How We Land 15+ Brand Mentions a Month by Automating Journalist Queries (Free N8N Workflow)

Journalist query automation is a multi-stage pipeline that ingests open reporter requests from platforms like Featured and MentionMatch, scores them against a structured spokesperson voice profile, drafts responses using an LLM, and routes them for human QA before submission. The goal is volume without quality loss: 100+ pitches a month at 3 minutes of human review per pitch, producing 10–15 brand mentions per month in category-relevant publications.

Reasons to Trust This Answer

Numbers as of Q2 2026.

• We run this system for VisibilityStack. 14.5% pitch-to-publication rate, 15+ brand mentions per month landed across 3 SMEs on our team (one in SEO/AI search, one in founder/AI marketing, one in content engineering).
• About 4 hours of human review per month per SME. No new hires required. The pipeline runs on a part-time operator at a 5 to 10 spokesperson capacity.

Scope: This article walks through how the journalist query automation works under the hood. For the agency upsell playbook (selling this as a $3K–$5K/month service to your clients), see the Media Mentions Upsell article.

Why Do Journalist Queries Feed AI Visibility?

Journalist queries are open requests reporters post on platforms like Featured and MentionMatch when they’re working on a story and need expert sources to quote. The reporter publishes the query, qualified experts respond, and the journalist picks the best quotes for their piece. When your spokesperson lands a placement, the brand and the named expert both get a mention in a category-relevant publication.

That mention is what AI search rewards. And it rewards very differently from traditional SEO. AI search isn’t a ranking game. There’s no list of ten blue links to climb. When a buyer asks ChatGPT, Claude, Perplexity, Google AI Overviews, or AI Mode for vendor recommendations in your category, the engine doesn’t sort results and pick the top one. It composes a single synthesized answer drawn from the three to five brands its training and retrieval systems most strongly associate with the category. You’re either in that answer, or you’re invisible. There’s no position 7 to settle for, no “we’ll get there next quarter” trajectory, the way SEO works. The engine either recognizes your brand as belonging in the category, or it doesn’t include you at all.

That makes AI search an authority recognition game. The question isn’t “how do I rank higher?” It’s “how does the engine learn that my brand belongs in this category in the first place?” Language models build entity-category associations from co-occurrence patterns in text (Mikolov et al., 2013). When your brand appears repeatedly alongside category-relevant terms across trusted third-party publications, the model learns to associate your brand with the category. When the model is asked about the category, your brand shows up in the answer. When a journalist quote lands in a category-relevant trade publication, two patterns compound at once: the brand becomes more associated with the category, and the named expert builds personal authority in their sub-category.

Recency makes the play even stronger. AI engines weigh recent content heavily. One-off PR fades. A steady cadence of placements doesn’t. The pattern decays without consistency, which is why automation matters. Journalist queries are uniquely suited to this work because the channel is built for volume. Week after week, month after month, the entity pattern stays fresh and reinforced. That’s why a sustainable cadence of journalist query placements outperforms sporadic flagship-publication wins in terms of AI visibility.

Why Does Manual Journalist Query Work Fail at Volume?

Manual journalist query response takes about 25 minutes per pitch. To start compounding, you need 100+ pitches a month in your category. That’s 50+ hours of senior writer time per spokesperson per month. I’ve watched most in-house teams start with enthusiasm and stop within 90 days. The math doesn’t survive the third month, when the team realizes they’re spending more time on pitches than on the work that actually moves their business.

We built a different option.

What Does the Automation Actually Produce?

Publication Expectations

Most placements land in category-specific trade publications that AI engines pull from when answering buyer questions in your vertical. If you’re a marketer, expect outlets like Marketer Magazine, MarTech Series, and Search Engine Journal. If you’re in SaaS or tech, expect TechBullion, Tech Times, and vertical SaaS blogs. If you’re in healthtech, expect HIT Consultant, MedCity News, and clinical practice publications. The pattern holds across categories: niche trade outlets in your vertical, not Forbes generalist roundups.

I’ll be honest: most of these publications have modest direct human readership. The value isn’t eyeballs on the article. The value is that AI engines train on and retrieve from these sources when answering category-specific questions. When your expert and brand appear repeatedly across publications that semantically cover your category, the model links your entity to the category in its training and retrieval data. That association is what gets you surfaced in product comparisons, vendor shortlists, how-to answers, and “best of” queries inside ChatGPT, Claude, Perplexity, Google AI Overviews, and AI Mode. Fifteen mentions across category-relevant trade pubs build that pattern faster than one Forbes hit ever could.

Volume Expectations

At full deployment, expect about 15 placements per month at the brand level across your spokespersons. With 3 SMEs running the pipeline in parallel, that’s roughly 5 placements per spokesperson per month. Most brands see meaningful AI citation lift starting around month three of consistent volume. ChatGPT and Perplexity citations usually appear by month six.

How Does the 6-Stage Automation Pipeline Work?

The automation has six stages. Every query that hits the system flows through all six before it can be submitted. If it fails at any stage, it gets logged and dropped.

Here’s the human/automation split at every stage so you know exactly what you’re signing up for:

Total human time per spokesperson per month: about 4 hours (voice profile maintenance + QA review + Featured paste).

1. Build the Voice Profile (the asset that compounds)

The voice profile is what makes volume not equal garbage. Each spokesperson has a single Airtable record that captures five things: phrasing patterns, past quotes from podcasts and interviews, credentials, topic stances, and a “would never say” list. One 30-minute intake session builds the first version. After that, you append. New quote from a webinar? Add it. New stance on an emerging topic? Add it. Over six months, we’ve roughly tripled each expert’s profile without a single additional intake call.

This is the asset that compounds. When you own the profile as a structured record, the marginal cost of drafting one more response is a Claude API call. That’s the unlock. Every other part of the automation is plumbing on top of this one asset.

The voice profile is also the quality ceiling. Garbage profile means garbage drafts, no matter how clever the scoring layer is. If I had to pick one thing from this article for you to take, it would be the profile structure. It works even if you never build the rest of the automation.

2. Pull Fresh Queries (Featured + MentionMatch APIs)

Open queries flow in from Featured and MentionMatch on a schedule. The Featured API returns about 1,400 open queries per month across our subscribed categories. MentionMatch adds another 1,000. The automation pulls on a schedule, dedupes against prior submissions, and drops anything with under 72 hours left on the clock (not enough time for a reliable spokesperson check). Roughly 2,400 queries land in the scoring stage every month.

Customize: swap the ingest nodes if you use Qwoted, Source of Sources, or another query source. The rest of the pipeline stays the same.

3. Score for Fit (the 60-point threshold that kills 94% of volume)

Scoring is where most of the volume dies. Each surviving query gets three scores:

• Topic fit (0 to 40). Does this query align with one of our spokesperson’s stated areas? A fintech query with no fintech expert scores zero. A growth marketing query with a growth marketing spokesperson starts at 30 and adjusts by specificity.
• Publication tier (0 to 30). Domain authority weight plus category relevance, pulled from our reference sheet. TechBullion at DA 76 scores 28. A brand-new blog scores 4.
• Proof availability (0 to 30). Do we have a real case study, quote, or data point that directly answers this? Voice profile proof points are tagged by topic. Tag match, score rises. Invent territory, score falls.

Below 60, the query is logged to a rejection sheet with the reason. Above 60, it moves to drafting. In a given month, we draft on about 150 of the 2,400 queries that survive freshness. That’s a 94% rejection rate before Claude writes anything. This is the single most important design choice in the automation: never ask AI to write about something the spokesperson cannot substantively answer.

A real example from last month. A Marketer Magazine query (DA 55, 30-hour deadline) about AI content detection false positives. Pushkar (our SEO/AI search lead) has three case studies on this from client work. Topic fit 38, publication tier 22, proof 28. Total 88. Drafted.

Same day, same publication: “How do you build a morning routine that supports creativity?” Topic fit 8, publication tier 22, proof 0. Total 30. Dropped.

Customize: tune the scoring weights and the 60-point threshold to reflect your own publication tier preferences and spokesperson coverage.

4. Draft in the Expert’s Voice (two Claude passes)

Two Claude passes. The first pulls the voice profile, the full query, the spokesperson’s tagged proof points, and the publication context to produce a draft. The second polishes with three rules: cut filler, verify credentials cited actually exist in the profile, and tighten the response to a direct answer. A short “never do” list lives in the prompt: never invent credentials, never fabricate quotes, never pad with qualifiers the expert would not use.

End-to-end time from query release to draft in the Google Sheet is about 35 minutes. Most of that is the schedule trigger interval. Actual compute is under 40 seconds.

Customize: tune the Claude prompt to your voice profile format. Most teams rewire this node to match how they structure POV statements and proof points.

5. Human QA (3 minutes per draft)

Every draft lands in a Google Sheet with a status cell (pending, approved, rejected). An n8n Slack node pings the reviewer the moment a draft is written. The spokesperson (or a trusted editor) opens the sheet, reads the draft, edits if needed, and flips the status to approved. That flip triggers submission.

Average time in the sheet: about 3 minutes per draft. About 8% get rejected outright, usually because the spokesperson has a fresh stance not yet in the profile. Those rejections feed back into the voice profile, which keeps it sharpening over time.

Why I keep the gate: Featured and similar platforms run AI-likelihood detection, journalists blacklist generic pitches, and one flag at volume can lock you out of a whole publication pool. Three minutes of QA is the cheapest insurance in the system.

6. Submit and Track

Approved drafts route to submission based on platform. MentionMatch fires through a Google Sheets Trigger node that posts the edited text. Featured gates its auto-submit API behind a paid tier, so most teams run a daily manual paste from the sheet. At 150 responses a month, the last click being human is the cheapest insurance in the system.

Every submission writes back to the same sheet with status, placement URL (once live), and publication tier. That becomes the reporting view: responses submitted, placements landed, acceptance rate by spokesperson, and pub tier distribution. Same sheet, no separate dashboard.

Customize: swap the submission method to match your platform. If you pay for Featured’s auto-submit tier, wire the webhook in place of the manual paste step.

Get the Workflow

Want to run this yourself? Download our free N8N workflow. It handles query sourcing, scoring, drafting, and Slack routing. Plug it into your existing N8N instance, configure for your spokespersons, and start running journalist query campaigns this week.