See ASB in action
Watch: fetch Amazon iPhone prices into a CSV file — recorded in ASB, compiled into a reusable skill, zero manual steps.
Local-first AI automation platform
visualbuild.me · Automation Skill Builder
Use AI to capture and structure your workflows. What runs is pure logic — deterministic, local-first, and reusable across every assistant.
Design time
Watch: fetch Amazon iPhone prices into a CSV file — recorded in ASB, compiled into a reusable skill, zero manual steps.
Compatible with
20 min
A 12-step SAP data export — recorded, packaged, and invokable in under 20 minutes
3 run modes
Standalone executables, AI-callable skills, and scheduled jobs — one build, same execution
0 cloud calls
Core automation runs fully offline — no API key needed at runtime
WHY ASB
Models reason about tasks, yet they cannot click, type, or drive your desktop without a bridge.
Classic RPA is heavy to build, fragile when UI changes, and expensive to maintain.
Package workflows into AI-callable skills through MCP — the same path as Cursor and other assistants.
CORE CAPABILITIES
Eight capabilities, one runtime. Build once, reuse across every assistant.
Control and operate desktop applications.
Automate web tasks and extract data.
Connect services with structured requests.
Extract text and structure from screens and files.
Expose skills to assistants via MCP.
Version and reuse automations as skills.
Run on your machine with local-first privacy.
Chain steps into reliable automations.
TYPICAL SCENARIOS
FINANCE
Generate reports and data dashboards
ERP
Automated ERP data processing
ACCOUNTING
Extract and process invoice data
DATA
Collect website data and content
COMMS
Automated email workflows
RPA
Reproduce and monitor RPA flows
From recording to MCP exposure — every stage visible in the UI.
Local-first
Execution stays on your hardware.
Traceability
Logs and records for review.
Allowlists
Tighten upstream AI proxy access.
Works offline
Core automation without mandatory cloud.
Security boundaries
Guardrails for vision paths and tools.
Version 0.9.0 · Windows installer (.exe), macOS disk image (.dmg), or ZIP archives
SUBSCRIPTION LICENSE
Each time an AI assistant invokes a skill via MCP, that counts as 1 call. A typical automation run uses around 20–30 calls.
Start free — no credit card needed. Every account gets 1,000 calls per month at no cost, resetting on the 1st of each month (your local time). When you're ready to do more, upgrade any time.
FREE
$0
1,000 calls / month
≈ 33–50 skill runs / month
Get startedSTARTER
$9 / mo
5,000 calls / month
≈ 165–250 skill runs / month
PRO
$29 / mo
20,000 calls / month
≈ 665–1,000 skill runs / month
GROWTH
$99 / mo
100,000 calls / month
≈ 3,300–5,000 skill runs / month
ENTERPRISE
Custom
Volume · SLA · deployment & integrations
Contact usTypical run: 20–30 calls. A skill with loops or retries may use more.
Add-on: +1,000 calls one-time for $2 · All prices USD before tax
Short answers; the manual remains authoritative for operational detail.
No. It is designed primarily as a self-hosted application you run on your infrastructure or workstation. You control networking, TLS, and who can reach the service.
No. Core features work over the web UI and HTTP API. MCP and integration with the rich skill ecosystem on the Claude community are optional when you want assistants or a skill runtime to consume packaged capabilities. We fully support that path: follow the user manual to install the skills you prefer, use the product’s built-in security checks to validate them, and execute with confidence.
No — it amplifies what your team can do. Think of it as a capable assistant that drafts and suggests; your team reviews, decides, and owns the outcome.
Sensitive data flows depend on your configuration: local execution, which models you call, and which external services you enable. Run data-protection assessments before processing regulated data. With this product’s design, interactions are auditable and can be reviewed in a visual way—helping security teams verify behavior instead of working blind.
Many automation tasks touch the desktop, filesystem, or internal APIs. Keeping execution close to the environment reduces latency and can simplify compliance—at the cost of you maintaining the runtime.
Yes—see the Visual Studio Marketplace listing or download a VSIX. The Automation Skill Builder app must still run locally; extensions only embed the UI. A Microsoft Office add-in remains under evaluation.
Vision stacks often download models on first use. Expect a longer cold start; subsequent runs are typically faster. See the manual for warmup and skip flags.
Community users can ask questions in the public forum — response times vary. If your team needs reliable support with a guaranteed response, check out our professional plan.
See the user manual for OS support and optional Python / Node.js prerequisites.
Two lanes—so expectations stay clear whether you are evaluating, self-hosting, or running under a commercial agreement.
For organizations that need onboarding, priority help, custom integrations, security review assistance, or deployment hardening, commercial support may be available from the maintainer or partners.
Scope, channels, and SLAs are defined in a separate agreement—not on this marketing page. Contact your vendor or project owner for entitlement and pricing.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。