18.1 Overview

Browser Control is AIUNIFY PROS SUITE's autonomous web-research and browser-navigation workspace.

The current interface identifies the feature as:

Browser Control

with:

“Autonomous browser agent interface”.

Browser Control combines several capabilities inside one workspace:

  1. A natural-language Research Objective
  2. Manual web navigation
  3. An autonomous AI research Agent
  4. Web searching
  5. Page navigation
  6. Extracted webpage text
  7. Parsed webpage links
  8. A visible browser viewport
  9. Search/navigation activity logs
  10. A maximum five-step autonomous research loop
  11. AI synthesis of gathered information
  12. Copy Answer
  13. Markdown report Download
  14. Copy Console Output
  15. Clear Console
  16. Optional reference-image input
  17. Shared PROS SUITE AI Model selection

Browser Control is therefore substantially different from AI Chat and the Standard AI Generator.

Instead of simply answering a Prompt from Model knowledge, its source-defined research workflow can:

Search → Navigate → Read → Analyze → Continue Research → Synthesize Findings

within a bounded autonomous loop.

18.2 Where Browser Control Is Located

Navigate to:

Sidebar → Core Tools → Browser Control

The current Sidebar route is:

/browser-control

and Browser Control carries both:

New

and:

Pro

interface metadata.

As explained earlier in this manual, the Pro badge itself should not be treated as the sole determination of entitlement. Actual availability depends on your current PROS SUITE account access.

18.3 Browser Control Is Also Classified as an AI Agent

The current feature catalogue classifies:

Browser Control

under:

AI Agents

with a source-defined fallback Token cost of:

25 Tokens.

However, the Browser Control workspace itself does not display a simple:

25 tokens per use

badge.

Its autonomous mission can also make multiple AI requests during one research sequence.

For that reason, this manual does not claim that an entire Browser Control mission will always cost exactly 25 Tokens.

More on Token behavior appears later in this chapter.

18.4 What Browser Control Is Designed to Do

Browser Control is best suited for tasks such as:

  1. Researching a company
  2. Comparing products or services
  3. Finding current pricing
  4. Reviewing public documentation
  5. Researching software features
  6. Reviewing official webpages
  7. Comparing information from multiple sources
  8. Reading a specific URL
  9. Identifying relevant links on a webpage
  10. Synthesizing information discovered during browsing
  11. Producing a reusable research report

18.5 Browser Control vs. AI Chat

AI Chat

Primarily:

Ask → AI Responds → Follow Up

Its current built-in utility list is limited to specific Chat tools.

Browser Control

Primarily:

Define Research Objective

Search Web

Navigate to Pages

Extract Page Information

Continue Research

Generate Final Synthesis

Use Browser Control when the task specifically benefits from webpage research rather than ordinary conversation.

18.6 Browser Control vs. Research Agent

PROS SUITE also contains a separate:

Research Agent

under AI Agents.

Browser Control should not be treated as simply another Name for Research Agent.

Browser Control has its own visible:

  1. Browser viewport
  2. Address bar
  3. Manual navigation controls
  4. Text Reader
  5. Parsed Links
  6. Telemetry Monitor
  7. Search/navigation loop

Research Agent is a separate PROS SUITE Tool and will be documented in its applicable chapter.

18.7 Browser Control Workspace Layout

The current Browser Control interface is divided into two primary areas.

Left Side

Research controls and activity:

  1. Browser Control header
  2. Research Objective
  3. Image attachment
  4. Example Prompts
  5. Launch Autonomous Agent
  6. Agent progress
  7. Telemetry Monitor
  8. Synthesis Results

Right Side

Browser environment:

  1. Back
  2. Forward
  3. Refresh
  4. URL/address field
  5. Live viewport
  6. Text Reader
  7. Parsed Links
  8. Manual/Agent status

18.8 Browser Control Header

The upper-left header displays:

Browser Control

and:

Autonomous browser agent interface.

Below it is the main research-control area.

18.9 Research Objective

The primary Prompt area is labeled:

Research Objective.

This is where you explain what you want Browser Control to investigate.

18.10 Research Objective Placeholder

The current Prompt field displays:

“Enter natural language research task... (e.g. 'Compare pricing of Apple Vision Pro on Best Buy vs Amazon')”

You do not need to write browser commands or code.

Describe the research outcome in normal language.

18.11 Example Research Objective

A useful request might be:

Research the pricing, core features, target customer, and enterprise positioning of three leading AI CRM platforms. Use current public sources and give me a comparison with key advantages and disadvantages.

This gives the Agent:

  1. Subject
  2. Research dimensions
  3. Desired comparison
  4. Desired final output

18.12 Weak Research Objective

A request such as:

Research CRM.

is extremely broad.

The Agent may need to decide:

  1. Which CRM products
  2. Which geography
  3. Which features
  4. Which time period
  5. Which sources
  6. What the final answer should contain

A more complete objective usually produces a more focused research process.

18.13 Recommended Objective Structure

For deeper research, include:

Topic

What are you researching?

Scope

Which products, companies, documents, or markets?

Questions

What specifically should be discovered?

Source Preference

For example:

  1. Official company websites
  2. Documentation
  3. Government sources

Comparison Criteria

For example:

  1. Price
  2. Features
  3. Market position
  4. Limitations

Deliverable

What should the final answer look like?

18.14 Example — Company Research

Research Company X using its public website. Identify its products, target market, pricing information, leadership positioning, main differentiators, and any publicly stated enterprise capabilities. Summarize the findings for a B2B competitive review.

18.15 Example — Product Comparison

Compare the current public pricing and major features of Product A, Product B, and Product C. Prioritize each company's official pricing and product pages, then give me a table-style comparison and recommendation by business size.

18.16 Example — Documentation Research

Review the official documentation for Platform X and identify how its authentication, API access, rate limits, and webhook functionality work. Summarize the most important implementation considerations.

18.17 Enter Sends the Research Objective

Inside the Research Objective field:

Enter

without Shift launches the Autonomous Agent.

18.18 Shift + Enter for a New Line

Because the launch handler responds to Enter only when Shift is not held:

Shift + Enter

can be used to add another line without starting the mission.

This is useful for structured research instructions.

18.19 Clear All

When either a Prompt or reference image exists, Browser Control displays:

Clear all.

Selecting it removes:

  1. Research Objective text
  2. Attached reference image

It does not run the research Agent.

18.20 Reference Image Attachment

Browser Control contains a Paperclip control titled:

Upload reference image.

The current file picker accepts:

image/*

meaning the verified attachment type is an image.

18.21 Maximum Image Size

The current Browser Control upload logic allows images up to:

5 MB.

18.22 Image Too Large

If the selected image exceeds 5 MB, Browser Control adds an Error log:

“Image upload failed: File size exceeds the 5MB limit.”

Select a smaller image and retry.

18.23 Successful Image Upload

When a valid image is loaded, Browser Control records:

“Image uploaded successfully: [filename] ([size] KB)”

18.24 IMAGE READY

After a reference image has been loaded, the Prompt area displays:

IMAGE READY.

A thumbnail is also displayed beneath the Prompt.

18.25 Removing the Reference Image

Hover over the image Preview and select the X control.

Browser Control removes the asset and adds:

“Reference image removed from workspace.”

18.26 Research Still Requires a Written Objective

Although Browser Control supports a reference image, the Launch Autonomous Agent button requires non-empty Research Objective text.

Therefore:

An image alone is not sufficient to launch the current Browser Control Agent.

Include a written task explaining what the Agent should research or do with the image.

18.27 How the Image Is Used

The reference image is supplied to the AI during the first Agent reasoning request.

It is also included in the first history context when the Agent begins performing Search or Navigate operations.

This lets the initial research objective include visual context.

18.28 Example — Image-Assisted Research

You could attach a product screenshot and enter:

Identify the product shown in this screenshot, then research the manufacturer's current public specifications, positioning, and pricing. Prioritize the official product website.

18.29 Example Prompts

Browser Control displays:

Example Prompts

beneath the Research Objective.

The current source defines four examples.

18.30 Apple Vision Pro Specs

Example:

Apple Vision Pro Specs

The underlying Prompt asks Browser Control to find:

  1. Key specifications
  2. Weight
  3. Current starting price

from the official Apple website.

18.31 Next.js 15 Features

Example:

Next.js 15 Features

The Prompt asks the Agent to search official Next.js blog/documentation information and summarize major features and changes.

18.32 Compare Retail Prices

Example:

Compare Retail Prices

The Prompt asks the Agent to compare iPhone pricing across Best Buy and Amazon.

18.33 GitHub Trending Today

Example:

GitHub Trending Today

The Prompt asks Browser Control to navigate to GitHub Trending and summarize the top three trending repositories.

18.34 Selecting an Example Prompt

Selecting an Example Prompt places its research instruction into the:

Research Objective

field.

It does not automatically start the Autonomous Agent.

Review or customize the Prompt first, then launch it.

18.35 Important Preset URL Limitation

Each source-defined preset also contains a startUrl, but the current Example Prompt button only places the preset's Prompt into the Research Objective.

The click handler does not navigate to that preset's stored start URL.

Therefore:

Selecting Apple Vision Pro Specs, for example, does not itself navigate the visible Browser to Apple.com.

The Agent can still search/navigate there as part of its research.

18.36 Launch Autonomous Agent

When your Research Objective is ready, select:

Launch Autonomous Agent.

This begins the source-defined autonomous research loop.

18.37 When Launch Is Disabled

The Launch button is disabled when:

  1. The Research Objective is empty
  2. The Agent is already running
  3. The underlying AI system is currently streaming


18.38 Running Sandbox Agent

During a mission, the button changes to:

Running Sandbox Agent ([iteration]/5).

This shows the current Agent iteration.

18.39 Maximum Autonomous Loop

The Browser Control source currently sets:

MAX_AGENT_ITERATIONS = 5.

The Agent therefore does not run an unlimited research loop.

18.40 What an Iteration Means

An iteration is one AI planning/research turn.

During an iteration, the Agent can:

  1. Analyze what it knows
  2. Decide to search
  3. Decide to navigate
  4. Receive research results
  5. Decide whether more investigation is needed
  6. Or produce its final answer

A single iteration can potentially contain one or more returned research tool calls.

18.41 Loop Progress Indicator

While the Agent is active, Browser Control displays:

Loop Active

and:

Iteration [number] of 5.

A progress bar also advances according to the current iteration.

18.42 What the Agent Is Instructed to Do

The current research-agent instructions tell the AI that it has two browser actions:

  1. browser_search
  2. browser_navigate

and instruct it to:

  1. Search when it does not already have a specific URL
  2. Navigate to relevant search results
  3. Read detailed page information
  4. Search/navigate multiple times when appropriate
  5. Produce a complete answer when enough information has been gathered


18.43 Browser Search

When the Agent decides it needs a web search, it performs a:

browser_search

operation.

The interface records:

Querying web: “[query]”.

18.44 What Search Results Contain

The current search processor creates result entries containing:

  1. Result number
  2. Title
  3. URL
  4. Snippet


These results are then returned to the AI so it can decide what to investigate next.

18.45 No Search Results

If no results are returned, the Agent receives:

“No search results found.”

It can then determine whether another research path is appropriate.

18.46 Search Error

If the search service fails, the research result contains:

Search error: [message].

18.47 Browser Navigate

When the Agent decides to read a particular webpage, it can use:

browser_navigate.

The activity log records:

Routing connection proxy to: [URL].

18.48 What Navigation Extracts

The Browser navigation process can retrieve:

  1. Page Title
  2. Final URL
  3. Extracted text content
  4. Page links


18.49 Links Included in Agent Page Reading

When page content is returned to the research Agent, the current processor includes up to the first:

10 links

in the formatted page-content result.

The visible Parsed Links tab can display the broader link collection returned for the page.

18.50 Navigate Error

If Browser Control cannot fetch a page, the research process returns:

Navigate error: [message].

18.51 Search → Navigate → Read

The intended research sequence is generally:

Search

Review search results

Navigate

Read page text

Review page links

Continue investigating if needed

Synthesize answer

This is the defining workflow of Browser Control.

18.52 Current Browser Page Is Part of the Agent Context

When the research Agent starts, its instructions include:

Current page URL: [current URL].

Therefore, manually navigating to a relevant starting page before launching can help give the Agent additional context.

18.53 Starting on a Specific Website

If you already know the appropriate official website:

  1. Enter its URL in the Browser address field.
  2. Press Enter.
  3. Confirm the page loads.
  4. Enter the Research Objective.
  5. Launch the Agent.

This can make the intended source clearer.

18.54 Agent Can Still Search Elsewhere

Providing a starting page does not force the research loop to remain on that website.

The Agent's instructions permit searching and navigating multiple times.

If your research must stay within one source/domain, say so explicitly in the Research Objective.

18.55 Example — Restricting Research

Use only the official company website and its linked documentation. Do not use third-party sources.

This gives the Agent a clearer research boundary.

18.56 Example — Multi-Source Research

Use each vendor's official pricing and product pages first, then use reputable third-party sources only where a direct comparison or independent review is useful.

18.57 Agent Can Finish Before Five Iterations

Five iterations are a maximum, not a required minimum.

If the AI returns a final text response without additional Browser tool calls, Browser Control records:

“Agent successfully finalized synthesis and delivered findings.”

and stops the loop.

18.58 Maximum Loop Threshold

If all five iterations are used and no final answer has yet been produced, Browser Control records:

“Maximum loop threshold met — Generating comprehensive review report...”

18.59 Final Forced Synthesis

After reaching the five-step threshold without an answer, Browser Control makes a final AI synthesis request instructing the Model:

“Based on all the research you've done, please provide your final comprehensive answer now. Do NOT call any tools.”

This final synthesis is separate from the five visible research iterations.

18.60 Possible Sixth AI Request

Because the research loop can use five AI iterations and then invoke a separate final synthesis request, one full mission can involve as many as:

five loop requests + one final synthesis request

under the current client workflow.

This matters when understanding Token usage and mission complexity.

18.61 No Unlimited Autonomous Browsing

The current implementation does not allow Browser Control to research indefinitely.

The five-iteration cap creates a fixed stopping boundary.

For very large research tasks, divide the work into focused missions.

18.62 Break Large Research into Multiple Objectives

Instead of:

Research everything about the entire global insurance technology market.

consider separate missions such as:

  1. Market size and growth
  2. Major competitors
  3. Software pricing
  4. Distribution models
  5. AI adoption
  6. Regulatory trends

This helps each mission use its limited research loop effectively.

18.63 No Stop Agent Button Is Established

While the Agent is running, the Launch button changes to Running Sandbox Agent, but the current Browser Control source does not establish a user-facing:

Stop

or:

Cancel Agent

control.

Allow the current mission to complete.

18.64 Avoid Starting a Mission Until the Objective Is Ready

Because there is no verified Stop button:

Prepare Objective → Review → Launch

is preferable to launching first and attempting to correct the mission afterward.

18.65 Telemetry Monitor

Browser Control contains a research activity console titled:

Telemetry Monitor.

This provides visibility into the Agent's research process.

18.66 Initial Console Message

When Browser Control first loads, the logs begin with:

“Browser agent initialized. Ready for instructions.”

18.67 Starting a Mission Replaces the Existing Logs

When a new autonomous mission begins, the current logs are reset and replaced by:

Agent started — “[Research Objective]”.

Therefore, preserve old logs before launching another mission if you need them.

18.68 Log Categories

The current console recognizes six activity types:

  1. Search
  2. Navigate
  3. Agent
  4. Result
  5. Error
  6. System


18.69 Search Logs

A Search entry represents web-search activity.

Example:

Querying web: “...”

18.70 Navigate Logs

A Navigate entry represents movement to a specific webpage through the Browser proxy.

Example:

Routing connection proxy to: ...

18.71 Agent Logs

An Agent entry represents agent-level mission activity.

The first entry typically identifies the Research Objective with which the mission was launched.

18.72 Result Logs

A Result entry identifies successful research completion or final synthesis.

Examples include:

Agent successfully finalized synthesis and delivered findings.

and:

Final research data synthesized.

18.73 Error Logs

An Error entry indicates a research/process problem.

One current example is:

“Model returned empty payload response. Terminal process aborted.”

18.74 System Logs

System logs provide progress and status information such as:

Step 2/5 — Analyzing current viewport & planning next action...

or information related to returned search/navigation results.

18.75 Log Timestamps

Each console entry includes a timestamp with:

  1. Hour
  2. Minute
  3. Second

based on the user's current browser environment.

18.76 Logs Automatically Scroll

As new entries are added, Browser Control automatically scrolls toward the newest log.

This makes it easier to follow active research.

18.77 Awaiting Remote LLM Instruction Packet

While the Agent or underlying AI system is working, the console can display:

“Awaiting remote LLM instruction packet...”

This is a waiting-state indicator.

18.78 Copy Console Output

The Telemetry Monitor contains a Copy control titled:

Copy Console Output.

Use it when you want to preserve the current research activity logs.

18.79 What Copy Console Output Copies

The copied text formats each log approximately as:

[time] [TYPE] content

and combines the entries line-by-line.

18.80 Copy Confirmation

After selecting Copy Console Output, the Copy icon temporarily changes to a Check icon for approximately two seconds.

The current source does not establish a separate toast notification for this action.

18.81 Clear Console

Beside Copy is a Trash control titled:

Clear Console.

18.82 What Clear Console Does

Clear Console removes the current log collection and restores the single default entry:

“Browser agent initialized. Ready for instructions.”

18.83 Clear Console Does Not Clear the Final Answer

The handleClearLogs action changes only the Log collection.

It does not clear:

  1. Research Objective
  2. Synthesis Results
  3. Current webpage
  4. Browser navigation history

according to the current source.

18.84 Clear All and Clear Console Are Different

Clear all

Clears:

  1. Research Objective
  2. Reference image

Clear Console

Clears:

  1. Telemetry logs

Do not confuse these two actions.

18.85 Telemetry LOGS Count

The bottom of Telemetry Monitor displays:

LOGS: [number].

This number reflects the current number of entries in the local console.

18.86 STREAMING / SYS_IDLE

The console status can display:

STREAMING

when the shared AI stream is active.

Otherwise it displays:

SYS_IDLE.

18.87 PROXY: SECURE Indicator

The console currently displays:

PROXY: SECURE.

This is a user-interface status label associated with the Browser Control proxy workflow.

18.88 TEL_PING: 47ms Is Not a Live Measurement

The current Telemetry bar displays:

TEL_PING: 47ms.

The value 47ms is hard-coded in the current interface rather than dynamically calculated from actual network latency.

Therefore:

Do not use TEL_PING: 47ms as a network-performance diagnostic measurement.

18.89 Synthesis Results

Once Browser Control has produced a final research answer, a lower-left panel appears titled:

Synthesis Results.

This is the main final-answer area.

18.90 Synthesis Results Use Markdown

The final Agent answer is rendered using PROS SUITE's Markdown Renderer.

Depending on the AI response, it can contain:

  1. Headings
  2. Lists
  3. Structured sections
  4. Links
  5. Emphasis
  6. Other supported Markdown

18.91 Copy Answer

The Synthesis Results header contains a Copy control titled:

Copy markdown content.

This is the equivalent of Copy Answer for the generated research result.

18.92 What Copy Answer Copies

The Copy action writes the complete current:

agentAnswer

to the clipboard.

It copies the underlying Markdown content.

18.93 Copy Answer Does Not Run More Research

Copying the Synthesis Results:

  1. Does not start another Agent mission
  2. Does not perform another search
  3. Does not modify the answer

It simply copies the existing result.

18.94 Copy Answer Confirmation

After copying, the icon changes temporarily from Copy to a Check.

18.95 Download Report

Beside the Copy control is:

Download report (.md).

This creates a Markdown research report from the completed Browser Control mission.

18.96 Report Format

The downloaded report begins with:

# AI Browser Research Report

and includes:

  1. Research Objective
  2. Engine
  3. Timestamp
  4. Final Agent Answer


18.97 Research Objective in the Report

The downloaded Markdown includes:

Research Objective: [your objective]

This helps preserve what the Agent was originally asked to investigate.

18.98 Engine in the Report

The report records:

Engine: [selected Model]

or:

Default

when no selected Model value is available.

18.99 Report Timestamp

The Markdown report records a Timestamp generated with the browser's local date/time formatting.

18.100 Downloaded Filename

The current report filename follows:

research_report_YYYY-MM-DD.md.

18.101 Filename Date Uses UTC

There is a subtle current-version distinction.

The report's internal Timestamp uses the browser's local time, but the filename's date is generated from an ISO timestamp and therefore uses the UTC date.

Around evening hours in North American time zones, the filename date can therefore be one calendar day ahead of the locally displayed report Timestamp.

This is expected from the current implementation.

18.102 Download Report Does Not Include Console Logs

The .md report contains:

  1. Objective
  2. Engine
  3. Timestamp
  4. Synthesis Answer

It does not include the Telemetry Monitor's complete Log collection in the current download implementation.

If you need the logs:

Copy Console Output separately.

18.103 Preserve Both Answer and Logs When Needed

For a research/audit workflow where you need both:

  1. Use Download report (.md).
  2. Use Copy Console Output.
  3. Store the console text with the report in your appropriate records.

18.104 No Universal Saved Research History

The current Browser Control source maintains:

  1. Research Objective
  2. Logs
  3. Agent Answer
  4. Browser history

as current-page state.

It does not establish a persistent:

  1. Saved Research Projects
  2. Research History page
  3. Previous Browser Control Missions

system.

18.105 Leaving or Refreshing Can Lose Research State

Because no persistent Browser Control mission-storage workflow is established in the supplied source, do not assume the current:

  1. Answer
  2. Logs
  3. Objective
  4. Browser navigation history

can be recovered after the Browser Control page is recreated.

Preserve important research before leaving.

18.106 No Save Research Button

The current Browser Control workspace does not provide:

Save Research

or:

Save Project.

Use:

  1. Copy Answer
  2. Download Report
  3. Copy Console Output

to preserve results.

18.107 No Delete Research Project Function

Because there is no source-verified Saved Research Project system, there is also no corresponding:

Delete Research Project

workflow.

Clear Console and Clear All only modify the current workspace state.

18.108 The Right-Side Browser

Browser Control contains a browser-style environment on the right side.

It begins with the current URL:

https://google.com

in the source-defined initial state.

18.109 Manual Browser Mode

When the Autonomous Agent is not running, the status badge displays:

Manual mode.

You can navigate manually before or after a research mission.

18.110 Agent Pilot Mode

While the Agent is running, the status changes to:

Agent Pilot Mode.

This indicates that the autonomous research loop is currently active.

18.111 Address Field

The Browser address field displays:

Enter URL to navigate manually...

Enter a webpage address and press Enter.

18.112 Automatic HTTPS Normalization

If you enter an address without starting it with http, Browser Control automatically prefixes:

https://.

For example:

example.com

becomes:

https://example.com

18.113 Manual Navigation Also Extracts Page Data

Manual URL navigation does more than update the visible Browser.

The current process also attempts to retrieve:

  1. Title
  2. URL
  3. Extracted text
  4. Links

for use by the Text Reader and Parsed Links tabs.

18.114 Back

The Browser toolbar includes a Back arrow.

It becomes available when earlier entries exist in the current Browser Control navigation history.

18.115 Forward

The Forward arrow becomes available when a later history entry exists.

18.116 Refresh

The Browser toolbar includes a Refresh control.

It reloads the current Browser Control URL through the manual navigation workflow.

18.117 Loading Indicator

While a page is loading, the Refresh icon animates and the address field displays a loading spinner.

18.118 Proxying Document

During page loading, Browser Control can display:

Proxying Document

with the current URL.

18.119 Load Timeout

The current page-loading visual state contains a fallback that ends after approximately:

10 seconds

if no Browser-loaded event clears it earlier.

The timeout ends the visual loading state; it should not itself be interpreted as proof that every page loaded successfully.

18.120 Connection Secure Tooltip

Hovering over the Lock icon displays:

✓ Connection Secure

and:

“SSL proxy active. Cookies and data routed through isolated API endpoint.”

This is the current Browser Control interface wording.

18.121 Treat the Security Tooltip as Interface Status

The supplied user-interface source confirms that the tooltip is displayed and that Browser Control routes pages through its Browser proxy endpoints.

The bundle does not contain enough backend infrastructure detail to independently audit every security property implied by that message.

Therefore, this manual records the interface wording but does not expand it into unsupported technical security guarantees.

18.122 Three Browser Tabs

The current Browser viewport provides:

  1. Live viewport
  2. Text Reader
  3. Parsed Links ([number])


These three views are extremely useful for understanding what Browser Control has loaded.

18.123 Live Viewport

Live viewport displays the proxied webpage visually inside Browser Control.

Use it to inspect the actual page presentation.

18.124 Agent Activity in Live Viewport

While the Agent is active, the Live viewport receives visual boundary/scan-line indicators showing that Browser Control is in Agent Pilot Mode.

These are interface indicators rather than webpage content.

18.125 Live Viewport Is Proxied

The Browser viewport loads the current page through:

/api/browser/proxy

rather than directly using the original site URL as the iframe source.

18.126 Some Websites May Behave Differently Through the Proxy

Because Browser Control uses a proxied/sandboxed environment, some websites may:

  1. Render differently
  2. Restrict content
  3. Fail to load
  4. Behave differently from a normal browser
  5. Require functions not supported by the proxy

A failed page does not necessarily mean the public website itself is offline.

18.127 Text Reader

Select:

Text Reader

to view the page's extracted text content.

This is useful when a webpage contains distracting design elements and you want to focus on the information Browser Control extracted.

18.128 Filter Text Content

Text Reader provides:

Filter text content...

Enter a word or phrase to filter the displayed extracted text.

18.129 How Text Filtering Works

The current Text Reader filter keeps lines containing your search text using a case-insensitive comparison.

This is a local filter of already extracted page text.

It does not launch another web search.

18.130 Reset Filter

When Text Reader filtering is active, select:

Reset Filter.

This returns to the complete currently extracted page text.

18.131 No Matching Extracted Text

If nothing matches the Reader filter, Browser Control displays:

“No extracted text matches your search.”

18.132 Text Reader Is Not the Same as Original HTML

The Text Reader displays the textContent extracted by the Browser proxy.

It should not be interpreted as:

  1. Full webpage source code
  2. Complete DOM
  3. Every hidden element
  4. Every dynamically loaded resource

It is a reader representation of extracted page text.

18.133 Parsed Links

Select:

Parsed Links ([number])

to review the links extracted from the loaded page.

18.134 Parsed Link Information

Each Parsed Links card can display:

  1. Anchor text
  2. URL


18.135 Search Links

The Parsed Links tab provides:

Search links or anchor text...

The filter searches both:

  1. Link text
  2. Link URL

case-insensitively.

18.136 Clear Search

When a Parsed Links search is active, select:

Clear Search.

18.137 Navigating from Parsed Links

Each link has a navigation control titled:

Navigate to URL.

Selecting it:

  1. Navigates Browser Control to that link.
  2. Switches the interface back to:
  3. Live viewport

18.138 No Matching Parsed Links

If no links match the current filter, Browser Control displays:

“No parsed links match your search filter.”

18.139 Text Reader and Parsed Links Are Page-Specific

These tabs represent the most recently extracted page.

If you navigate elsewhere:

  1. Page text changes
  2. Parsed links change

They are not a persistent multi-page research archive.

18.140 Browser Navigation History

Browser Control maintains a current-session list of visited URLs and an active history position.

This supports the Back and Forward buttons.

18.141 Browser History Is Not Saved Research History

Navigation history should not be confused with a persistent Browser History page.

The source does not establish restoration of this Browser Control navigation history after the workspace is recreated.

18.142 Autonomous Agent Changes the Visible Browser Page

When the Agent performs browser_navigate, it calls the same Browser navigation workflow used by the visible Browser viewport.

Therefore:

You can watch the Browser move to pages the research Agent chooses to inspect.

18.143 Agent Search Does Not Necessarily Show a Search-Engine Page

When the Agent performs browser_search, Browser Control queries its search endpoint and gives those results directly to the Agent.

The visible Browser does not need to display a conventional search-engine results page for every autonomous search.

18.144 Agent Navigation Does Update the Viewport

By contrast, browser_navigate updates the visible Browser destination.

This allows you to see the page being investigated.

18.145 Manual Navigation While Agent Is Running

The current source does not explicitly disable every manual Browser navigation control while Agent Pilot Mode is active.

However, changing pages manually during an autonomous research mission can make the visible viewport diverge from what you expect the Agent to be analyzing.

Best practice:

Allow the Agent to complete its research before performing unrelated manual navigation.

18.146 Browser Control Is a Research Agent, Not a General Robotic Browser

The current Agent instructions establish only two autonomous research actions:

  1. Search
  2. Navigate/read


The current source does not establish autonomous Agent functions for:

  1. Typing into arbitrary website forms
  2. Logging into websites
  3. Making purchases
  4. Adding products to carts
  5. Sending messages
  6. Posting content
  7. Booking appointments
  8. Uploading files to arbitrary websites
  9. Performing financial transactions
  10. Clicking arbitrary DOM elements as an Agent tool

Do not assume Browser Control performs those actions merely because it displays a Browser viewport.

18.147 Manual Browser Form Capability Is Separate

The embedded Browser sandbox permits certain webpage scripting/form behaviors, but that does not create an autonomous AI form-submission tool.

The source-verified Agent capability remains Search + Navigate/Read.

18.148 No Source-Verified Autonomous Purchase Capability

Browser Control can research public pricing.

It should not be treated as a purchasing Agent.

For example:

Compare prices

is source-aligned.

Buy the cheapest product for me

is not established by the current Browser Control toolset.

18.149 No Source-Verified Login Automation

The autonomous tool definitions do not establish:

  1. Username entry
  2. Password entry
  3. MFA completion
  4. Account Login automation

Use Browser Control primarily for accessible public-page research.

18.150 No Source-Verified Website Modification

Browser Control cannot be assumed to:

  1. Edit your website
  2. Update a third-party CMS
  3. Modify a CRM
  4. Change account settings

Those functions require dedicated systems.

18.151 Selected AI Model

Browser Control reads the current shared:

selectedModel

from your PROS SUITE account.

The shared AI streaming workflow then sends the current selected Model with each applicable Agent AI request.

18.152 Change the Model Before Launching

If you want a particular available Model for Browser Control:

  1. Select it from the PROS SUITE Header.
  2. Return to Browser Control.
  3. Prepare the Research Objective.
  4. Launch the Agent.

18.153 Model Is Recorded in Downloaded Report

The currently selected Model is written into the downloaded Markdown report as:

Engine.

This is useful when preserving research performed with different Models.

18.154 Provider API Keys Can Apply

Because Browser Control uses the shared PROS SUITE AI streaming system, user-configured provider API Keys can be included with the applicable AI request.

If a selected Model requires a missing provider credential, follow Chapters 10 and 11.

18.155 Browser Control Token Definition

The current PROS SUITE feature catalogue defines:

Browser Control — 25 Tokens.

However, this is a feature-level default/fallback definition.

18.156 Browser Control Does Not Display a Per-Mission Cost

Unlike the Standard Generator, the Browser Control page itself does not show:

25 tokens per use

or:

Your balance: ...

beside the Research Objective.

Therefore, users should monitor their overall Monthly Tokens through the normal PROS SUITE account interface.

18.157 One Mission Can Use Multiple AI Requests

The Agent invokes the shared AI stream repeatedly as it plans its research.

The loop can make up to five reasoning requests and, when necessary, an additional final synthesis request.

18.158 Exact Mission Deduction Is Not Established by the Included Source

The Browser Control client does not contain its own explicit /api/tokens/deduct call.

Instead, each AI request is sent through /api/ai/stream with:

tool: "browser-control".

The server-side AI endpoint responsible for final Token accounting was intentionally excluded from the sanitized User Operations source bundle.

Therefore, this manual does not assert that:

  1. One full mission always costs 25 Tokens
  2. Every iteration costs 25 Tokens
  3. Five iterations always cost 125 Tokens
  4. A final synthesis has a particular additional charge

Those deductions are not source-verifiable from the supplied user-side bundle.

18.159 Account Balance Refresh

The shared AI streaming workflow refreshes the authenticated user state after each AI stream completes.

This allows updated Token information to be reflected elsewhere in PROS SUITE.

18.160 Best Token Practice for Browser Control

Because a mission can require multiple AI steps:

  1. Check Monthly Tokens before starting.
  2. Use a focused objective.
  3. Specify likely source domains where possible.
  4. Avoid extremely broad tasks.
  5. Let one mission finish before launching another.
  6. Check your balance after substantial research activity.

18.161 Browser Search and Token Usage Should Not Be Guessed Separately

The current client does not establish a user-visible individual Token charge for:

  1. Search endpoint use
  2. Navigation endpoint use
  3. Text Reader
  4. Parsed Links
  5. Manual Browser navigation

Do not assign made-up Token prices to these operations.

18.162 Synthesis Results Are AI-Generated

Even though Browser Control can research actual webpages, the final Synthesis is generated by an AI Model.

Therefore, the final response can still:

  1. Misinterpret a source
  2. Miss relevant context
  3. Combine facts incorrectly
  4. Overstate conclusions
  5. Contain unsupported inference

Review important findings.

18.163 Source Links Are Not Guaranteed in the Final Answer

The Agent receives search-result URLs and webpage content as part of its research history.

However, the current Synthesis Results interface does not establish a separate mandatory:

  1. Sources panel
  2. Citation list
  3. Footnotes section
  4. Source verification table

The final AI response may include links when generated, but this is not guaranteed by the current interface.

18.164 Verify Important Research

For high-value business research:

  1. Review the final Synthesis.
  2. Look at the actual page in Live viewport.
  3. Use Text Reader.
  4. Review Parsed Links.
  5. Visit the most important sources directly.
  6. Verify key facts before relying on them.

18.165 Verify Current Pricing

For price comparisons:

  1. Confirm product variant
  2. Confirm currency
  3. Confirm subscription interval
  4. Confirm sale vs. standard price
  5. Confirm geography
  6. Confirm taxes/shipping where relevant
  7. Confirm the page date/current availability

Price information can change rapidly.

18.166 Verify Legal and Regulatory Research

Browser Control can help locate and summarize information, but legal/regulatory conclusions should be verified against:

  1. Official statutes
  2. Regulations
  3. Government agencies
  4. Qualified counsel where appropriate

18.167 Verify Financial Research

For financial or investment decisions, confirm:

  1. Dates
  2. Figures
  3. Source identity
  4. Market conditions
  5. Official filings
  6. Applicable professional guidance

before acting.

18.168 Verify Medical or Health Research

Health-related conclusions require appropriate authoritative/professional verification.

The presence of web research does not make the final AI synthesis medical advice.

18.169 Use Official Sources When They Matter

For high-confidence research, include source instructions such as:

Prioritize the manufacturer's official documentation.

or:

Use the government agency's official website.

or:

Use the company's official investor relations materials.

18.170 Do Not Assume the First Search Result Is Best

Browser Control's Agent is instructed to select relevant pages, but relevance is still AI-determined.

For important research, manually inspect the key source.

18.171 Troubleshooting — Launch Button Is Disabled

Check whether:

  1. The Research Objective is empty
  2. The Agent is already running
  3. Another underlying AI stream is still active


18.172 Troubleshooting — Image Will Not Upload

Check:

  1. The file is an image.
  2. It is under 5 MB.
  3. The Agent is not already running.

The current attachment control is disabled while the Agent runs.

18.173 Troubleshooting — Image Exceeds Limit

If the Telemetry Monitor reports:

Image upload failed: File size exceeds the 5MB limit.

reduce the file size and retry.

18.174 Troubleshooting — Agent Stops After Five Steps

This is expected.

The current research loop has:

MAX_AGENT_ITERATIONS = 5.

If no answer has already been produced, Browser Control then attempts its final comprehensive synthesis.

18.175 Troubleshooting — Model Returned Empty Payload

The current interface can log:

“Model returned empty payload response. Terminal process aborted.”

Possible next steps:

  1. Confirm the selected Model remains available.
  2. Check provider API-Key requirements.
  3. Check your Token Balance.
  4. Simplify the objective.
  5. Retry the mission.

18.176 Troubleshooting — Sandbox Process Failure

If the Agent throws an exception, Browser Control adds:

Sandbox process failure: [message].

Review the Error log and retry if appropriate.

18.177 Troubleshooting — Search Returns No Results

The Agent can receive:

No search results found.

Try:

  1. More precise terminology
  2. Correct product/company spelling
  3. A direct URL
  4. A less restrictive research objective

18.178 Troubleshooting — Search Error

If the search service itself fails, the returned research content reports:

Search error: ...

Retry later or start from a direct relevant URL.

18.179 Troubleshooting — Page Fetch Failed

Browser navigation can return:

Navigate error: Page fetch failed

or another Navigate error.

Possible causes include:

  1. Website restrictions
  2. Proxy compatibility
  3. Invalid URL
  4. Temporary site problem
  5. Unsupported page behavior

18.180 Troubleshooting — Page Does Not Look Normal

Remember that Live viewport displays a proxied/sandboxed version of the website.

Some pages may behave differently than they do in your normal browser.

18.181 Troubleshooting — Text Reader Is Empty

Possible explanations include:

  1. The page returned little extractable text.
  2. The page failed to load.
  3. Content is heavily dynamic.
  4. Your Text Reader filter hides everything.

First select:

Reset Filter

if filtering is active.

18.182 Troubleshooting — Parsed Links Is Disabled

The Parsed Links tab is disabled when:

  1. No Page Data exists
  2. The currently extracted page contains no links


18.183 Troubleshooting — Cannot Find a Link

Use:

Search links or anchor text...

The filter searches both link text and URL.

18.184 Troubleshooting — Browser Appears Stuck Loading

The UI automatically clears its loading overlay after approximately ten seconds if the expected loaded event does not arrive.

If the underlying page remains unavailable:

  1. Try Refresh.
  2. Enter the URL again.
  3. Try the site's main domain.
  4. Use another public source.

18.185 Troubleshooting — Final Synthesis Panel Does Not Appear

Synthesis Results appears only when agentAnswer contains a completed answer.

Check the Telemetry Monitor for:

  1. Agent activity
  2. Result
  3. Error
  4. Maximum-loop synthesis

18.186 Troubleshooting — Copy Answer Does Nothing

Copy Answer requires a completed Synthesis result.

If no agentAnswer exists, the Copy handler returns without performing an action.

18.187 Troubleshooting — Download Report Does Nothing

Report Download also requires a completed agentAnswer.

Wait for Synthesis Results to appear first.

18.188 Troubleshooting — Report Is Markdown

This is expected.

The report's MIME type is:

text/markdown

and its filename ends in:

.md.

18.189 Troubleshooting — Report Filename Date Looks One Day Ahead

The current filename uses the UTC ISO date, while the report Timestamp uses local browser time.

Around local evening hours, those dates can differ.

This is current-version behavior.

18.190 Troubleshooting — Downloaded Report Has No Activity Logs

This is also expected.

The current Markdown report contains the Synthesis Answer and mission metadata, not Telemetry logs.

Use:

Copy Console Output

when you need the research activity record.

18.191 Troubleshooting — Clear Console Removed My Logs

Clear Console intentionally resets the logs to the default initialization entry.

There is no source-verified Undo for this action.

Copy important logs before clearing.

18.192 Troubleshooting — Old Logs Vanished When a New Mission Started

The current mission-start handler replaces the existing Log collection with the new:

Agent started — ...

entry.

Preserve old logs before launching another research mission.

18.193 Troubleshooting — No Saved Research History

The current Browser Control source does not establish persistent mission storage.

Download important reports before leaving the workspace.

18.194 Troubleshooting — Browser Control Result Has No Citations

A separate citation system is not source-verified for Synthesis Results.

If source traceability matters:

  1. Inspect the actual Browser pages.
  2. Preserve relevant URLs.
  3. Use Parsed Links.
  4. Ask the Research Objective to include source URLs in the final answer.

For example:

Include the URL for every major source used in the final report.

18.195 Best Practice — Ask for Source URLs

Because automatic citations are not guaranteed, include:

At the end, list the important source URLs used for the research.

This gives the AI a clear output requirement.

18.196 Best Practice — Use a Specific Starting URL

When the source is known:

  1. Navigate manually.
  2. Confirm the correct page.
  3. Launch the Agent.

This can reduce unnecessary searching.

18.197 Best Practice — State Source Priority

Example:

Prioritize official sources. Use third-party sources only for independent comparison.

This improves the research strategy.

18.198 Best Practice — Define What “Current” Means

For time-sensitive research, write:

Find the currently published pricing as of today.

or:

Use the latest official release information available on the vendor's website.

Then verify the date in the underlying sources.

18.199 Best Practice — Define Geography

Pricing and product availability can differ by country.

For example:

Compare current U.S. pricing in USD.

is more precise than:

Compare pricing.

18.200 Best Practice — Define Product Version

Use:

iPhone 16 Pro Max 256GB

rather than:

iPhone 16

if exact pricing is important.

18.201 Best Practice — Request Structured Synthesis

For easier reuse, ask for:

  1. Executive Summary
  2. Findings
  3. Comparison
  4. Risks
  5. Recommendation
  6. Source URLs

Browser Control's Markdown Synthesis can format this structure cleanly.

18.202 Best Practice — Inspect the Evidence Before Acting

Use all three right-side views:

Live viewport

→ What the actual webpage looks like

Text Reader

→ What text was extracted

Parsed Links

→ What links were found

This is more reliable than relying solely on the AI summary.

18.203 Best Practice — Preserve High-Value Research Immediately

After an important mission:

  1. Download report (.md)
  2. Copy Console Output
  3. Copy important source URLs
  4. Store them in the appropriate business records

Do this before starting another mission.

18.204 Best Practice — Do Not Overload One Mission

Because Browser Control has a five-iteration research limit, a narrow objective usually performs better than an enormous multi-industry assignment.

Break complex work into logical research modules.

18.205 Best Practice — Avoid Unnecessary Repeated Missions

If the first report is strong but missing one item, consider launching a narrower follow-up mission rather than repeating the entire research assignment from scratch.

18.206 Best Practice — Monitor Token Balance

Browser Control can perform multiple AI reasoning steps during one mission.

Review Monthly Tokens before and after larger research tasks.

18.207 Best Practice — Choose the Model Intentionally

Complex research may benefit from a stronger reasoning Model, but Model choice can also affect provider access and usage.

Select the desired Model before launching.

18.208 Best Practice — Preserve the Model in the Report

Because Download Report automatically records the selected:

Engine

the .md report can help you identify which Model generated a particular research synthesis.

18.209 Best Practice — Do Not Treat Telemetry as an Audit Trail

Telemetry Monitor is useful for observing:

  1. Search
  2. Navigate
  3. Agent
  4. Result
  5. Error
  6. System

activity.

However, it should not be interpreted as an independently certified forensic audit trail.

Some interface labels and values—such as TEL_PING: 47ms—are static presentation elements.

18.210 Best Practice — Keep Sensitive Information Out of Public Research

Browser Control is designed around public web research.

Do not unnecessarily place into the Research Objective:

  1. Passwords
  2. API Keys
  3. Customer credentials
  4. Highly sensitive personal data
  5. Confidential trade secrets

especially when they are not required for the task.

18.211 Recommended Browser Control Workflow

A complete workflow is:

OPEN BROWSER CONTROL

Optional:

MANUALLY NAVIGATE TO STARTING URL

RESEARCH OBJECTIVE

Optional:

UPLOAD REFERENCE IMAGE

Optional:

SELECT EXAMPLE PROMPT

LAUNCH AUTONOMOUS AGENT

Agent loop:

ANALYZE

SEARCH

NAVIGATE

READ

SEARCH / NAVIGATE AGAIN AS NEEDED

Up to:

5 ITERATIONS

If needed:

FINAL SYNTHESIS

SYNTHESIS RESULTS

Review evidence using:

LIVE VIEWPORT

TEXT READER

PARSED LINKS

Preserve:

COPY ANSWER

DOWNLOAD REPORT (.MD)

COPY CONSOLE OUTPUT

18.212 Browser Control User Checklist

Before launching:

  1. I know what I want researched.
  2. My Research Objective is specific.
  3. I identified the products/companies/topics.
  4. I specified the desired sources where important.
  5. I specified geography where relevant.
  6. I specified product/version where relevant.
  7. I defined the desired final output.
  8. I selected the appropriate AI Model.
  9. I checked Monthly Tokens.
  10. I manually loaded a starting URL if useful.
  11. I attached an image only if it contributes to the research.
  12. My image is under 5 MB.
  13. I understand the Agent can perform up to five research iterations.
  14. I understand there is no verified Stop Agent button.

18.213 During-Research Checklist

While Browser Control is active:

  1. I can see Running Sandbox Agent.
  2. I can see the current iteration.
  3. I can monitor Telemetry Monitor.
  4. I recognize Search logs.
  5. I recognize Navigate logs.
  6. I recognize System logs.
  7. I recognize Result logs.
  8. I recognize Error logs.
  9. I understand the visible Browser can change as the Agent navigates.
  10. I avoid unrelated manual navigation during the research loop.
  11. I wait for Synthesis Results before treating the mission as complete.

18.214 Research Verification Checklist

Before relying on important findings:

  1. I read the complete Synthesis.
  2. I inspected important source pages.
  3. I used Text Reader where useful.
  4. I reviewed Parsed Links.
  5. I confirmed important source URLs.
  6. I verified pricing dates.
  7. I verified market figures.
  8. I checked product variants.
  9. I distinguished source facts from AI conclusions.
  10. I verified high-stakes claims independently.

18.215 Research Preservation Checklist

Before leaving or starting another mission:

  1. I selected Copy Answer if needed.
  2. I downloaded the .md report.
  3. I copied the Console Output if needed.
  4. I preserved important source URLs.
  5. I understand a new mission resets the current logs.
  6. I understand Browser Control does not establish persistent Saved Research Projects.
  7. I understand Clear Console cannot be undone through a verified UI control.

18.216 What Browser Control Currently Supports

The source verifies subscriber-facing capabilities for:

Research Input

  1. Natural-language Research Objective
  2. Multi-line input
  3. Example Prompts
  4. Reference image
  5. 5 MB image limit

Autonomous Research

  1. AI reasoning loop
  2. Maximum five research iterations
  3. Browser Search
  4. Browser Navigate/Read
  5. Final forced synthesis if necessary

Manual Browser

  1. Address bar
  2. HTTPS normalization
  3. Back
  4. Forward
  5. Refresh
  6. Current-session history

Browser Inspection

  1. Live viewport
  2. Text Reader
  3. Text filtering
  4. Parsed Links
  5. Link filtering
  6. Navigate from parsed link

Monitoring

  1. Telemetry Monitor
  2. Search logs
  3. Navigate logs
  4. Agent logs
  5. Result logs
  6. Error logs
  7. System logs
  8. Timestamps
  9. Copy Console Output
  10. Clear Console

Results

  1. Synthesis Results
  2. Markdown rendering
  3. Copy Answer
  4. Download Markdown Report
  5. Research Objective metadata
  6. Model/Engine metadata
  7. Timestamp

18.217 What Browser Control Does Not Currently Establish

The supplied user-facing source does not establish:

  1. Unlimited autonomous browsing
  2. User-configurable iteration count
  3. Stop Agent button
  4. Pause Agent button
  5. Persistent Saved Research Projects
  6. Research mission history
  7. Universal automatic citations
  8. Mandatory Sources panel
  9. PDF report export
  10. DOCX report export
  11. Automatic Email sharing
  12. Autonomous website Login
  13. Password entry automation
  14. MFA automation
  15. Autonomous checkout/purchases
  16. Autonomous financial transactions
  17. Arbitrary form submission by the Agent
  18. Posting to external websites
  19. Automatic CRM updates
  20. Automatic Email sending
  21. Full webpage source-code inspection
  22. Guaranteed access to every website
  23. A user-visible exact per-mission Token cost

These capabilities should not be described as active subscriber functions unless a later user-facing release verifies them.

18.218 Understanding the Two Browser Modes

Browser Control can be thought of as having two operating modes.

Manual Mode

You control:

  1. URL
  2. Back
  3. Forward
  4. Refresh
  5. Parsed Link navigation

Agent Pilot Mode

The AI research process can:

  1. Search
  2. Navigate
  3. Read
  4. Analyze
  5. Synthesize

The current status badge identifies which mode is active.

18.219 Browser Control at a Glance

The current subscriber experience can be summarized as:

BROWSER CONTROL

Autonomous browser agent interface

RESEARCH OBJECTIVE

Enter natural language research task...

Optional:

REFERENCE IMAGE

LAUNCH AUTONOMOUS AGENT

LOOP ACTIVE

Iteration 1–5

Possible actions:

SEARCH

NAVIGATE

READ

Visible in:

TELEMETRY MONITOR

and:

LIVE VIEWPORT

Research inspection:

TEXT READER

PARSED LINKS

When enough information exists:

SYNTHESIS RESULTS

Preserve:

COPY ANSWER

DOWNLOAD REPORT (.MD)

COPY CONSOLE OUTPUT

18.220 Chapter Summary

AIUNIFY PROS SUITE Browser Control is a specialized autonomous web-research workspace labeled:

Browser Control

“Autonomous browser agent interface.”

Users define a natural-language:

Research Objective

and launch:

Launch Autonomous Agent.

The current Agent architecture is bounded to:

5 research iterations

and is instructed to use two research actions:

  1. browser_search
  2. browser_navigate

to locate, navigate to, read, and analyze public webpage information.

If the Agent reaches the end of its five-step loop without already producing a final answer, Browser Control performs a separate final synthesis request instructing the Model to deliver a comprehensive answer without additional Browser tools.

The workspace provides a Telemetry Monitor with:

  1. Search
  2. Navigate
  3. Agent
  4. Result
  5. Error
  6. System

activity types. Logs can be preserved using Copy Console Output or reset using Clear Console.

The right-side Browser supports:

  1. Back
  2. Forward
  3. Refresh
  4. Manual URL entry
  5. Live viewport
  6. Text Reader
  7. Parsed Links


Text Reader can locally filter extracted page text, while Parsed Links can search link Names/URLs and navigate directly to a selected link.

When research is complete, Synthesis Results displays the AI's final Markdown answer. Users can copy the result or download:

research_report_YYYY-MM-DD.md

containing:

  1. AI Browser Research Report
  2. Research Objective
  3. Selected Engine
  4. Timestamp
  5. Final synthesis


The feature catalogue currently defines Browser Control with a fallback cost of 25 Tokens, but Browser Control itself can make multiple AI-stream calls during one mission, and the server-side Token-accounting behavior is outside the sanitized source bundle. Accordingly, this manual does not claim a fixed total Token charge for an entire Browser Control mission.

Most importantly, Browser Control's verified autonomous capability is a research workflow:

Search → Navigate → Read → Analyze → Synthesize

It is not source-verified as a general robotic Browser capable of logging into arbitrary accounts, entering passwords, completing purchases, submitting arbitrary forms, or executing transactions.

The recommended operating principle is:

Define a Focused Objective → Prioritize Reliable Sources → Launch the Agent → Watch the Research Process → Inspect the Underlying Pages → Verify Important Findings → Download the Report and Preserve Source Information

Write Your Comment