Skip to content
Faisal Mahmud TusherDigital marketing, SEO & analytics
with Faisal Tusher

Collection

AI in Marketing Troubleshooting

AI problems in marketing arrive as symptoms: a draft that cites a study nobody can find, a customer assistant quoting a guarantee that has changed, customers who keep asking a support assistant for a person, a generated image rejected or labelled by an ad platform, a report figure nobody can reproduce, an automated flow that sent the wrong offer to a segment, customer lists or transcripts pasted into an AI tool, output that used to pass review now needing heavy editing, and AI tools used every day while deadlines and workload look the same as before. Each page here starts from one of those symptoms, separates the causes in a diagnosis table and gives the check, fix, verification and prevention habit for each, linking the foundations, applications and governance guides that teach the method.

Looking for how to use this library? Read the guide below the list.

All 9 pages in this collection

How these pages work

Most diagnoses here begin by collecting the failures, because one wrong answer proves little and a pattern names the layer. An accuracy problem starts with a log of recent inventions and the source each one should have come from; a wrong-answer problem starts with a sample of wrong answers traced to the passage each one cited; an unresolved-question problem starts with the conversations that ended in a request for a person; a creative problem starts with the rejection exactly as the platform gave it; a reporting problem starts by rebuilding the disputed figure from the source data; an automation problem starts with the run that sent the messages, paused; a quality problem starts by dating the change from the review log; and a data problem starts by telling the data protection owner, then listing every case. Once the fault is visible, a diagnosis table lists what you can see, the check that confirms each cause and the fix. Each cause then gets a short section with the fix, a way to verify it and the habit that prevents it, followed by a routine that keeps the whole set under watch.

The pages assume the methods are taught elsewhere and link to them. Why a model produces likely text rather than checked facts is in the guide to how language models generate text; how Grounding works and how a tool finds passages in a library is in the grounding and retrieval guide; building a test set and rerunning it after every change is in the guide to testing prompts and models; and review tiers, fact checks and claim checks are in the accuracy and review workflows guide.

Find the page for your symptom

Choose the row that matches what you are seeing. Diagnosis pages in this section are also listed beneath this introduction automatically; the last three rows send situations that belong somewhere else to the page that owns them.

What you are seeingStart withBackground
Drafts or published pages contain figures, quotes, awards or features that do not existAI-written content contains invented factsAccuracy and review workflows
A customer-facing assistant quotes an old policy, the wrong plan or a price that has changedAI assistant giving customers wrong answersPreparing documents for an AI assistant
Customers keep asking the assistant for a person, repeat the question or give up and phone or email insteadAI assistant not resolving customer questionsAI in customer service
An ad platform rejected, labelled or removed a generated image, video or copy variantAI-generated ad creative rejectedAI for creative
A figure an AI tool produced cannot be reproduced by the person who checks itAI-generated report numbers do not matchAI for analysis and reporting
A workflow with an AI step sent an unapproved offer, a wrong name or a message to the wrong peopleAI automation sent the wrong messagesAI for marketing automation
Customer lists, transcripts or order histories have been pasted into an AI toolCustomer data pasted into AI toolsMinimising data before prompting
Output from a prompt or assistant that used to pass review now needs heavy editingAI output quality getting worseTesting prompts and models
The team uses AI tools every day, yet deadlines, output and workload look the same as beforeAI tools not saving timeMeasuring AI's impact on team output
An AI error has already reached customers and needs containing todayHandling an AI mistake that reached customersWriting an AI use policy
AI-assisted pages are live but do not rank or convertAI-written content not performingAI for content
You need to check one answer a tool gave before anyone relies on itFact-checking an AI answerPrompt patterns for marketing

Source, prompt, model, review or permission: decide which layer failed

Most symptoms in this section trace to one of five layers, and naming the layer first decides who fixes it. A source failure means the material the tool drew on was missing, stale or wrong: no sources supplied, superseded documents left in the library, a help centre that was out of date before the assistant read it. A prompt failure means the instruction never carried the audience, the material, the constraints or the rule to answer only from the library. A model failure means behaviour changed under a setup that used to work, through a new version, a vendor update or a prompt edit nobody retested. A review failure means a person read for fluency rather than tracing facts, or the gate before upload or sending was skipped. A permission failure means the tool was allowed to do more than its risk justified: an agent free to send or change records where a fixed workflow with an approval step was needed, or offers and legal copy left to the model instead of locked as rules.

The test is to ask what would have stopped the failure. If a correct source would have, it is the source; if the source was there and the tool ignored it, look at the prompt and the retrieval; if the same setup worked last month, look at what changed; if a person saw the output and passed it, look at the human review step; and if nobody saw it before customers did, look at permissions. The NIST AI Risk Management Framework, as the site's governance guides apply it, organises the same work into four functions, govern, map, measure and manage: name an owner, know where each use sits and what could go wrong, measure how it behaves, and change the setup on that evidence rather than on one bad answer. Every statement these pages make about what models and tools do is the one the foundations section makes.

When to review instead

A diagnosis page fixes one failure. When several of these symptoms arrive together, when nobody can say which uses of AI the team runs or who owns them, or when a new assistant or workflow is about to go live, a review is the better tool. The AI use register template records every use with its risk tier, owner, data, permissions, reviewer, versions and incidents, and every control in the governance section attaches to it; the content review checklist is the gate every AI-assisted article, ad or email passes before publication; and the customer service launch checklist is the gate before an assistant answers customers, from a test on real past questions to a weekly review booked in advance. The AI marketing hub places foundations, applications and governance side by side.