OpenCode + AionUi: Full Desktop AI Agent to Replace Claude Cowork for Free

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: OpenCode + AionUi: Full Desktop AI Agent to Replace Claude Cowork for Free
- URL: https://www.youtube.com/watch?v=xOOUEx8XBDE
- Topic: Interfaces + Open Design
- My current learning frame: Install AionUi with OpenCode underneath, then run two parallel sessions at once (build a two-sheet expense tracker with a bar chart while a second session renames a desktop file) and inspect both outputs in the preview panel.
- Why this matters: New playlist item from AI Stack Engineer; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Open code is one of the better open source coding agents out right now. It runs in your terminal, it works with pretty much any model you want, and it doesn't lock you into a single company. So,..."
- 2:48 / Evidence 2: "part that matters most for this video, it auto detects the coding agents you already have installed and gives all of them a proper interface to work in. So, Open Claw, Hermes Agent, Claude Code, Code X, Gemini..."
- 4:38 / Evidence 3: "workspace. If you don't have it yet, you install it first through the Open Code site or its install script, and then Aion UI picks it up automatically the next time you open the app. You can also..."
- 6:28 / Evidence 4: "spreadsheet I can preview without ever leaving the window. While that runs, I can spin up a second task at the same time, and this is where the multi-agent side comes in. I'll have another Open Code session..."
- 8:02 / Evidence 5: "a monthly file cleanup running on a cron schedule without you sitting there. The app even keeps your system from sleeping while a task is active. So, when you put it all together, you've taken open code, a..."

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A UI critique sheet for judging whether an AI interface improves control.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Canvas -> Artifact -> Preview -> Feedback -> Iteration
   - 3 concrete examples that apply the video idea to real agentic work
   - 2 failure modes the video helps prevent
   - a checklist I can use the next time I run Codex or Claude
   - one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "OpenCode + AionUi: Full Desktop AI Agent to Replace Claude Cowork for Free", not a generic Interfaces + Open Design essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.