InputBuffer.io

Setting Up Buffers

InputBuffer routes incoming feedback into named buffers — automatically. You define what belongs in each buffer; the AI reads that definition and sorts every new input without you touching it. This guide walks you through creating your first buffer, writing effective routing instructions, and reviewing what the AI does with your inputs.

  1. 1

    Navigate to Buffers

    Open your organization dashboard and click Buffers in the left sidebar.

  2. 2

    Create your first buffer

    Click Add Buffer in the top right. Fill in the fields:

    • Name — a short label for this category. Examples: Bug Reports, Feature Requests, Billing, Performance.
    • Description (required) — one sentence explaining what this buffer is for. The AI uses this to decide what belongs here.
    • Routing Instructions (optional but recommended) — explicit rules for the AI. See Routing instructions below.

    Click Create Buffer. The buffer appears in your list.

    Buffers list with one buffer

  3. 3

    Submit inputs — the AI routes them automatically

    Once you have at least one buffer, every new input that arrives is analyzed by the AI classifier. It reads the input title and description, compares them against all of your buffers' names, descriptions, and routing instructions, and makes a routing decision.

    What happens to each input:

    • Confidence ≥ 80% — the input is automatically assigned to the matching buffer. No action required.
    • Confidence 50–80% — the input is flagged for your review. It appears on the Review page at /o/$orgSlug/review so you can confirm or reassign it.
    • Confidence below 50% — the input remains unclassified. You can assign it manually from the input detail page.

    When auto-create buffers is enabled, the AI can also suggest a new buffer if no existing one fits well. It will only do this when its confidence in the new buffer exceeds the buffer creation threshold (default 40%). All three thresholds are adjustable in Settings → AI Settings.

    When you're just starting out, aim for 3–5 buffers with clear, non-overlapping purposes. The AI routes best when each buffer has a distinct meaning. Overlapping buffers (e.g., "Bugs" and "App Bugs") lead to low confidence and more manual review.

  4. 4

    View inputs inside a buffer

    Click a buffer's name in the list to open its detail page. You'll see all inputs routed here, sorted newest first.

    Buffer detail page

    From here you can read individual inputs, add internal notes, and track how feedback in this category evolves over time.

Routing instructions

Routing instructions are the most direct way to control what the AI puts in a buffer. Write them as plain-English rules describing what belongs and — optionally — what does not.

Examples:

  • Route here only when the user reports a crash, error, or unexpected behavior.
  • Billing and payment issues only. Not for login problems or account setup.
  • Feature requests and suggestions for new functionality. Not for bugs.
  • Performance complaints: slowness, timeouts, loading delays. Not for errors.

Tips:

  • Use "only when" and "not for" — these exclusions matter as much as inclusions.
  • Mention keywords users actually write: "crash", "slow", "billing", "can't login".
  • Keep instructions to 1–3 sentences. Longer instructions don't improve accuracy.

If you leave routing instructions empty, the AI routes using the buffer's name and description alone. That works fine for clearly-named buffers. Add routing instructions when two buffers could plausibly match the same input.

Reviewing low-confidence classifications

When the AI's confidence falls between 50% and 80%, the input lands on the Review page instead of being auto-applied. Navigate to Review in the sidebar (or go to /o/$orgSlug/review) to see them.

Review page

For each item you'll see the AI's suggested buffer and its confidence score. You can:

  • Mark reviewed — accept the AI's routing decision.
  • Leave it for now and come back later.

Every correction you make is recorded and fed back into the AI's learning loop. Over time, the classifier improves for your specific content.

If you consistently see the same kind of input land in review, refine that buffer's routing instructions. Adding a targeted sentence usually moves those inputs from review into auto-apply.

AI-suggested buffers

As your inputs accumulate, the AI may suggest new buffers for patterns it notices that don't fit your existing categories. These appear at the top of the Buffers page under an AI suggested banner, shown as yellow draft cards.

Each draft shows:

  • The suggested buffer name
  • The AI's reason for suggesting it
  • How many inputs are already associated with it

You have two options:

  • Approve — the draft becomes an active buffer and starts receiving new inputs.
  • Delete — discards the suggestion. Inputs associated with it become unclassified.

AI-suggested buffers also appear on the Review page if you prefer to manage all pending items in one place.

Editing a buffer

To change a buffer's name, description, or routing instructions, click the pencil icon on the right side of any buffer row in the list. This opens an edit modal with the same fields as creation, plus an icon picker.

Changes take effect immediately for new inputs. Inputs already routed to the buffer are not re-classified.

To adjust when the AI auto-applies vs. flags for review, go to Settings → AI Settings and change the auto-apply threshold (default 80%) or review threshold (default 50%).

Next steps

  • Feedback Widget — collect feedback directly from your web app or docs site with no backend required
  • API Reference — full reference for all API endpoints, parameters, and response schemas