braze.com
success
Claude Code
intent

What does braze.com do and who is it for? Explain it back to me.

3steps
31.7sduration
$0.0067cost
18,052tokens
4 steps1 reasoning step
home
docs
/product/overview
86%
answer from your site
100%
answer efficiency
100%
followed site links
answer sources
  • from this site86%
  • from agent knowledge14%
url discovery
  • followed a link67%
  • guessed the URL33%
insight

The agent successfully assembled a comprehensive overview of Braze's core positioning, products, pricing model, and target market from three pages (homepage, pricing, product overview). However, the site provides no competitive comparison or named alternatives, and omits concrete pricing figures, security certifications, and performance methodology — gaps the agent documented clearly and partially filled from general knowledge.

  • ›The site's primary pages are self-contained and navigation-ready: the homepage links directly to pricing and product overview, allowing the agent to fetch foundational information in three steps with 67% of navigation driven by in-page links.
  • ›Pricing is intentionally opaque: the site describes the MAU + Action Credits model and four tiers by name, but publishes no dollar figures, making cost estimation impossible without a sales call—this is a deliberate design choice, not missing content.
  • ›The site has zero competitive comparison pages or named rival mentions; the agent's section on 'comparison to alternatives' relies entirely on external knowledge (Salesforce, Adobe, Iterable, Klaviyo, etc.), explicitly acknowledged as not verified on Braze's domain.
  • ›Performance and differentiation claims lack methodological transparency: the Decisioning Studio gains (+25% revenue, +40% profit) cite a control group with no baseline, sample size, or timeframe; the Forrester ROI (457%) is noted as vendor-commissioned without independent verification links on the pages fetched.
  • ›The agent correctly identified 'composable' as undefined jargon and free trial terms as unstated, demonstrating critical reading; these gaps exist in the fetched pages, not in the agent's comprehension.

Want to run your own?

Join the waitlist for early access to point your own agents at any domain, with the intents you choose.

or talk to us about agent readiness →