Pango Neuro blog thumbnail featuring 3D jewel badges representing Gem personas for ad operations

How to use Gems in Neuro for ad operations

Save the reporting rules you keep typing: which metrics to use, what to check, and how to write the result. A Neuro Gem keeps those instructions ready for the next task.

In Neuro, a Gem is an operating mode

Media buyers tend to ask Neuro the same handful of things: “Summarize last week’s performance,” “Find budget-cut candidates,” “Draft report copy for the client.” But even when the question is identical, the standard for a good answer changes every time. A response written for a client report and a response written for budget-change review shouldn’t come back in the same tone or format.

A Neuro Gem stores task instructions you can apply to chat. A weekly-report Gem might specify the audience and required metrics; a budget-review Gem might request before-and-after values and risks to check. Test the output against those instructions after saving them.

  1. In the chat input box, open the Gems menu and click Create new Gem.
  2. Name it after a single task. Names like Weekly performance report, Budget change review, and Creative fatigue review work well because anyone gets them at a glance.
  3. For save location, choose Workspace shared if it’s a standard the whole team will use, or My Gem if it’s a personal workflow.
  4. Under Guidelines, spell out the role, the data to check, the order of analysis, the actions it must never execute, and the output format.
  5. Select a Gem in chat, then ask away as usual. The same question gets read through the lens of whichever Gem you picked.
  6. If answers keep missing the mark, don’t pile more onto your question—update the Gem’s guidelines instead. For recurring work, the standard belongs in the Gem, not in every prompt.
You select Gems from the tools menu in the chat input box. Pick a task-specific Gem and the same question gets read through that Gem’s rules.Tap or click to zoom and view the full screen

Five Gems worth starting with

You don’t need to turn every task into a Gem on day one. Start with the work that comes up most often and where inconsistent standards quickly drive up your operating costs.

Keep personal Gems separate from workspace-shared Gems and you can manage individual workflows and team-wide standards side by side.Tap or click to zoom and view the full screen
GemWhat to hand off to NeuroExample opening question
Weekly performance report GemSummarize the key changes across connected ad accounts, likely causes, and next steps, formatted for client reportingCompare the last 7 days with the prior 7 days and write it up as a draft summary to send to the client

Budget review GemSurface budget increase and decrease candidates, then build approval cards that lay out the evidence and risks for approversFind candidates to scale next week’s budget up or down—don’t execute, just package them as approval cards

Creative fatigue review GemRead CTR, frequency, conversion rate, and landing-message alignment together to shortlist creatives to refreshBreak down campaigns showing signs of creative fatigue over the last 14 days by likely cause

Client playbook GemApply a specific brand’s banned phrasing, reporting tone, KPI priorities, and budget-change rulesUsing this client’s standards, flag any absolute claims that should come out of this week’s report

New account owner onboarding GemWalk through account structure, recent change history, recurring issues, and what to check nextExplain this workspace’s ad account structure and the top current risks a new owner should review first

All five play to what Neuro does best. Ad platform data gets pulled through MCP tools, brand context comes from the workspace, and any recommendation that would change a live account stops in a format a human can review first.

Write Gem guidelines like an ops doc

A Gem whose guidelines stop at “You are a marketing expert” is close to useless. An ad operations Gem should read more like an ops manual than a character sheet. Spell out the order in which the AI reads data, where it has to stop, and the format its answer should take.

In Gem guidelines, spelling out the decision flow and execution boundaries matters more than describing the role itself.Tap or click to zoom and view the full screen
Guideline fieldWhat to writeExample
RoleWhose work you’re supporting, and on what taskYou’re the performance lead’s assistant analyst, and you assemble the evidence before any budget change
Data to checkWhich ad data and context to look at firstStart with campaign performance and recent change history in Google Ads, Meta Ads, and Naver Ads
Order of analysisThe review sequence to follow before drawing a conclusionWork in this order: goals and conversion definitions, campaign structure, budget pacing, conversion quality, then creative signals
Execution boundariesActions the AI must never carry out on its ownNever change budgets, bids, or campaign status directly—only propose them as approval cards
Output formatAn answer structure the team can review at a glanceLay out likely causes, ruled-out causes, supporting metrics, risks to check, and next steps in a table

Test the saved Gem on one real weekly report. If it misses a metric you always need, update the Gem. If a detail matters only this week, add it in chat. Judge the instructions by the results, not by how short your prompt becomes.

Sources

Related posts