Browser Automation for Agents arenaBuyer checklist

Every requirement we judge browser automation for agents products against, as a ready-to-send RFP checklist — with each item's priority, why it matters, and how the top-ranked products score on it today.

52 requirements · 14 themes · verdicts for 7 products · updated 2026-09-16 · priorities mirror the story weights our scoring uses (methodology)

Procurement report →

Show the markdown export

# Browser Automation for Agents — buyer checklist (RFP)

Derived from ProductArena's evidence-graded user-story taxonomy for Browser Automation for Agents: 52 judged requirements. Priorities mirror story weights (3 = must-have, 2 = should-have, 1 = nice-to-have).

## Action primitives

- [ ] **[must-have]** Drive the page through DOM-understanding action primitives (act/click/type on described elements) that survive selector and layout changes
- [ ] **[should-have]** Cache resolved actions or generated code so repeat runs replay deterministically at lower cost and latency than re-prompting the LLM
- [ ] **[should-have]** Switch to a vision or computer-use action mode that operates on screenshots for canvases and UIs the DOM path can't handle
- [ ] **[nice-to-have]** Preview candidate actions on the current page (observe/plan) before committing the agent to act

## Agenticness

- [ ] **[must-have]** Plug MCP servers into this product so it can use their tools
- [ ] **[must-have]** Connect an agent via an official MCP server
- [ ] **[must-have]** Drive the product through a documented public API
- [ ] **[must-have]** Delegate tasks to a built-in AI assistant inside the product
- [ ] **[should-have]** Point an agent at llms.txt or agent-oriented docs
- [ ] **[should-have]** Run the product headlessly / in CI for automation
- [ ] **[should-have]** Use an official CLI
- [ ] **[should-have]** Issue scoped/least-privilege API credentials for an agent
- [ ] **[should-have]** Build against official SDKs
- [ ] **[should-have]** Subscribe to events via webhooks
- [ ] **[should-have]** Get AI-generated insights and suggestions from my data inside the product
- [ ] **[should-have]** Set up automations that run autonomously in the background
- [ ] **[should-have]** Operate the product with natural-language commands
- [ ] **[should-have]** Explore an interactive API reference with runnable examples
- [ ] **[should-have]** Download a machine-readable API spec (OpenAPI or equivalent)
- [ ] **[should-have]** Rely on versioned APIs with a documented deprecation policy
- [ ] **[nice-to-have]** Test against a sandbox environment without touching production data

## Auth session persistence

- [ ] **[must-have]** Persist logged-in browser state in reusable profiles so agents skip the login wall on every subsequent run
- [ ] **[should-have]** Connect my existing Playwright, Puppeteer, or CDP automation code to the product's browsers instead of rewriting it
- [ ] **[should-have]** Store credentials in a vault and have the agent complete logins including TOTP/2FA challenges without exposing secrets to the model

## Automation depth

- [ ] **[must-have]** Define rules that trigger actions automatically on events
- [ ] **[should-have]** Perform bulk operations across many items at once
- [ ] **[should-have]** Schedule recurring jobs or workflows
- [ ] **[nice-to-have]** Version, review, and roll back my automations

## Deployment modes

- [ ] **[should-have]** Run the agent against a local browser on my own machine for development, without any cloud account

## Framework model support

- [ ] **[should-have]** Plug the browser layer into agent frameworks (Claude Agent SDK, Vercel AI SDK, LangChain, CrewAI) through documented adapters
- [ ] **[should-have]** Bring my own LLM provider — the framework is model-agnostic rather than locked to one vendor's models

## Nl task execution

- [ ] **[must-have]** Hand the product a natural-language goal and it completes a multi-step web task end to end — navigating, filling forms, and clicking through flows
- [ ] **[should-have]** Submit a browser task over a hosted HTTP API and receive the result by polling or webhook, without managing any browser myself
- [ ] **[should-have]** Compose repeatable multi-step workflows with loops, conditionals, and parameters instead of one-shot prompts

## Openness

- [ ] **[must-have]** Export all of my data in open formats and leave
- [ ] **[must-have]** Self-host the core product
- [ ] **[should-have]** Do everything through the API that I can do in the UI
- [ ] **[should-have]** Read the product's source under an open license

## Pricing limits

- [ ] **[should-have]** See transparent per-task or per-browser-hour pricing and documented rate/concurrency limits before committing

## Privacy posture

- [ ] **[must-have]** Prevent my data from being used to train AI models
- [ ] **[should-have]** Choose where my data is stored (region/residency)
- [ ] **[should-have]** Control data retention and deletion
- [ ] **[should-have]** Opt out of telemetry and usage tracking

## Replay debugging

- [ ] **[should-have]** Watch a session live and take human control mid-run when the agent gets stuck
- [ ] **[should-have]** Debug a failed agent run from recorded replays — video, screenshots, step-by-step action timelines

## Scale parallelism

- [ ] **[should-have]** Run a fleet of concurrent browser sessions with documented concurrency limits and programmatic session management
- [ ] **[nice-to-have]** Get webhook notifications when tasks and sessions finish instead of polling for status

## Stealth captcha

- [ ] **[should-have]** Rely on a documented captcha stance — automatic solving, human fallback, or explicit non-support — instead of silent task failures
- [ ] **[should-have]** Enable stealth fingerprinting and residential or geo-targeted proxies so legitimate automations aren't blocked as bots
- [ ] **[nice-to-have]** Point to the vendor's published acceptable-use and anti-abuse posture governing what its stealth and automation features may be used for

## Structured extraction

- [ ] **[must-have]** Extract typed, schema-validated data (Zod/Pydantic-style) from pages the agent visits, not just raw text
- [ ] **[nice-to-have]** My agent can download files from and upload files to the sites it operates, with the artifacts retrievable afterwards

---

Source: https://ultrametric.ai/productarena/arena/browser-agents (evidence-graded verdicts for 7 products) · methodology: https://ultrametric.ai/productarena/methodology

Chips show the top 5 ranked products' current verdict on each requirement — ✓ full · ~ partial · ! disputed · — none · n/a not applicable.

Action primitives — stories about action primitives in this arenaAction primitives· 4 items

Stories about action primitives in this arena

developerDrive the page through DOM-understanding action primitives (act/click/type on described elements) that survive selector and layout changes
Core requirement — weighs 3× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
developerCache resolved actions or generated code so repeat runs replay deterministically at lower cost and latency than re-prompting the LLM
Important, not disqualifying — weighs 2× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
developerSwitch to a vision or computer-use action mode that operates on screenshots for canvases and UIs the DOM path can't handle
Important, not disqualifying — weighs 2× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
developerPreview candidate actions on the current page (observe/plan) before committing the agent to act
Differentiator, not a dealbreaker — weighs 1× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
nice-to-have

Agenticness — how well agents can access and operate the productAgenticness· 17 items

How well agents can access and operate the product

ai-native userPlug MCP servers into this product so it can use their tools
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userConnect an agent via an official MCP server
Core requirement — weighs 3× in arena scoring · 4 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userDrive the product through a documented public API
Core requirement — weighs 3× in arena scoring · 5 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userDelegate tasks to a built-in AI assistant inside the product
Core requirement — weighs 3× in arena scoring · 4 of 5 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userPoint an agent at llms.txt or agent-oriented docs
Important, not disqualifying — weighs 2× in arena scoring · all 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userRun the product headlessly / in CI for automation
Important, not disqualifying — weighs 2× in arena scoring · 5 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userUse an official CLI
Important, not disqualifying — weighs 2× in arena scoring · 3 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userIssue scoped/least-privilege API credentials for an agent
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userBuild against official SDKs
Important, not disqualifying — weighs 2× in arena scoring · 5 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userSubscribe to events via webhooks
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userGet AI-generated insights and suggestions from my data inside the product
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userSet up automations that run autonomously in the background
Important, not disqualifying — weighs 2× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userOperate the product with natural-language commands
Important, not disqualifying — weighs 2× in arena scoring · 4 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userExplore an interactive API reference with runnable examples
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)
Important, not disqualifying — weighs 2× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userRely on versioned APIs with a documented deprecation policy
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userTest against a sandbox environment without touching production data
Differentiator, not a dealbreaker — weighs 1× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
nice-to-have

Auth session persistence — stories about auth session persistence in this arenaAuth session persistence· 3 items

Stories about auth session persistence in this arena

developerPersist logged-in browser state in reusable profiles so agents skip the login wall on every subsequent run
Core requirement — weighs 3× in arena scoring · 6 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
developerConnect my existing Playwright, Puppeteer, or CDP automation code to the product's browsers instead of rewriting it
Important, not disqualifying — weighs 2× in arena scoring · 4 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
automation-engineerStore credentials in a vault and have the agent complete logins including TOTP/2FA challenges without exposing secrets to the model
Important, not disqualifying — weighs 2× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Automation depth — how much of the product can run unattendedAutomation depth· 4 items

How much of the product can run unattended

ai-native userDefine rules that trigger actions automatically on events
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userPerform bulk operations across many items at once
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userSchedule recurring jobs or workflows
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userVersion, review, and roll back my automations
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
nice-to-have

Deployment modes — stories about deployment modes in this arenaDeployment modes· 1 item

Stories about deployment modes in this arena

developerRun the agent against a local browser on my own machine for development, without any cloud account
Important, not disqualifying — weighs 2× in arena scoring · 3 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Framework model support — stories about framework model support in this arenaFramework model support· 2 items

Stories about framework model support in this arena

developerPlug the browser layer into agent frameworks (Claude Agent SDK, Vercel AI SDK, LangChain, CrewAI) through documented adapters
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
developerBring my own LLM provider — the framework is model-agnostic rather than locked to one vendor's models
Important, not disqualifying — weighs 2× in arena scoring · 2 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Nl task execution — stories about nl task execution in this arenaNl task execution· 3 items

Stories about nl task execution in this arena

developerHand the product a natural-language goal and it completes a multi-step web task end to end — navigating, filling forms, and clicking through flows
Core requirement — weighs 3× in arena scoring · 3 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai agentSubmit a browser task over a hosted HTTP API and receive the result by polling or webhook, without managing any browser myself
Important, not disqualifying — weighs 2× in arena scoring · 1 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
automation-engineerCompose repeatable multi-step workflows with loops, conditionals, and parameters instead of one-shot prompts
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Openness — open source, data portability, and self-hosting storiesOpenness· 4 items

Open source, data portability, and self-hosting stories

ai-native userExport all of my data in open formats and leave
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userSelf-host the core product
Core requirement — weighs 3× in arena scoring · 3 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userDo everything through the API that I can do in the UI
Important, not disqualifying — weighs 2× in arena scoring · 1 of 6 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userRead the product's source under an open license
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits· 1 item

Free-tier ceilings, usage caps, and rate limits before you have to pay

developerSee transparent per-task or per-browser-hour pricing and documented rate/concurrency limits before committing
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Privacy posture — data-handling and privacy storiesPrivacy posture· 4 items

Data-handling and privacy stories

ai-native userPrevent my data from being used to train AI models
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
ai-native userChoose where my data is stored (region/residency)
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userControl data retention and deletion
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
ai-native userOpt out of telemetry and usage tracking
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Replay debugging — stories about replay debugging in this arenaReplay debugging· 2 items

Stories about replay debugging in this arena

automation-engineerWatch a session live and take human control mid-run when the agent gets stuck
Important, not disqualifying — weighs 2× in arena scoring · 2 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
automation-engineerDebug a failed agent run from recorded replays — video, screenshots, step-by-step action timelines
Important, not disqualifying — weighs 2× in arena scoring · 2 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have

Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism· 2 items

Running many jobs at once — concurrency, fleets, queueing

automation-engineerRun a fleet of concurrent browser sessions with documented concurrency limits and programmatic session management
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
developerGet webhook notifications when tasks and sessions finish instead of polling for status
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
nice-to-have

Stealth captcha — stories about stealth captcha in this arenaStealth captcha· 3 items

Stories about stealth captcha in this arena

automation-engineerRely on a documented captcha stance — automatic solving, human fallback, or explicit non-support — instead of silent task failures
Important, not disqualifying — weighs 2× in arena scoring · 4 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
automation-engineerEnable stealth fingerprinting and residential or geo-targeted proxies so legitimate automations aren't blocked as bots
Important, not disqualifying — weighs 2× in arena scoring · 3 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
should-have
automation-engineerPoint to the vendor's published acceptable-use and anti-abuse posture governing what its stealth and automation features may be used for
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
nice-to-have

Structured extraction — stories about structured extraction in this arenaStructured extraction· 2 items

Stories about structured extraction in this arena

developerExtract typed, schema-validated data (Zod/Pydantic-style) from pages the agent visits, not just raw text
Core requirement — weighs 3× in arena scoring · 4 of 7 products fully deliver this today
Steel Skyvern Hyperbrowser Stagehand Notte
must-have
developerMy agent can download files from and upload files to the sites it operates, with the artifacts retrievable afterwards
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
Steel Skyvern Hyperbrowser Stagehand Notte
nice-to-have

Full evidence behind every verdict lives on the arena page and each product page — chips above deep-link straight to the judged story.

🌐Browser Automation for Agents arenaBuyer checklist

🛠️Action primitives — stories about action primitives in this arenaAction primitives· 4 items

🤖Agenticness — how well agents can access and operate the productAgenticness· 17 items

🔑Auth session persistence — stories about auth session persistence in this arenaAuth session persistence· 3 items

⚙️Automation depth — how much of the product can run unattendedAutomation depth· 4 items

🚀Deployment modes — stories about deployment modes in this arenaDeployment modes· 1 item

✨Framework model support — stories about framework model support in this arenaFramework model support· 2 items

🤖Nl task execution — stories about nl task execution in this arenaNl task execution· 3 items

🔓Openness — open source, data portability, and self-hosting storiesOpenness· 4 items

💲Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits· 1 item

🔒Privacy posture — data-handling and privacy storiesPrivacy posture· 4 items

💻Replay debugging — stories about replay debugging in this arenaReplay debugging· 2 items

⚡Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism· 2 items

🛡️Stealth captcha — stories about stealth captcha in this arenaStealth captcha· 3 items

🔎Structured extraction — stories about structured extraction in this arenaStructured extraction· 2 items