Specialist automation

Which AI agent platforms can drive a browser or a desktop?

This is the most specialized axis in the taxonomy and the numbers say so. Of 955 vendors, 108 document full browser, desktop or remote computer control for workflows that cannot be done through stable APIs. 88 document partial coverage and 759 document none.

Every vendor in the index is assessed against the same 14 point taxonomy from public documentation, and no vendor pays for placement. Counts on this page were measured across all 955 public vendors on October 7, 2026.

How the 955 vendors split

Full coverage108 vendors, 11.3%
Partial coverage88 vendors, 9.2%
No public evidence759 vendors, 79.5%

No public evidence means the reviewed sources did not document the capability. On this index that is a statement about the evidence, not proof that the capability is absent. See methodology.

What counts as full coverage

Full coverage means documented control of a real interface: a hosted or local browser, a desktop session, or remote computer control the agent drives itself. Partial usually means web scraping, a headless fetch or a third party browser engine wired in as an integration rather than owned by the platform. A terminal, sandbox or code execution environment is autonomous execution but not this axis, an ingestion crawler that builds the knowledge corpus belongs on knowledge grounding, and an agent operating the vendor's own admin screens does not count. Where a vendor documents actions inside a platform that publishes no API but does not state the mechanism, the cell is Partial.

How to read these numbers

Read the 759 as scope rather than as failure. Most agents in the index act through APIs by design, which is faster, more reliable and easier to audit, so an absent score here is usually the correct engineering choice. The browser lane itself documents full coverage for all 42 of its members, as it should. The number that carries information is the spread outside that lane: coding at 26 percent, agent builders at 19, multi agent platforms at 17 and agent infrastructure at 15, then a long tail in single digits, with SRE at zero. Screen driving remains a specialist tool bought for systems that never got an API, not a capability spreading across the market.

Leading platform for browser & computer use in each use case

Picked mechanically: the highest total coverage vendor in each lane that documents full evidence on this axis, one vendor per row. Scores are out of 14.

  1. 1. Appian, for enterprise operations agents

    14 / 14

    Full enterprise operations agents ranking · Compare the whole lane on all 14 axes

  2. 2. FLOWX.AI, for multi-agent platforms

    14 / 14

    Full multi-agent platforms ranking · Compare the whole lane on all 14 axes

  3. 3. Gumloop, for GTM and revenue agents

    14 / 14

    Full GTM and revenue agents ranking · Compare the whole lane on all 14 axes

  4. 4. Mastra, for agent infrastructure platforms

    14 / 14

    Full agent infrastructure platforms ranking · Compare the whole lane on all 14 axes

  5. 5. ServiceNow, for customer support agents

    14 / 14

    Full customer support agents ranking · Compare the whole lane on all 14 axes

  6. 6. UiPath, for agent builders

    14 / 14

    Full agent builders ranking · Compare the whole lane on all 14 axes

  7. 7. GitHub Copilot, for coding agents

    13.5 / 14

    Full coding agents ranking · Compare the whole lane on all 14 axes

  8. 8. HappyRobot, for voice agents

    13 / 14

    Full voice agents ranking · Compare the whole lane on all 14 axes

  9. 9. Adopt AI, for browser and computer-use agents

    12.5 / 14

    Full browser and computer-use agents ranking · Compare the whole lane on all 14 axes

  10. 10. Redbird, for data analyst agents

    11.5 / 14

    Full data analyst agents ranking · Compare the whole lane on all 14 axes

  11. 11. CoOrdio, for healthcare agents

    8.5 / 14

    Full healthcare agents ranking · Compare the whole lane on all 14 axes

  12. 12. Assail, for security and SOC agents

    8 / 14

    Full security and SOC agents ranking · Compare the whole lane on all 14 axes

Documented coverage by use case

Share of each lane documenting full coverage on this axis. Vendors that sit in two lanes count in both, the same rule the rankings and matrices use.

Use case Full coverage Share
browser and computer-use agents 42 of 42 100%
coding agents 18 of 70 26%
agent builders 23 of 118 19%
multi-agent platforms 9 of 52 17%
agent infrastructure platforms 27 of 186 15%
enterprise operations agents 28 of 301 9%
healthcare agents 5 of 69 7%
data analyst agents 4 of 59 7%
GTM and revenue agents 6 of 138 4%
voice agents 3 of 83 4%
customer support agents 5 of 115 4%
security and SOC agents 1 of 85 1%
SRE and DevOps agents 0 of 37 0%

Recent verified changes from the vendors named above

Capability coverage is not a static picture. These are the most recent sourced change log entries for the platforms listed above, newest first, one per vendor. Scores on this page update as entries like these are verified.

  1. Appian browser/computer use

    High impact

    Agentic RPA in Appian RPA 9.27 takes a goal written in plain language and works toward it on screen, capturing what it sees, then navigating, clicking, typing and reading until the goal is met. It works with any application visible on screen, from SAP and mainframe terminals to legacy desktop software and web browsers, and adapts when a dialog moves, a button label changes or a pop up appears. New Switch and Try-Catch actions can wrap it so a robotic task recovers from errors without stopping the run.

    October 23, 2026 · Verified · All Appian changes

  2. Gumloop browser/computer use

    High impact

    Release 12.0.0 gives Gumloop agents their own browser. An agent can now open a real browser and click, type, sign in, fill forms and download files on any site, with or without a connector.

    October 6, 2026 · Partially Verified · All Gumloop changes

  3. GitHub Copilot browser/computer use

    High impact

    GitHub Copilot can now operate desktop apps on macOS and Windows, in public preview in Copilot CLI and the Copilot app. It reads what is on screen, clicks, types, scrolls and drags through workflows, including software with no API or MCP integration.

    October 1, 2026 · Verified · All GitHub Copilot changes

  4. FLOWX.AI agent capability

    Medium impact

    FlowX.AI 6.0 upgrades the Developer Agentic Harness, the Designer's AI agent that plans app changes and builds them on its own branch. A plan can now be split into stories that the agent builds one slice at a time, each with steps to test it before the next one starts. Comment mode lets a builder select a component in the running app and say what should change, and a single agent rail replaces the Command Center and the AI buttons in each editor.

    October 30, 2026 · Partially Verified · All FLOWX.AI changes

  5. UiPath agent capability

    High impact

    Autopilot Chat returns to Orchestrator and now works directly on the customer's tenant instead of only answering questions. It can manage processes, jobs, queues, assets, triggers, machines and folders, look into failed jobs and access issues, and help plan, build and deploy automations. Admins pick an approval mode, from asking before every operation to running with no approval prompts, and can connect MCP servers and switch tools and skills on or off.

    October 28, 2026 · Partially Verified · All UiPath changes

Full change log · updated weekly across the whole index

Questions buyers ask

Should I expect this from a general platform?

No. If your target systems have APIs, an agent that uses them is the better architecture. This axis matters when a critical system has no API and the only path is the interface a person would use.

How is this different from the browser agent category?

This page measures the capability across every vendor in the index. The browser and computer use lane is the set of vendors whose whole product is that capability, ranked and compared on its own pages.

Why do some infrastructure vendors score full?

Because they sell hosted browsers and control interfaces for other people's agents. They are suppliers to the capability rather than agents that use it, and the grid records the documented capability either way.

The other 13 axes

No single axis decides a shortlist. Buyers who care about this one usually check testing, debugging & optimization and integrations & tool calling next, or open the full taxonomy to see how the 14 axes fit together.

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.