Launch HN: Intuned (YC S22) – Build and run reliable browser automations as code

Stop writing browser automation

Describe what you need. Intuned Agent builds production-ready Playwright code, deploys it, and fixes it when sites change. You get the reliability of code without writing it yourself.

Scrapers

Extract data from any website—e-commerce, government portals, job boards, and more. Use Intuned Agent to generate and maintain your Playwright code. Deploy with built-in stealth, auth, scheduling, and scale.

Key Features:

Intuned Agent — Generate scrapers from a prompt and schema, fix issues with AI when sites change

Your code, your way — Write in TypeScript or Python using Playwright or any compatible library or framework

Stealth & auth — Anti-detection, captcha solving, login handling built in

Scheduled jobs & monitoring — Recurring runs with full logs and session recordings

Auto-scaling — One machine or hundreds, we handle it

Crawlers

Discover, navigate, and collect data across thousands of pages. Build crawlers that follow links, parse sitemaps, and index content—with built-in stealth, scheduling, and scale.

Key Features:

Your code, your way — Write in TypeScript or Python using Playwright or any compatible crawling library or framework

Crawl4AI support — First-class support for Crawl4AI—deploy and scale your crawlers without managing infrastructure

Stealth mode — Anti-detection, proxies, and captcha solving built in

Scheduled jobs & monitoring — Recurring crawls with full logs and session recordings

Scalable infrastructure — Control how many machines to run on, we handle the rest

RPA

Build browser automations that interact with websites on behalf of your users—form submissions, data entry, account actions, and more. Deploy with built-in auth handling, stealth, and concurrency control. Perfect for integrating with services that don't offer APIs.

Key Features:

Built-in authentication support — Write create.ts and check.ts (or .py), Intuned manages the session lifecycle—validating, reusing, and recreating as needed

Your code, your way — TypeScript or Python with Playwright, or AI-driven via Anthropic Computer Use, OpenAI CUA, Stagehand, Browser-use, or Gemini Computer Use

UI actions or network calls — Automate via browser interactions or faster in-browser network requests

Stealth mode — Anti-detection, proxies, and captcha-solving built in

API-first with concurrency control — Deploy as an API endpoint, set parallel limits, we queue and execute

AI Automation

Build AI-powered automations that can navigate, interact, and extract from any website. Whether you're building AI agents as a product or using AI to automate scraping and workflows—deploy with built-in stealth, auth, and scale.

Key Features:

Works with any AI browser library or API — Anthropic Computer Use, OpenAI CUA, Stagehand, Browser-use, Gemini Computer Use, Intuned/Browser SDKs, and more

Mix code and AI — Combine deterministic Playwright logic with AI-driven steps in a single automation

Stealth mode — Anti-detection, proxies, and captcha solving built in

Built-in authentication support — Write create.ts and check.ts (or .py), Intuned manages the session lifecycle - you can use AI for that too

AI usage controls — Monitor and limit AI credit usage across your automations

Scalable infrastructure — Deploy as an API or schedule jobs, control concurrency, we handle the rest

Managed Scraping

Need hundreds or thousands of scrapers? Our solution engineers—powered by Intuned Agent—build and maintain them for you. We've delivered thousands of production scrapers. You tell us what data you need, we handle the rest.

Key Features:

We build, you ship — Tell us the sites and schemas, we deliver production-ready scrapers

Cost-effective delivery — Solution engineers + Intuned Agent means faster builds at lower cost

Ongoing maintenance — Sites change, we update your scrapers so they keep running

Your code, no lock-in — You own the code, switch to self-serve anytime, no reselling or black boxes

Flexible pricing — Flat fee per source or custom arrangements

Built on Intuned infrastructure — Same stealth, auth, scale, and monitoring you'd get building yourself

Web Tasks API

Web Tasks that learn each run

Run any web task from a prompt. Add a reuseKey and it learns —faster and cheaper with every run.

const companySchema = z.array(
z.object({
name: z.string(),
location: z.string(),
}),
);
await webTasks.run({
task: "Scrape YC companies. Return name, batch, description, and URL.",
startUrl: "https://www.ycombinator.com/companies",
parameters: { batch: "S24" },
outputSchema: companySchema,
reuseKey: "yc_companies_scraper",
});
// ✓ created skill yc_companies_scraper
// ✓ wrote reusable helpers
// ✓ returned 247 companies · 6m 12s · $0.84 AI + 0.10 compute hrs
await webTasks.run({
task: "Scrape YC companies. Return name, batch, description, and URL.",
startUrl: "https://www.ycombinator.com/companies",
parameters: { batch: "W24" },
outputSchema: companySchema,
reuseKey: "yc_companies_scraper",
});
// ✓ reused skill yc_companies_scraper
// ✓ returned 208 companies · 58s · $0.12 AI + 0.02 compute hrs

class Company(BaseModel):
name: str
location: str
await web_tasks.run(
task="Scrape YC companies. Return name, batch, description, and URL.",
start_url="https://www.ycombinator.com/companies",
parameters={"batch": "S24"},
output_schema=list[Company],
reuse_key="yc_companies_scraper",
)
# ✓ created skill yc_companies_scraper
# ✓ wrote reusable helpers
# ✓ returned 247 companies · 6m 12s · $0.84 AI + 0.10 compute hrs
await web_tasks.run(
task="Scrape YC companies. Return name, batch, description, and URL.",
start_url="https://www.ycombinator.com/companies",
parameters={"batch": "W24"},
output_schema=list[Company],
reuse_key="yc_companies_scraper",
)
# ✓ reused skill yc_companies_scraper
# ✓ returned 208 companies · 58s · $0.12 AI + 0.02 compute hrs

Intuned Web Tasks runs browser automations from natural-language instructions — scraping, crawling, form filling, multi-step actions, and downloading files. Use it whenever the user asks to extract data from, act on, or pull files from a website. ## Flow If no task has been given yet, ask what they want to automate in one line and offer 1–2 examples — e.g. "What would you like to automate? For example, 'scrape all companies from the YC directory' or 'download every PDF from a site'." When the user gives you an automation task: 1. Ask whether to trigger via the Intuned CLI or the SDK (TypeScript or Python). 2. Trigger it, using their request as the task. Don't ask anything else unless a required input is missing. ## Optional inputs Include these only when they apply and you can infer them from the task — never ask for them: - parameters — dynamic inputs that change between runs. - outputSchema — JSON Schema, only when extracting structured data. - startUrl — only when known; the agent infers it otherwise. - reuseKey — when you re-run the same or similar task (e.g. to change a limit or parameter), reuse the reuse.key the previous run returned, or a key the user gives you. Only omit it for a brand-new task; the server then generates one — keep it and reuse it on follow-ups for the same/similar task. Never ask whether the task is repetitive. ## CLI Install first if missing: npm install -g @Intuned/cli, verify with intuned -v. intuned platform webtasks run "<task>" --json Add --reuse-key <key> when re-running the same/similar task (the prior run's key) or when the user provided one. ## TypeScript SDK (npm install @Intuned/client) import { IntunedClient } from "@Intuned/client"; await client.webTasks.run({ task: "<what to do>", startUrl: "<url, optional>", parameters: { /* optional / }, outputSchema: { / jsonSchema, optional */ }, // reuseKey: the prior run's key on follow-ups, or one the user gave }); ## Python SDK (pip install intuned-client) from intuned_client import IntunedClient client.web_tasks.run(body={ "task": "<what to do>", "start_url": "<url, optional>", "parameters": {}, // optional "output_schema": {}, // optional }) ## Docs Refer here for more options and details: https://intunedhq.com/docs/main/07-web-tasks/overview.md

Intuned Agent

The AI agent that builds,updates, and fixes automations

Describe what you need. The agent builds it, fixes it, and keeps it running.

Build any automation

Describe what you need — a scraper, RPA workflow, crawler, or any automation — and the agent builds it as production-ready code.

Edit project

Describe the change. The agent edits the code, validates against the live site, and delivers a diff you can review.

Update this to get only US Jobs

Fix with AI

One click from a failed run. The agent reads the error, analyzes traces, and writes a fix.

"job title": "Creative Director""url": "jobs.apple.com/..."

Platform Features

Infrastructure that just works

Everything you need to run browser automations in production. Built in, not bolted on.

Built-in authentication

Write create.ts and check.ts (or .py), we handle the rest—validating, reusing, and recreating sessions automatically.

Anti-detection suite

Stealth mode, automatic captcha solving, and proxy support built in. Run automations without getting blocked.

Online IDE

Zero setup, no dependencies. Write, test, and deploy automations from your browser. Fully integrated environment.

• US - Specialist: Full-Time, Part-Time, and Part-Time TemporaryApple RetailMay 14, 2026Various Locations within United States☆
• Multimodal Generative Modeling EngineerSoftware and ServicesMay 14, 2026Cupertino☆
• Multimodal Generative Modeling EngineerSoftware and ServicesMay 14, 2026San Diego☆
• Java Server Engineer-ASESoftware and ServicesMay 14, 2026San Diego☆
• Front End SW Engineer - iOS / Web - iCloudSoftware and ServicesMay 14, 2026San Diego☆
• Hardware System Design Electrical Engineer - iPhone DevboardHardwareMay 14, 2026Cupertino☆
• Engineering Program Manager, PackagingHardwareMay 14, 2026Cupertino☆
• Senior Data Scientist, Marketing AnalyticsOperations and Supply ChainMay 14, 2026Cupertino☆
• Engineering Program Manager, Data Center OperationsSoftware and ServicesMay 14, 2026Garland☆
• Engineering Program Manager, Data Center OperationsSoftware and ServicesMay 14, 2026Maiden☆
• Systems Software EngineerHardwareMay 14, 2026San Diego☆

CLI

Local development with full control. CI/CD ready, team collaboration, version control.

Observability

Full logs, traces, and session recordings for every run. See what happened and why.

Runs

Single execution via API. Set max concurrent requests, we queue the rest. Built for RPA and integrations.

const result = await
intunedClient.project.run.start("rpa-example",
{
"api": "list",
"parameters": {
"cateogry": "books"
},
"retry": {
"maximumAttempts": 4
},
"authSession": {
"id": "test-auth-session",
}
});

result = await intuned_client.project.run.start(
"rpa-example",
{
"api": "list",
"parameters": {
"category": "books"
},
"retry": {
"maximum_attempts": 4
},
"auth_session": {
"id": "test-auth-session",
}
}
)

Jobs

Scheduled, batched execution. Control how many machines to run on. Built for scrapers and crawlers.

const result = await
intunedClient.project.run.start("rpa-example",
{
"api": "list",
"parameters": {
"cateogry": "books"
},
"retry": {
"maximumAttempts": 4
},
"authSession": {
"id": "test-auth-session",
}
});

result = await intuned_client.project.run.start(
"rpa-example",
{
"api": "list",
"parameters": {
"category": "books"
},
"retry": {
"maximum_attempts": 4
},
"auth_session": {
"id": "test-auth-session",
}
}
)

Built for developers

API-first · No lock-in · Usage-based pricing · Usage monitoring & alerts

Testimonials

Hear from our users

“ Within an hour of trying the agent, I knew this was going to save us months of work. Writing and maintaining scrapers has been our biggest time sink for as long as I can remember. We can't wait to move everything over.”

“ The Intuned team knows browser automation inside out. Complex auth, aggressive bot detection — they figure it out every time. Hundreds of scrapers running reliably, and we barely have to think about it.”

“ We depend on Intuned for production workloads — thousands of runs a day. The platform handles browser automation flawlessly, and the monitoring is the best we've seen. Browser traces, logs, timing — when something goes wrong, we know exactly why in minutes.”

“ Within an hour of trying the agent, I knew this was going to save us months of work. Writing and maintaining scrapers has been our biggest time sink for as long as I can remember. We can't wait to move everything over.”

Blog

Latest news

How bot detection works (and why your automation gets blocked)

A builder's guide to the bot detection stack: IP and TLS fingerprinting, browser and framework signals, behavioral analysis, and CAPTCHAs, and the specific things that get a legitimate scraper or RPA flow caught.

Jun 2, 2026

Run Webwright scripts in the cloud with Intuned

Webwright writes you a working browser script. The webwright-to-intuned skill turns that craft into a hosted API your product can call, with your logic untouched.

Jun 2, 2026

Introducing the New Intuned

A code-first browser automation platform with an AI agent that builds and maintains your automations as deterministic, production-ready code.

Apr 4, 2026

Examples