Hark Handoff
An agent that clicks, types, and navigates real websites in its own virtual computer, no API required, to actually complete tasks like booking or ordering for you.
The verdict on Hark Handoff: Automating multi-step tasks on websites that have no developer API to hook into Hark Handoff is betting that the ceiling on browser agents has been the wrong training target: predicting UI actions instead of text tokens is a real architectural difference, not just marketing, and it shows up in the benchmark numbers. Pricing: Technical preview (waitlist): usage-based, roughly $0.18/1M input tokens and $2.37/1M output tokens.
Best For
Automating multi-step tasks on websites that have no developer API to hook into
Standout Feature
Predicts the next UI click or keystroke rather than the next word, which is why it leads the OM2W web-navigation benchmark
TL;DR
A genuinely different architecture for browser agents, still in technical preview with real open questions about enterprise security.
Alternatives
Fit Score: use-case reference
How this is scoredHark Handoff scored 1 to 5 on five dimensions for the named use cases below. Part of our catalog-wide use-case reference, not a product-quality review rating.
Automating multi-step tasks on websites that have no developer API to hook into
3.6/5- Capability
- 5/5
- Reliability
- 2/5
- Value
- 4/5
- Ease
- 4/5
- Compatibility
- 3/5
Predicting the next UI action rather than the next word is a genuinely different architecture that leads the OM2W web-navigation benchmark, with token pricing well below comparable frontier computer-use agents (standout, pros). Reliability is low because it's still technical preview only with unresolved enterprise security and data-access questions (cons).
Production workflows needing a settled, enterprise-security-reviewed agent today
1.8/5- Capability
- 2/5
- Reliability
- 1/5
- Value
- 2/5
- Ease
- 2/5
- Compatibility
- 2/5
Its own ourTake says this is not yet something to build a production workflow around, and enterprise security and data-access questions aren't fully answered (cons), so it's a mismatch for anyone needing a settled, reviewed agent right now rather than a waitlisted preview.
Editorial judgment grounded in this tool's own published pricing, features, and our existing pros and cons, not a certification or a measured benchmark. Product quality is assessed separately under our review methodology.
Overview
Not yet reviewedProduct quality is assessed from original evidence. How reviews work.
Hark Handoff is a computer-use agent that navigates the open web the way a person would, clicking, typing, and reading screens inside a dedicated virtual computer spun up for each task, rather than calling developer APIs behind the scenes. That lets it act on sites with no API at all: booking a flight, ordering food, messaging a candidate on LinkedIn, or filling out a form on a site it has never seen. Rather than predicting the next word in a sentence, its underlying model predicts the next UI action, a click or keystroke, which is the architectural bet behind its benchmark-leading score on the OM2W web-navigation benchmark.
It connects to a user's existing accounts so it can act with their saved addresses and payment methods already in place. Founded by Brett Adcock, previously behind Figure AI and Archer Aviation, and backed by a $700M Series A at a $6B valuation, Hark is currently in technical preview with a waitlist rather than a public launch, and token costs are already priced well below comparable frontier computer-use agents. Hark Handoff fits anyone who wants an agent to actually complete a multi-step task on a website that has no automation-friendly API, not just answer a question about it.
The source of the legacy catalog rating and review count has not been substantiated. Neither is presented here as a verified review rating or included in review structured data.
Workflow Fit Scores are separate, use-case-specific editorial judgments, not user-review averages. Read the Fit Score methodology.
- • Genuinely novel architecture, not just another API wrapper
- • Token costs well below comparable frontier computer-use agents
- • Strong founding team and funding behind continued development
- • Technical preview only, no firm public release date
- • Enterprise security and data-access questions still unresolved
- • Model only post-trained so far, quality could shift meaningfully with pre-training
Key Features
- Dedicated virtual computer per task (browser, filesystem, terminal)
- Navigates sites with no API using UI-action prediction
- Connects to existing accounts, addresses, and payment methods
- Leading score on the OM2W web-navigation benchmark
Trust & Data
Verified 2026-09
- Training on your data
- Not publishedThe legal documents found raise a product-identity concern: the privacy policy refers to 'our website (Hark.ai)' and the Terms of Service describe Hark as an AI safety and research company, referencing unrelated features (image-to-video, avatars) that don't match the waitlisted computer-use agent product cataloged here. It's unclear whether these documents govern this specific product or a different/broader offering sharing the domain. The one document that would directly address model training, a separate 'Non-User Privacy Notice,' returned a 404 at every path tested.
- Compliance
- Not published
- Retention
- Retains Personal Data for as long as reasonably necessary to provide the Services and comply with legal obligations; no specific periods stated.
- Export
- Not published
Sources: hark.com/privacy policy, hark.com/terms
As published by the vendor. Verify independently before purchase decisions.
Our Take
The token pricing undercutting comparable agents by an order of magnitude matters once you're running this at any real volume. The honest caveats are that it's still a technical preview with no firm public release date, and letting an agent operate a virtual computer with access to your saved accounts raises security and privacy questions that aren't fully answered yet. Worth getting on the waitlist for if browser automation without an API is a real bottleneck for you; not yet something to build a production workflow around.