfectly. That was never the moat. The agent that converts is the one the seller owns — its accounts, its payments, its data — and the world's biggest retailer just proved it inside ChatGPT.

Read article
Replacing browser-agent tool loops with eval() in a Chrome sandbox

Research

Replacing browser-agent tool loops with eval() in a Chrome sandbox

A for-loop should not cost tokens. We let the model write browser workflow code once, then execute it locally through a sandboxed `rtrvr.*` DSL layer.

Read article
The Four Architectures for Website AI Agents

Research

The Four Architectures for Website AI Agents

RAG bots can only talk. API-tool agents ship a second maintenance org. Code sandboxes burn per-user server cost. Only DOM-native execution inherits the web's own truth model — live HTML, user session, existing IAM. A structural comparison.

Read article
AI Subroutines: automation scripts that run inside your tab

Product

AI Subroutines: automation scripts that run inside your tab

Turn a successful browser action into a deterministic routine that can run again without another planning loop.

Read article

PUT IT TO WORK

Run the idea on a real site.

Start with the sites open in Chrome. Move repeated or parallel work to Cloud. Talk to us when the agent belongs inside your product or team.