SKU Manager: Troubleshooting & FAQ

Quick answers to common questions and issues

Start Here.

Most “it’s not working” reports come down to one of four things: the filter isn’t enabled, the AI server isn’t running, Send pictures is unticked, or billing isn’t active on the API account. The sections below walk through them.

Nothing Showing in the AI Panel #

You do not need to restart the app after a change. New searches, ticked or unticked searches, and profile and script edits take effect while the app runs.

Work through these in order — each one is a real case we’ve seen:

Is the AI Sku Analysis panel visible? View → Panels if not.
Is your filter enabled? Open Home → Filters and turn on its Enabled switch. A new filter starts switched off.
Is the filter’s action Apply AI Prompt, with your profile selected?
Is the AI server running? If the panel says AI SKU Manager Server is Not Running, click Data → Ai → Start AI Server.
Is the feed Started, and does your search actually match the filter’s condition? The analysis only runs on listings the filter catches.
Panel says No Matching AI Filter? No filter with Apply AI Prompt caught that listing — create or enable the filter (the panel lists the five steps).
Rows say Analyzed with errors in the Current AI Status column? The AI request ended without a usable answer. Check your API key and billing, then right-click the row → Refresh AI analysis.
Rows read Not analyzed? With Analyze new listings only selected, the first batch stays that way until you click a row.

AI analysis runs only on listings a filter catches. The filter’s Action must be Apply AI Prompt, with your profile selected. A new filter starts switched off, so turn on its Enabled switch in the Filters list.

With Analyze new listings only selected, the first batch a search pulls when you press Start stays Not analyzed, except the row you have selected, which is analyzed. Grid → Initial Results Max sets the size of that batch. Click any other row in that batch to analyze it. Rows found later are analyzed as they arrive, and each one reads Not analyzed, then Analyzing…, then Analyzed.

The Current AI Status column has five states. Not analyzed means no analysis has run. Analyzing… means a request is running. Analyzed means a result is saved. Outdated means the result is older than Keep results (days), or the profile, prompt or model has changed. Analyzed with errors means the request ended without a usable answer.

If a row reads Analyzed with errors, check that your API key is right and billing is active on your provider account. Then right-click the row and choose Refresh AI analysis. A row that no filter catches does not show this status. It stays Not analyzed and the panel shows No Matching AI Filter. No Matching AI Filter in the panel means no enabled Apply AI Prompt filter caught this listing.

Stopping a server does not stop the feed. New rows can arrive in batches after the first batch.

No Filter, No Analysis.

The setup wizard does not create the filter — it’s a separate step in Home → Filters. If you finished the wizard and nothing has ever run, this is almost certainly why. See Create the Filter in the Quick Start Guide.

Is My Filter Actually Triggering? #

Not sure whether your filter matches anything? Test it visually:

Load some search results first.
Go to Home → Filters and edit your filter.
Change the Action from Apply AI Prompt to Format rows, pick a BackColor under Format style, and click Ok.
Look at your results — the highlighted rows are exactly the listings the AI would analyze.
Change the action back to Apply AI Prompt when you’re done.

The Analysis Ignores the Photos #

If defect calls look blind to obvious photo damage, or the analysis never mentions what’s visible in the images, check that Send pictures is ticked on the Fields & Columns tab. Then check the model.

gpt-6-luna reads listing photos. In Custom mode the list shows only models that accept images. Send pictures and Send description are under Send Prompt Fields on the Fields & Columns tab. Both are ticked by default.

Open Data → Ai → AI Settings (click Stop Service [Edit Configuration] first if the server is running — the configuration is locked while it runs), check the Model dropdown on the AI Configuration tab, and save with Start Service [Save Configuration] if you change it.

AI Column Problems #

Extra Columns I Never Asked For #

The column list is auto-detected from your prompt’s JSON and includes every key it finds — including junk. Open your profile → Fields & Columns → untick anything that isn’t a real column. Keep only the ones you defined under ## AI COLUMN CONFIGURATION.

A Column is Blank or Missing #

The column must be a key in your prompt’s JSON example, have exact values in ## AI COLUMN CONFIGURATION, and be ticked under User-Defined Custom Columns (Results).
Give every column an Unknown fallback so it’s never blank, and keep values exact — Yes, not yes or Y. The grid sorts and filters on them verbatim.
Your new column appears under Detected — not selected. Tick it.

The app finds your columns by reading the JSON keys in your prompt’s example output, such as "Can Return": "Yes". A name that is not a JSON key there is not listed. Open the Fields & Columns tab, or click the Auto Detect Custom Columns icon at the top of the columns panel, and the list reads the prompt again.

Template Showing Raw Code #

Check the Display Template contains valid HTML and was actually saved.
Check the template’s placeholder names match your prompt’s JSON fields — the assistant that wrote your prompt keeps the two in sync, so if you edited one by hand, that’s the first suspect.
Paste the whole template again from your master file. Never hand-edit inside the box.

AI Analysis Takes Too Long #

Analysis typically takes a few seconds per listing after it arrives — reading photos is the slow part. If it’s consistently slow:

Trim your prompt to what actually matters for the buy decision.
Images are the costly part of a call. If photos do not affect your decision, untick Send pictures on the Fields & Columns tab.
Click Feedback Trace on the AI panel and take the saved zip to your AI project: “This is taking longer than expected. Can we reorganize the prompt for speed based on what’s most critical?”

API Provider Issues #

“Rate Limited” or Throttling Errors #

New API accounts are sometimes throttled at first — check your email for verification requests from the provider. Usually resolves within 24–48 hours.

Billing or Authentication Errors #

Verify billing is active on your API account — this is the #1 issue people hit.
Check the API key is complete, with no missing characters. Test it in the provider’s dashboard.
Check your usage in the provider’s dashboard after a few days to see actual spend.

A Change Doesn’t Take Effect #

While the server runs, the settings are locked. Click Stop Service [Edit Configuration] to edit, then Start Service [Save Configuration] to save.

Click Stop Service [Edit Configuration] first. While the server runs the configuration is locked — buttons are greyed and checkboxes won’t tick.
Re-paste the whole prompt or template from your master text file — don’t hand-edit in the box.
Save with Start Service [Save Configuration] — that button is the save; there is no separate save button.
If a row reads Outdated, click the refresh icon in its Current AI Status cell to analyze it again. If you changed only the template, the row still reads Analyzed. Click another row that reads Analyzed, then click this row again to see the new template. Neither click runs a new analysis.

After you change the prompt or model, rows analyzed under the old settings read Outdated. To analyze one again, click the refresh icon in its Current AI Status cell, or click the row if it is not the selected one. This is paid, and the app does not ask first. To re-run a row that reads Analyzed, right-click it and choose Refresh AI analysis. The app asks first.

Frequently Asked Questions #

General #

What Model Should I Use? #

Model	Notes
`gpt-6-luna`	Recommended. Our guides use it.
`gpt-6-sol`	Under More models.
`gpt-5.6-terra`	Under More models.

Our guides use gpt-6-luna. It is the Recommended OpenAI model in the app and it reads listing photos. The model dropdown shows each model’s current price.

You pick the model from a dropdown in the profile’s AI Configuration tab — there’s nothing to type or format. OpenAI is the path our guides walk, but the app also supports Google (Gemini), Anthropic (Claude) and xAI (Grok) — pick your provider, paste that provider’s API key, and each model dropdown marks its own Recommended entry: gemini-flash-lite-latest for Google, gpt-6-luna for OpenAI, claude-haiku-4-5 for Anthropic and grok-4.7 for xAI.

Standard shows a short list for four providers: Google (Gemini), OpenAI (ChatGPT), Anthropic (Claude) and xAI (Grok). Custom shows the full catalog of models that accept images. A profile already set to a model outside the Standard list stays on Custom, so it keeps working.

How Much Does it Cost to Run? #

Usually cents per listing. The model dropdown shows each model’s pricing, and your provider’s billing dashboard shows actual usage after a couple of days. On the Data tab leave Analyze new listings only selected (the default). Rows already in the grid are then not analyzed when the server starts, except the row you have selected if it reads Not analyzed. Clicking a Not analyzed row runs a paid analysis with no question. With Analyze initially loaded listings selected, starting the AI server analyzes every Not analyzed row a filter catches, including rows found while the server was stopped. With the server already running, pressing Start also analyzes the first batch a search pulls. Each one is a paid call. When you start the server, the app asks first if the estimate is over $10. Results are kept for the number of days set in Keep results (days) and they survive a restart.

Can the AI Do Calculations and Math? #

Yes. Pricing logic, profit calculations, quantity math and similar can all go in your prompt.

Working with Product Data #

How Many Products or Variants Can I include in My Prompt? #

Dozens to hundreds works well.
Thousands is too many — it slows processing and increases costs. For big lists, use Internal Endpoint mode instead: it matches listings against your own CSV locally, with no per-listing API cost.

Can I Use My Excel Price Sheet? #

Yes. When creating your prompt with Claude or ChatGPT, upload the spreadsheet, explain what each column contains, and the assistant builds the matching logic into your prompt. Works well for different models with different max prices, variants you buy vs. don’t, and condition-based pricing.

AI Columns vs. Display Template #

What’s the Difference? #

	Display Template	AI Columns
Where it shows	AI Sku Analysis panel	Results grid
Best for	Detailed analysis, explanations	Quick Yes/No decisions
Format	Full HTML with formatting	Short, exact values

Example: you only buy listings that accept returns. Add an AI Column called Can Return that outputs exactly Yes, No or Unknown — then sort or filter the grid on it and skip the No rows without opening a single listing.

Running Both Modes #

Can I use AI Analysis and Internal Endpoint at the same time? #

Yes. They are separate systems with separate servers — the Data tab has a Start button for each, and each renders into its own panel. A filter triggers AI analysis; Internal Endpoint needs no filter at all — your search terms are its scope.

Still Stuck? #

Check the basics: filter enabled? AI server running? Feed started? API billing active?
Use feedback traces: select the bad result, click the Feedback Trace link at the top right of the AI panel, rate it and describe what’s wrong. That saves one zip with a complete diagnostic snapshot — the data sent, the exact prompt, the AI’s answer, and the images — which you (or support) can work from. Open the folder with Data → Ai → Open AI Traces.
Contact us: Live Support at uBuyFirst.com, or su*****@*******st.com.

To report a wrong result, click the Feedback Trace link at the top right of the panel. Open your saved traces with Data → Ai → Open AI Traces.