Gives one Browser Operator a visible goal, watches the live page, handles sign-in or MFA through takeover, verifies the result from current DOM evidence, and returns a screenshot-backed Run Receipt.
Designed for
Product, support, and operations teams that need evidence from a website without an API or browser extension
Operating goal
Complete one bounded website investigation and return visible proof instead of an unverified summary.
2 steps from trigger to verified handoff, with success and failure paths.
1 MCP layer and 1 connected tools with explicit auth and risk levels.
3 guardrails, 3 evals, and 1 harnesses before production use.
Completes one bounded website goal through policy-validated accessible actions.
Fast structured planning model
Turns the final page evidence into a concise owner-ready result.
Balanced reasoning model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A workflow skill that captures the operating contract, tool boundaries, and escalation rules for Browser QA Investigation Team.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes task resources, prompt templates, connector tools, and audit records behind a permission-aware boundary.
Pursue the configured website goal through the Browser Operator and return final evidence.
Summarize only the current visible evidence and identify any unresolved gap.
Open it in Codelit, refine it with the agent chat, then generate the architecture or product plan from the same workflow spec.
Open in Agent WorkflowA code-first support agent built around specialist ownership, function tools, MCP resources, guardrails, traces, and eval loops so customer answers can move fast without leaking account state.
An n8n-centered workflow that turns a business automation request into a tested app workflow with conditional logic, human-in-the-loop checks, cost controls, and failed-run repair notes.
A controlled workflow for small teams that want an internal agent to answer operational questions, create tickets, inspect connected apps, and prepare approved actions across the company stack.