Core feature

Track the questions your buyers actually ask

Every buyer question is a prompt, and every prompt gets a different answer. Siftly tracks your prompt set across ChatGPT, Perplexity, and Google AI Overviews, samples each one repeatedly, and shows whether your brand was named, which competitors were named beside you, and which sources the answer was built from.

best stability running shoes for flat feetExecutions
DateMentionedLocationPlatformBrand Mentions
Jun 24ChatGPT+2
Jun 24Perplexity+1
Jun 23ChatGPT+1
Jun 23Google AIO
Jun 22Perplexity+3
Mention rate 60% across 5 runsOpen run

the prompt set

Your prompt set is your keyword list, and it moves

Start from the questions your buyers ask. Onboarding generates a starting set from your domain, your topics, and your personas. You edit it, add your own, and archive the ones that stop mattering. Each prompt carries the topic and personas it belongs to, so results roll up the way your team thinks.

One answer proves nothing. Engines are non-deterministic: the same question can name you in one run and skip you in the next. Siftly runs each prompt repeatedly and reports the rate, not a single lucky or unlucky snapshot.

18 suggested prompts await your reviewReview
PromptTopicIntentSource
best shoes for overpronation 2026StabilityCommercialCompetitorrunnersworld.com
how do I know if I need stability shoesFitNewInformationalSearch Consolestride.com
zephyr vs stride for long runsComparisonEvaluationCompetitorgearpatrol.com

every execution

Read the answer, not just the score

Open any run and see what was said. Each execution keeps its platform, date, and location, the brands the answer named, the search queries the engine fanned out to, and the citations it built the answer from. Your own brand is marked in the mention list, so presence and absence are both obvious.

Find the prompts you are not tracking yet. Siftly proposes new prompts from two places: answers where a competitor is cited and you are not, and searches you already appear for in Search Console. Each suggestion carries its intent and its source, and one click adds it to your tracked set.

18 suggested prompts await your reviewReview
PromptTopicIntentSource
best shoes for overpronation 2026StabilityCommercialCompetitorrunnersworld.com
how do I know if I need stability shoesFitNewInformationalSearch Consolestride.com
zephyr vs stride for long runsComparisonEvaluationCompetitorgearpatrol.com

AI Prompt Tracking

What AI Prompt Tracking Measures

AI prompt tracking is the practice of maintaining a set of the questions your buyers ask AI assistants, running those questions against the engines repeatedly, and recording what each answer said about your brand. It is the AI-search equivalent of a rank-tracked keyword list, with one important difference: the unit is a whole answer, not a position, so what matters is whether you were named at all, who was named beside you, and which sources the engine trusted.
Siftly records four things for every prompt: whether your brand was mentioned, which topic the prompt belongs to, which brands appeared in the answer, and the citations behind it. Those four turn a pile of answers into something you can act on.
Prompts, not keywords: "running shoes" is a keyword. "What are the best stability running shoes for flat feet?" is a prompt. The second is what people actually type into an assistant, and it is the unit engines answer.

How it works

How Sampling Works

Run each prompt repeatedly

A single answer is one sample of a probabilistic system. Siftly runs your prompts on a daily schedule so the result is a rate across many answers rather than one draw.

Run them per engine

ChatGPT, Perplexity, and Google AI Overviews answer the same question differently. Each engine is sampled separately, so you can see where you are strong and where you are absent.

Run them per location

Answers change by country. Prompts carry the locations you track, and every execution records the one it ran in, so a global average never hides a market where you are invisible.

Report the rate

Mention rate is the share of runs that named your brand. A brand in four answers out of ten has a 40% mention rate, which a single-shot checker would report as either 0% or 100%.

AI Prompt Tracking

What Each Execution Records

What is recordedWhy it matters
Platform and dateEngines drift. Dated, per-engine records are what let you attribute a change to a model update rather than to your own work.
LocationThe same prompt answers differently by country, so an execution without a location is not comparable to another.
MentionedWhether your brand appeared in this specific answer, which is what the mention rate is built from.
Brand mentionsEvery brand the answer named, with yours marked, so you can see who you are being shortlisted against.
Search queriesThe queries the engine fanned out to before answering, which tell you what it thought the question was about.
CitationsThe pages the answer was built from, which is where content and outreach work starts.

AI Prompt Tracking

Where New Prompts Come From

A prompt set goes stale. Siftly keeps proposing additions from two sources, and both are evidence-backed rather than generated from nothing:

Competitor citations

Questions where a rival's page is the source and yours is not

Search Console

Searches you already rank for that engines are now answering

Intent

Commercial, evaluation, informational, or navigational

One click

Accept a suggestion and it joins your tracked set

Each suggestion states its own case: which competitor pages are cited for that question, how often, and whether any of them are yours. You accept it, or you dismiss it and it stops coming back.
Keep the set honest: track the questions buyers ask, not the ones you wish they asked. A prompt naming your product category is worth ten that name your brand, because the ones that name your brand were never in doubt.

Getting started

Time to value, not time to configure

Day 1

Generate the set

Siftly reads your domain and builds a starting prompt set across your topics and personas. Review it, edit anything, and add the questions your sales team hears.

Day 2

First full sweep

Every prompt runs across your entitled engines and locations. You get mention rate, the competitors named beside you, and the sources each answer used.

Week 2

Work the gaps

Filter to the prompts where you are missing, read the answers that beat you, and send them to content or outreach. Review the suggestions queue as it fills.

Questions

FAQ

AI prompt tracking means keeping a set of the questions your buyers ask AI assistants, running those questions against engines like ChatGPT, Perplexity, and Google AI Overviews on a schedule, and recording what each answer said: whether your brand was named, which competitors were named, and which sources the answer cited.
Each prompt is sampled repeatedly rather than checked once, because engines are non-deterministic and the same question can produce a different answer on the next run. Siftly reports mention rate across those runs, which is a stable number, instead of a single answer that could be a lucky or unlucky draw.
Yes. Prompts carry the locations you track, and every execution records the location it ran in. That matters because answers change by market, and a global average can hide a country where your brand never appears.
Start with the set Siftly generates from your domain, topics, and personas, then add the questions your sales and support teams actually hear. After that, the suggestions queue proposes prompts drawn from answers that cite your competitors and from searches you already appear for.
Rank tracking measures a position in a list of links. Prompt tracking measures an answer: whether you were named in it, who else was named, and what it was built from. There is often no list at all, so presence in the answer is the thing to measure.

Your buyers are asking AI.
Be the answer.