Agent Systems · core
Browser & Computer-use Agents
DOM and accessibility-tree control, screenshots, visual grounding, action planning, waits, recovery, and confirmation.
Mental model
Computer use is closed-loop control: observe current state, choose one bounded action, execute, verify the resulting state, and recover from drift.
How to study Browser & Computer-use Agents
Begin by restating the mental model in your own words, then connect it to a concrete system you have built or operated. Name the mechanism, the constraint it addresses, and the trade-off it introduces. Use WebArena: A Realistic Web Environment for Building Autonomous Agents, Mind2Web: Towards a Generalist Agent for the Web, OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments to check details, but close the source before writing your explanation. Retrieval is the learning step; rereading is only preparation.
Next, compare Browser & Computer-use Agents with Agent Communication & Interfaces, Durable Agent Execution. Ask what changes in correctness, latency, resource use, operability, and failure recovery. Complete Design exercise: Browser & Computer-use Agents and preserve the command, input, output, and one failed attempt as evidence. Finish by explaining the idea without jargon to someone who has not studied the track.
Proof of understanding
- Explain the mechanism from first principles and identify the state it reads or changes.
- Give one situation where the concept is the right choice and one where it is not.
- Predict a realistic failure mode before running the drill, then compare the prediction with evidence.
- Connect the result to a roadmap or build artifact instead of treating the concept as isolated trivia.
Learn from primary sources
- WebArena: A Realistic Web Environment for Building Autonomous Agents (doc)
- Mind2Web: Towards a Generalist Agent for the Web (doc)
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (paper)
- Developing a Computer Use Model (Anthropic) (article)
- Playwright Documentation (doc)
Practice and explain it back
Design exercise: Browser & Computer-use Agents
DOM and accessibility-tree control, screenshots, visual grounding, action planning, waits, recovery, and confirmation. Implement designOutline() returning non-empty values for: observation, boundedAction, stateVerification. Each value must name a concrete mechanism or decision.
Expected evidence: A design outline with observation, boundedAction, stateVerification plus an explicit failure mode or trade-off.
Open the interactive drill →Review prompts
- Screenshot-plus-coordinates versus the accessibility tree: what does each get right and wrong?
Build evidence
Synthesize: Agent Systems
Engineer useful agents with bounded loops, tools, memory, protocols, durability, permissions, and long-running control. Produce one working system, benchmark, or evidence-backed design that integrates the path.
- Implements or precisely models the core mechanisms from all three milestones
- Includes at least one injected failure or adversarial case and demonstrates recovery
- Reports quality, latency, resource, reliability, or usability measurements relevant to the domain
- Ships a concise architecture note explaining decisions, trade-offs, and remaining risks