Skip to main content
Home
GrN.dk

Main navigation

  • Articles
  • Cases
  • Services
  • Your Digital Project Manager
  • About Greg Nowak
  • Image Gallery
  • Contact
User account menu
  • Log in

Join my community / free newsletter — sign up here

Breadcrumb

  1. Home

OpenAI Computer Use: Browser Agents Need Credentials, Not Demos

Illustrated infographic summarizing: OpenAI Computer Use: Browser Agents Need Credentials, Not Demos

By Greg Nowak. Last updated 2026-08-18.

A browser agent that completes a supplier form or updates an admin portal makes a good demonstration. The operational test begins when it must sign in, handle sensitive data, recover from a changed page, and stop before an expensive mistake.

That changes the nature of the project. OpenAI computer use is not simply a clever layer on top of browser automation. Once it reaches authenticated systems, it becomes an identity, security, and workflow-control project. Business owners should judge it by the quality of those controls—not by how confidently the cursor moves.

Computer use is ready for narrow, controlled workflows

OpenAI’s current guidance describes three implementation patterns: the built-in Responses API computer tool, custom tools connected to an existing automation harness, and code-execution environments with browser or desktop controls. Current guidance centres this work on GPT-5.4; an older pilot built around computer-use-preview should be treated as a migration project.

The right pattern depends on the work. A visual loop can handle shifting labels and irregular layouts. A custom harness suits teams that already use Playwright, Selenium, or an internal automation platform. Code execution helps when the workflow needs DOM inspection, conditional logic, or browser-library calls. If every field and rule is stable, conventional automation may still be cheaper and easier to maintain.

Give the workload its own identity

The quickest route to a risky pilot is letting the agent borrow an employee’s administrator account. Instead, create a dedicated account or role for the workflow wherever the target application supports it. Grant access only to the necessary records and actions, and keep production credentials separate from development.

For OpenAI API authentication, workload identity federation can remove the need to store long-lived API keys in supported environments. A trusted workload presents an externally issued identity token, which OpenAI exchanges for a short-lived access token mapped to a project service account. This limits the value and lifetime of a stolen credential.

Run the browser in an isolated environment, pass an empty environment-variable set, and disable extensions and local filesystem access where possible. Maintain an allowlist of permitted domains and actions. Page content must remain untrusted: instructions displayed inside a portal do not become valid merely because the agent can read them.

Put approval at the point of consequence

Human approval should not interrupt every harmless click. Let the agent navigate, inspect, and prepare the work, then pause immediately before an action changes the risk. OpenAI specifically recommends human involvement for purchases, authenticated workflows, destructive actions, and anything difficult to reverse.

  • Confirm before submitting a purchase, payment, deletion, or permission change.
  • Confirm before sending, posting, or uploading information to another party.
  • Confirm before typing sensitive data unless narrowly defined consent already covers that exact use.
  • Stop and escalate when a page contains suspicious instructions or possible prompt injection.

The confirmation should name the action, destination, and likely consequence. “Continue?” is not informed approval.

Choose the least complex workable harness

Workflow characteristic Starting approach First control to add
Stable page and predictable rules Conventional browser automation Tests, retries, and change detection
Visual variation with low-risk actions Built-in computer-use loop Isolated browser and domain allowlist
Existing Playwright or Selenium estate Custom harness with model tools Narrow schemas and audit logging
DOM-heavy logic or conditional loops Code-execution harness Sandbox, timeouts, and resource limits
Money, deletion, permissions, or external communication Hybrid workflow Human approval before execution
A useful agent handles ambiguity while deterministic code and people retain control of consequential actions.

Bound side effects with explicit functions

Visual control is useful for reading an irregular screen. It is a poor reason to make every consequential action an unrestricted click. Route actions such as creating an order, changing access, sending a message, or submitting a payment through explicit functions with narrow JSON schemas.

OpenAI recommends enabling strict mode so function calls adhere reliably to their schemas. Use tool_choice to limit the available tools. When sequence matters, set parallel_tool_calls to false, ensuring that the model calls no more than one function in a turn.

This creates a practical division of labour: the model interprets the page, while ordinary application code validates inputs, checks policy, records the event, and performs the approved side effect.

Run it as a recoverable job

Browser work is naturally failure-prone. Sessions expire, pages time out, layouts change, and approvals may take hours. Production workflows therefore need durable states such as queued, running, awaiting approval, completed, failed, and cancelled.

For long OpenAI requests, use background=true and poll the response until it reaches a terminal state. Webhooks can notify your system when a response completes; verify every webhook signature against the raw request body before accepting the event.

Store the workflow version, account used, approved domains, tool calls, confirmations, outcome, and safe error details. Define retry rules per action. Retrying a page read may be harmless; retrying “submit order” may create a duplicate. When the outcome is uncertain, escalate instead of guessing.

What should the first pilot prove?

  1. Value: one repetitive workflow has enough volume or delay to justify intervention.
  2. Containment: the agent can reach only named systems, accounts, and actions.
  3. Control: sensitive or irreversible steps stop at the correct approval boundary.
  4. Recovery: operators can inspect, resume, or terminate a failed run safely.
  5. Maintainability: the team can detect page drift and update the workflow without reconstructing a demo.

Track completed cases, human interventions, exceptions, run time, and cost per completed case. Clean escalation can be more valuable than a high apparent completion rate that conceals duplicate submissions or silent errors.

The sensible procurement question is not, “Can an agent use this website?” It is, “Can we operate this workflow safely when credentials expire, screens change, and people need to intervene?” That is the difference between a promising demonstration and a dependable business capability.

Planning a browser-agent pilot?

Greg can help map the workflow, select the right harness, define credential and approval boundaries, and coordinate the rollout. Talk through the project with Greg.

Related on GrN.dk

  • AI agents need a browser policy before they start clicking around
  • AI automations need a spend dashboard before the first runaway bill
  • A Voice Agent Is Only Ready When the Human Handoff Works

Need help with this kind of work?

Plan a controlled browser-agent pilot Get in touch with Greg.

Sources

  • Computer use | OpenAI API
  • Function calling | OpenAI API
  • Workload identity federation | OpenAI API
  • Background mode | OpenAI API
  • Webhooks | OpenAI API
Last modified
2026-08-18

Tags

  • AI automation
  • OpenAI API
  • browser automation
  • workflow governance
  • operations consulting

Review Greg on Google

Greg Nowak Google Reviews

 

Written recommendations from Trafik og Veje, Aarhus Municipality (2011) and AgroTech (2010) — read them on LinkedIn.

Illustrated infographic summarizing: From Supplier Invoice to Bookkeeping: AI with a Control Checkpoint
From Supplier Invoice to Bookkeeping: AI with a Control Checkpoint
2026-08-18

AI can reduce the work involved in processing supplier invoices, but reliable bookkeeping requires validation, duplicate checks, approval and a clear audit trail.

Illustrated infographic summarizing: Nginx 1.30 Changed the Upstream Defaults—Test Before You Upgrade
Nginx 1.30 Changed the Upstream Defaults—Test Before You Upgrade
2026-08-17

Nginx 1.30 defaults upstream proxying to HTTP/1.1 with keepalive enabled. Here is what to inspect, model and test before upgrading.

Illustrated infographic summarizing: OpenAI’s Assistants API Shuts Down in Ten Days. Is Your App Ready?
OpenAI’s Assistants API Shuts Down in Ten Days. Is Your App Ready?
2026-08-16

OpenAI’s Assistants API shuts down on August 26, 2026. Learn what to inventory, how to preserve state and how to cut over without breaking the product.

Illustrated infographic summarizing: WordPress 7.1 Forces the Editor Into an iframe—Test Your Custom Blocks
WordPress 7.1 Forces the Editor Into an iframe—Test Your Custom Blocks
2026-08-15

WordPress 7.1 removes the non-iframe editor fallback. Learn how to audit custom blocks, test real workflows and fix compatibility issues before launch.

Illustrated infographic summarizing: GitHub will stop sending jobs to stale self-hosted runners
GitHub will stop sending jobs to stale self-hosted runners
2026-08-14

GitHub starts enforcing runner versions on August 24, 2026. Audit and upgrade self-hosted runners before builds and deployments start stalling.

Illustrated infographic summarizing: Your AI Agent Has Shell Access. What Can It Reach?
Your AI Agent Has Shell Access. What Can It Reach?
2026-08-13

A practical guide to mapping what a shell-enabled AI agent can reach, then containing its access to files, credentials, networks, tools, and high-impact actions.

Illustrated infographic summarizing: Cloudflare Changed DoH JSON. What Else Is Parsing DNS as Text?
Cloudflare Changed DoH JSON. What Else Is Parsing DNS as Text?
2026-08-12

Cloudflare’s DoH JSON change exposes brittle DNS parsing. Find affected scripts, test both formats, and choose a safer integration contract.

Illustrated infographic summarizing: Your Website Can Answer Questions Now. Should It?
Your Website Can Answer Questions Now. Should It?
2026-08-11

NLWeb makes conversational website search practical to deploy. The real question is whether your content, users and team are ready to support it.

Illustrated infographic summarizing: AI Search Finally Has Reports. Now Connect Visibility to Revenue
AI Search Finally Has Reports. Now Connect Visibility to Revenue
2026-08-11

Google and Bing now expose first-party AI search data. The real task is connecting citations and impressions to analytics, CRM outcomes, and revenue.

Illustrated infographic summarizing: The Bot Passed Your CAPTCHA. What Did It Do Next?
The Bot Passed Your CAPTCHA. What Did It Do Next?
2026-08-11

Passing a challenge is only one signal. Session analysis, server-side validation and endpoint-specific controls help reduce bot abuse without blocking customers.

More articles

Built by AI — available for your business. The daily articles on this site are researched, written and illustrated by an autonomous AI pipeline. At nowa.dk I install the same kind of AI automation in businesses at fixed prices — site in Danish, English version here, and web/marketing agencies have a dedicated page.

RSS feed

Footer

  • All articles
  • Contact

GrN.dk — AI automation, web platforms, web optimization, data handling and logistics.

© 2026 GrN.dk · LinkedIn · Contact · AI automation in Danish: nowa.dk

Behind GrN.dk: Individual Entrepreneur Codecrafter · Tax ID 305669096 · Bakhtrioni St. 22, 0194 Tbilisi, Georgia · official business register