Cloud Browsers
Every agent eventually hits the wall: a page that loads fine in curl and renders nothing in your pipeline. V4 removes the wall. Managed headless Chromium sits behind the API — spin up a browser, render JavaScript, interact with pages, take screenshots, and extract content from SPAs. No Puppeteer to configure, no browser pools to babysit, no anti-bot systems to fight. You send a URL; you get the rendered web.
Google SERP
For the first time, Keirolabs speaks to Google directly. One call returns the full results page as clean, structured JSON: organic results, knowledge panels, featured snippets, local packs, and “People also ask.” Fifty billion indexed pages behind a single endpoint — no parsing HTML, no proxies, no SERP scraping infrastructure of your own.
Stability, engineered — not promised
Every failure mode from our July incident has been architecturally eliminated. V4 runs on three independent compute providers, none carrying more than 45% of traffic, with per-region circuit breakers and active health probes every five seconds. Pre-warmed standby capacity activates in under twenty seconds. When something upstream breaks, your requests fail over before you notice — and the 99.95% uptime SLA holds because the system was built to hold it.
WebAgents, autonomous by default
The headline capability of V4 isn't an endpoint — it's an agent. The KeiroLabs WebAgent doesn't query a search API and hand you URLs. It operates a self-correcting ReAct loop over the live web: it plans its own sub-queries, scrapes and chunks what it finds, grades every chunk against a quality gate, and re-searches when the evidence is thin — up to six iterations — before synthesizing a cited answer.
Intent
Classifies the query and picks a depth: light, medium, or deep.
Plan
Generates 3–5 hyper-specific sub-queries aimed past SEO spam, at primary sources.
Execute
Runs the queries across the web; payloads are scraped, converted to Markdown, and chunked.
Quality gate
An internal judge grades every chunk. Insufficient or contradictory data triggers a new iteration — up to six.
Synthesize
Formats the final answer with strict, inline citations.
WebAgents in Slack
You don't need a pipeline to put the WebAgent to work. V4 ships it inside Slack — drop a question in a channel, and the same autonomous loop that tops the benchmarks runs it live: planning, searching, verifying, and answering with citations, right in the thread. Deep research where your team already is.
Benchmarked, not marketed
We put the WebAgent through four industry-standard datasets — over 6,000 queries in total — and published everything: methodology, prompts, judge configuration, and raw scores. Accuracy is graded by an independent LLM judge against official ground truth. Read the full study on GitHub
vs. frontier LLMs (zero-shot)
vs. search APIs & web agents
What was tested
| Dataset | Questions | Correct | Accuracy |
|---|---|---|---|
| SimpleQA | 4,321 | 3,907 | 90.42% |
| FreshQA | 500 | 453 | 90.60% |
| GAIA | 466 | 360 | 77.25% |
| Frames | 824 | 601 | 72.94% |
Everything else in V4
/search/lite
Sub-300ms searches at $0.25/1k requests, built for high-volume RAG pipelines that need speed over depth.
Streaming responses
SSE-based streaming on /answer and /agentic. Intermediate results arrive as they happen — no waiting on the full completion.
Regional pinning
Pin requests to EU, US, or APAC with the X-Region header. Data sovereignty with zero configuration.
Batch v2
10x throughput, live progress webhooks, auto-retry on transient failures. 100k queries in a single job.
SDKs, rebuilt
Fully typed Python, Node, and Go SDKs with async/await, streaming, and automatic retries. Zero config to start.
Adaptive rate limits
Per-endpoint token buckets that burst when you need them, with clear Retry-After headers and usage visibility in the dashboard.
Changelog
Cloud Browsers — managed headless Chromium behind the API, with session management, screenshots, and JS rendering.
Google SERP endpoint — structured Google results with organic, knowledge graph, and local pack parsing.
/search/lite — ultra-fast search at $0.25/1k for high-volume RAG pipelines.
SSE streaming on /answer and /agentic for real-time intermediate results.
Stability overhaul — multi-provider compute, circuit breakers, 5s active health probes, pre-warmed standby.
Batch v2 — 10x throughput, live progress webhooks, 100k query jobs.
All SDKs rebuilt with streaming, full type safety, and automatic retries.
Regional pinning is now GA — X-Region header for EU/US/APAC data sovereignty.
HTTP 200 on timeout — upstream timeouts now correctly return 503 with Retry-After.
Empty result ambiguity — genuine empty results now include an empty_reason field.