What will you build with it?
One desktop app for work that would otherwise take several specialised tools, a lot of copy-pasting, or a lot of repetition. AgentDock puts the AI you already use to work on it, with you approving what matters.
The examples below are things you can ask for, not projects we completed or results we promise. The one recorded run is marked and linked to its evidence. AgentDock helps you do the work; it does not replace the people who are good at it.
- 01
Websites
Point an agent at a folder, describe the site, review each change before it lands, and keep going until it ships.
Try asking for: A five-page site for a local business: layout, copy, forms and a deploy script.
- Claude Code
- Codex
- Antigravity
- 02
Full-stack applications
Uses ProPlan the work, split it across agents, and read what each one changed. With Pro, AIgency plans it once and runs the independent parts side by side.
Try asking for: A booking app with accounts, a database, payments and tests.
- AIgency
- Worktrees
- Change review
- 03
Desktop software
Keep the code, the terminal and the agents in one place, and let an agent run builds and read the failures.
Try asking for: A cross-platform desktop tool with packaging scripts and an auto-update check.
- Terminal
- Approvals
- 04
Debugging and code maintenance
Hand a failing test or a stack trace to an agent, review the diff, revert in one click if it's wrong, and hand the conversation to another agent for a second opinion.
Try asking for: Find why a nightly job fails, fix it, and upgrade the dependency that caused it.
- Handoff
- Change review
- Terminal
- 05
Product prototyping
Describe the product, compare how different agents would build it, and keep the version you like.
Try asking for: Three clickable takes on the same onboarding flow, in a day.
- Compare
- Projects
- 06
Research
Uses ProGive agents a question and sources. With Pro, the Agent Browser reads real sites in a browser you can watch, and the findings come back as a document.
Try asking for: A briefing on a market's main suppliers, with each claim linked to its page.
- Agent Browser
- Attachments
- 07
Testing
Uses ProAgents write the tests, run them, and report what failed. With Pro, an agent can also click through the running app in the Agent Browser.
Try asking for: A regression suite for checkout, plus a written report of what broke.
- Terminal
- Agent Browser
- 08
Business automation
Uses ProSchedule a prompt to run daily or weekly, with a calendar of what ran and what it found, and approvals where you want a person in the loop.
Try asking for: Every Monday: summarise last week's support tickets and draft the replies for review.
- Automations
- Approvals
- 09
Browser-assisted work
Uses ProThe Agent Browser gives an agent a real browser to read and operate, alongside you, with the page in view while it works.
Try asking for: Fill a supplier form from a spreadsheet, stopping at the final submit for you to approve.
- Agent Browser
- 10
Content production
Uses ProGenerate images and video with your own Sarness server for free. Pro adds production workflows: batch runs, multi-step pipelines and agents that coordinate the whole job.
Try asking for: A product teaser: script, voiceover, stills and a cut, kept with the campaign files.
- Sarness generation
- Creative Suite
- 11
Multi-agent delivery
Uses ProAIgency plans a goal, assigns each task to the agent that suits it, runs independent tasks side by side, and has another agent check the result before it reports.
Try asking for: A command-line to-do app, planned in six tasks across two agents, built and verified. This is a real, recorded run.
- AIgency
- Verification