Think-Act task automation File, browser, and app automation

Do it once with Think-Act. Hand off the repeat runs.

Every Friday, new product photos land in the same folder. Ask the agent to match filenames to your product codes, copy matches into the right folders, and leave anything it can’t identify alone. Check the first batch before scheduling another.

Windows 10 and 11 now. Mac release planned.

The Agent Workspace shows the task prompt and response.

Source

Supply context

Run

Use available tools

Activity

Keep work visible

Review

Check the result

The Agent Workspace shows the task prompt and response.
The Agent Workspace shows the task prompt and response.
The Agent Workspace shows the task prompt and response.
Good first automations

Pick a routine with a clear finish

A sorted batch of photos, a supplier page open on the right item, or a project folder ready for a new client: pick something you can check at a glance.

Set up the next client project

Create the standard folders and copy in the kickoff material. Leave the originals alone.

Check a supplier’s catalog

Give it three part numbers. Ask it to open the matching listings and flag missing stock or lead times.

Match incoming receipts

Read order numbers from receipt images, match them to purchase orders, and set uncertain matches aside for review.

Document a recurring process

Record a short walkthrough, then use your notes to draft and test a checklist.

Why these make good first workflows

Low consequence Clear input Clear result Easy to check Worth repeating
Before the run

Tell the agent what starts and ends the job

For product photos, name the incoming folder, supply the product codes, and specify “copy, don’t move.” Ask it to list the files it couldn’t match.

Example task brief

“Match these five photos to the product codes. Create any missing product folders and copy each match there. Leave the originals alone and show me the filenames you couldn’t match.”

Input

What should it work from?

Output

What should it produce?

Limits

What should stay untouched?

Check

What does “done” look like?

Success criteria are optional. Add them when a measurable finish condition helps. They help define “done”; they do not replace reviewing the source.

  1. Choose a test batch

    Give it five photos, the product codes, and a destination. Ask to see the proposed matches first.

  2. Run with available, enabled tools

    Think-Act can use the capabilities exposed to the run, subject to permissions and policy. A missing connector should be reported, not simulated.

  3. Check the result and activity

    Compare the output with the original material and inspect relevant activity. Correct the brief or method when something important is missed.

  4. Save only what proves reliable

    Preserve the reviewed method as a local Skill, including prerequisites, required tools, boundaries, and the expected result.

Desktop Agent workspace

Watch a first run before repeating it

Review the tool activity and check the destination folders. A Skill saves the instructions; a scheduled task tells Think-Act when to run them.

The Agent Workspace shows the task prompt and response.
The Agent Workspace shows the task prompt and response.
A specific starting point
Describe the task and attach relevant material. Add optional success criteria when there is a clear completion condition.
An inspectable run
Know which tools are available, review recorded activity, and respond to approval requests where policy requires them.
A method worth keeping
Once the process proves reliable, preserve its instructions, prerequisites, and expected result as a reusable local Skill.
Document automation

Turn invoice data into a weekly table

Extract supplier, due date, and total. Ask the agent to flag unreadable fields rather than fill them in.

Extract the fields the task needs

Ask for specific names, dates, amounts, or line items. Flag unclear source content so it remains visible during review.

Prepare a consistent output

Organize the extracted content into a table, CSV text, summary, or checklist with a structure you can inspect.

Draft the follow-up

Use the reviewed information to prepare questions, a reply, or next steps. Sending or submitting it requires an appropriate tool and permission.

OCR and AI interpretation can miss detail or context. Check important names, dates, totals, clauses, amounts, and obligations against the source.

The document workspace shows the source and extracted text.

Source

Original document

Extract

Requested fields

Prepare

Useful structure

Review

Verify source

The document workspace shows the source and extracted text.
Screen recording to SOP

Document the manual steps first

Record a short walkthrough. Use your notes to write a checklist and keep the clip as a reference for exceptions.

  1. Record the process

    Capture the relevant steps while you perform them.

  2. Generate steps

    Prepare an SOP or checklist from the recording.

  3. Review and edit

    Correct omissions and add prerequisites or warnings.

  4. Save as a Skill

    Keep the tested method as local workflow guidance.

  5. Reuse later

    Check that the next task still meets its prerequisites.

Screen Recorder includes capture controls and audio options.
Screen Recorder includes capture controls and audio options.

Useful beyond the next run

Turn a walkthrough into an SOP, checklist, bug report, or tutorial draft. Review it for missing decisions, setup steps, and exceptions before sharing or reusing it.

A Skill preserves workflow guidance

Skills are reusable local instructions or playbooks. Capture the proven process, its prerequisites, and the expected result.

A Skill does not supply a missing capability. Any required tool must still be available, trusted, enabled, and permitted for the run.

Test first. Save second. Reuse after the behavior is understood.

Tools and connectors

Add a connector only for missing access

The agent already has file and browser tools. Use an MCP connector if the task needs a compatible external service.

An available tool

An enabled, healthy tool can expose specific capabilities to the run. Think-Act may use them according to configured permissions and policy.

For example

Read a permitted file through an available filesystem capability.

A consequential action

File changes, message sending, and external writes need appropriate tool access. Configured policy may require approval before the action continues.

For example

Preparing a reply is different from sending it through an enabled messaging capability.

A missing capability

Think-Act should identify the missing tool and explain what the task needs. It can still prepare useful content, but it should not claim the external action happened.

For example

Draft an issue from a bug report while making clear that it has not been submitted.

Check the capabilities available to your setup

Categories can include filesystem, browser, database, GitHub, app APIs, and local MCP. These are capability categories, not a promise that every connector is installed or available.

Third-party local MCP packages may execute code on your device. PixLab does not control arbitrary packages. Review their sources before installation and enable only software you trust.

Review & approve

Preview changes before applying them

For a rename job, request a table of old and new names first. Set tool permissions to match what you want the agent to do.

Action policy

ALLOW ASK BLOCK
ALLOW
A trusted supported action can continue according to policy.
ASK
Pause for review before the gated action continues.
BLOCK
Prevent the action from being used by the workflow.

What to review around a consequential action

  • Check the proposed action and target

    Read what will change, which file or system is involved, and whether it matches the task's boundaries.

  • Approve or deny when asked

    Approve a gated action only when the proposal is understood. Deny it if the target, scope, or result is wrong.

  • Inspect what happened afterward

    Review supported activity and the actual output. A completed run still needs to be checked against the request.

  • Recover only where supported

    Use available recovery mechanisms when the workflow supports them. Do not assume an external action can be undone.

  • Save the workflow after testing

    Preserve the checks, prerequisites, and approval expectations that made the method reliable.

Automation FAQ

Desktop automation questions

Practical limits, approvals, and how to reuse instructions safely.

Can Think-Act interact with any desktop application automatically?

Not every app. Think-Act can use supported desktop and browser controls; locked screens, missing tools, and permissions can prevent an action.

Can Think-Act ask before a write or external action?

Yes. The security policy decides when to ask. You can also request a proposed change first and review it before asking the agent to apply it.

Should I automate consequential work first?

Start with a task you can check, like comparing two files. Leave payments, deletions, and publishing out of a first run.

What happens if the workflow needs a connector that is missing?

The agent can't use a missing connector. Add a trusted one if the job needs it, or ask for a local draft instead.

When should I save a workflow as a Skill?

Save it when you have tried the steps, checked the result, and expect to repeat the job with different inputs.

Do I need the Desktop Agent for every repeated task?

No. Use Writing Assist for a rewrite or OCR for a scan. Choose the agent when the result takes several steps.

Is there a free version I can try?

Yes. The free allowance lets you try a task with your own files. See current plan options.

Free to install · Windows & macOS

Try your routine on one small batch

Start with five files. Preview where they belong, ask the agent to copy them, and open the destination to see whether the routine worked.

Windows macOS Available tools only Controlled actions