Smart Loop FAQs

A typical AI "workflow" often looks like this:

• the request is in a chat tab
• the source material is in your notes
• the next step is in your head
• the answer is somewhere else
• returning to the work means hoping AI retrieves the right context

That is not effective delegation.

That is fragmented work that prevents real progress.

Smart Loop gives delegated work a durable home. A single note holds the assignment, context, thread or result, review, next step, and deliverable.

Smart Loop is a workflow.

It is the pattern of making the work clear, sending the note with context, and improving the note from the result.

Smart Plugins make that workflow easier inside Obsidian, but Smart Loop is not another plug-in to install.

No.

You can use your preferred chat provider, model workspace, agent, or AI tool.

Smart Chat helps when you want the thread link, active/done state, or returned result attached to the note inside Obsidian.

It does not replace the chat tool you already use.

Smart Loop doesn't care which provider you use. Use your preferred chat provider, model workspace, agent, or AI tool.

The best providers provide a URL to each chat thread you delegate work to so that it can be referenced from the outcome note.

Smart Loop does not require you to replace the AI tool you already use.

You can delegate through ChatGPT, Claude, Gemini, a local model, an agent, a model project, or another AI workspace.

Smart Chat helps when you want continuity inside Obsidian. A thread can be saved into the same note. A thread can also be marked active or done to make managing threads easier.

Using Smart Loop does not mean AI automatically rewrites your notes.

AI should not work ON your notes.

AI should work IN your notes.

Working inside the note creates leverage:

• package context
• delegate to AI
• review output
• keep drafts and threads visible

Manually improving the trusted note protects judgment. Clarify the outcome by hand. Delegate the work to AI. Compound progress by maintaining trust through careful note improvements that lead to better delegated work.

A note stays trusted when you decide what gets included.

See the Smart Loop simple demo.

Agents, projects, and other model-owned workspaces can be useful execution surfaces.

Smart Loop and these surfaces are not mutually exclusive.

Smart Loop gives them a better starting point and a better return point.

The note remains the place where the outcome, context, review, and deliverable can be managed.

Every model, agent, project, or chat surface can start from the same human-readable note.

Start with a single note that already represents real work.

Good examples include a draft, project, decision, meeting, research question, support issue, or page you actually care about.

The note should be clear enough that you can judge whether the AI answer helped.

Start with plain sections:

• outcome
• context
• chat or thread
• review
• next step
• deliverable

You can keep it simple. The point is that the work has a durable home.

Clarify -> Delegate -> Compound is Smart Loop reduced into the key moves.

After the behavior makes sense, the short name is:

Clarify -> Delegate -> Compound

Clarify means the work is clear enough to judge.

Delegate means AI receives the assignment with useful context.

Compound means the result improves the note, the next pass, or the final deliverable.

Review checks the output.

Compound improves the next run.

Done is when the output matches your understanding, intent, and expectations.

You can complete your first Smart Loop in minutes.

1. Clarify what done looks like: write 3-5 lines in an outcome note.
2. Delegate the work by copy and pasting the outcome note into chat.
3. Compound by improving the note based on the response.

The size of the outcome will influence how many iterations of the loop are necessary. Going from idea to outcome will continue to get faster if your notes remain trusted and operate multiple loops at the same time.

You know it worked when the note where the work lives improves from a reviewed result.

A single section is enough.

Improve the outcome, constraints, context, review, next step, or deliverable.

When the note is better, the next AI request starts from a better place.

Close the loop before moving on.

A clever response is not the finish line. And a bad response can still create real progress. Before moving on, use the review process to improve the note.

Even a weak answer can help.

If the answer is generic, the note may need a clearer outcome, better constraints, cleaner context, or a more specific next action.

Improve the note first. Then delegate again from the better note.

Improve the starting note before copying more context.

A generic answer often means the note needs a clearer outcome, stronger constraints, cleaner context, or a more specific next action.

Then ask again from the better note.

Start with the smallest useful context.

Context is a scope dial, not a dumping ground.

Start with the note that owns the assignment. Expand only when linked support matters or the answer names a real missing source.

Yes.

Agents, Projects, and model-owned workspaces can be useful execution surfaces.

Smart Loop gives them a better starting point and a better return point: the note keeps the outcome, context, review, and deliverable inspectable by the user.

Smart Loop is a workflow.

Smart Plugins make it practical inside Obsidian because notes, links, context, and thread state can live together.

The broader idea is portable: AI work improves when the assignment, context, thread, review, and deliverable have a durable home.

No.

• external context sources
  • ex. from code repositories
• finer context control
  • ex. include folders and exclude specific files in folders
• vault visualization
  • ex. creating context packages based on clusters
• performance
  • ex. large vaults can benefit from improved performance in the Connections and Lookup features

No. AI output can work inside a note before it earns a place in the trusted note.

You decide what gets promoted after review.

Open a single note that already matters.

Write the outcome.

Add one constraint that would make an insufficient outcome obvious.

Copy the note or the smallest useful context.

Ask your AI tool for one outcome-focused answer.

Return to the note, review the answer, and improve one trusted section.

Smart Loop is not another agentic system that takes more time to set up than it saves.

It is not more prompting.

It is not dumping your whole vault into context.

It is not replacing every chat tool or agent workspace.

It is not asking AI to overwrite your trusted notes.

It is a durable workflow around AI work, so the thread, context, next step, and latest draft can return to the note for review.

Pick a single desired outcome and create a note to manage the work (the outcome note).

1. Define what done looks like.
2. Attach useful context (use Smart Context).
3. Copy the note and context to the clipboard (use Smart Context) & paste it into the chat to delegate the work.
4. Save a link to the thread in the note (use Smart Chat).
5. Review the response against what done looks like.

Review either reveals a usable result or insights to improve the outcome note for a better next delegation. Real progress can be made on every iteration.

You have not finished a Smart Loop just because you found a note, copied context, saved a thread, or received an AI answer.

Those are useful steps. They are not the finish line.

The loop finishes when the review process improves the outcome note or reveals a usable deliverable.

When the note is better, the next AI request starts better. The outcome note becomes a trusted resource for improving delegation.

Read the main Smart Loop page for the workflow.

Use Smart Connections when you need related notes from the current note.

Use Smart Context when you need to send controlled context to AI.

Use Smart Chat when the thread should stay attached to the note.