AI search & content ops
How Bonzer runs agentic content ops with Morrison
What half a year of running our own SEO and content work with Morrison changed across keyword research, audit, briefing, drafting, publishing, refresh and governance, what is still the consultant's job, and the prompts our team actually uses.
13 min readUpdated
Updated November 14, 2026: Updated to the current product (Skill names, automation schedules, chat and workflow limits) and corrected the AI Overview advice to match Google's documentation.
This is how Bonzer, the SEO agency behind Morrison, uses Morrison in its own SEO and content work: stage by stage, from keyword research to governance, with the prompts our consultants and writers actually use and an honest list of what has not changed. We built Morrison because we couldn’t find a tool that did what we needed for the work we do. We wrote this note half a year in, with our consultants and content team using it every day. (Since then, Morrison has been shortlisted for Best Software Innovation at the Global Search Awards 2026.)
We’re still learning where Morrison earns its keep and where it doesn’t. What’s already clear is that every step of the pipeline - keyword research, audit, briefing, drafting, publishing, refresh, governance - gets meaningfully better when Morrison is doing the legwork next to the consultant.
An engine, not an oracle
The framing we landed on internally, and the one we’d encourage any agency leader to start from: Morrison is not the driver. Our consultants and specialists are. Morrison sits next to them - with the whole client site indexed, the brand voice doc in its context, and Search Console, GA4, Google Ads, Ahrefs and live Google results connected - and answers the question they would otherwise have spent forty minutes assembling from six tabs.
The work that used to eat the day was the lookup, cross-reference and synthesis layer. Often the biggest share of any task. The part where the answer means three CSV exports and a manual stitch. That part is now more or less a sentence and an answer - and the consultant gets to spend more of the day on the work that actually needs them, with more context than before, because the lookup is suddenly cheap.
What’s left is everything we were already good at, with more room to do it well. Strategy is still set by the consultant who understands the client’s business. Editorial calls are still made by the content lead who has read the last twelve months of the site. Brand positioning, market judgment, the client relationship - all the things that make Bonzer a good agency to hire - remain human work.
Same consultants. Same content people. The job they were already great at, with a new instrument on the bench.
1. Keyword research - what’s actually worth chasing?
Most keyword research lives in a patchy stack of exports - a query report pulled from Search Console, a Keyword Planner CSV, a SERP tool scrape, all reconciled by hand in a spreadsheet. The sources don’t talk to each other, so the reconciliation is where the time goes and where most of the signal quietly leaks out. A keyword-research session in Morrison pulls the seed terms together in one place: every query already earning impressions for the client’s domain in Search Console (including the long tail of near-miss queries that never get manual attention), keyword difficulty and competitor visibility from Ahrefs, and - where it helps - the live results for each candidate.
The result is a clustered, intent-tagged keyword set weighed against the client’s actual authority - not a generic difficulty score read in isolation. The difference matters more than it looks. A keyword that reads as “hard” for a generic site is often very reachable for a site that already owns the surrounding cluster; a keyword that reads as “easy” can be a dead end if the client has no supporting authority. Where the pattern fits, the candidate set walks into kickoff already prioritized on what’s defensible for this specific client - not on what a generic tool thinks the average site can win.
Search Console
Ahrefs
SerpApiWhere it earns its keep, three categories consistently surface that consultants otherwise miss. First, queries the client already has impressions for but ranks outside the top 10 for - the cheapest wins available, and the ones that rarely surface unless you join Search Console to the live results. Second, commercial-intent queries that competitors monetize but the client doesn’t address yet. Third, long-tail clusters around the client’s strongest topical authority - the queries that compound rather than cannibalize, because Morrison has the site indexed before scoring them.
The point of joining the data isn’t a fancier export. It’s that the consultant can ask a question that crosses sources - “which of these 800 candidates have impressions but no clicks, what’s the dominant blocker per cluster, and what’s the realistic effort to get to the top 3?” - and get one answer that takes the client’s actual authority into account. When it’s part of the flow, kickoff starts from a defensible shortlist rather than a brainstorm.
2. Audit - where does the portfolio actually sit?
Every engagement starts with the same question: what should this client’s next move be? An audit against the client’s indexed site, joined with Search Console, GA4 and the live results, can land a defensible cluster plan in an afternoon - work that used to live in spreadsheets across two days.
The consultant still makes the call. What lifts is the floor of the input - from “what I had time to look at” to “the whole portfolio, scored.” That difference shows up in the recommendation. An audit can pull a coverage map across every cluster a client owns, the clusters competitors own that the client doesn’t touch yet, and a freshness check for every page that ranks. The whole-site parts come from the URL grid, where the content analyzer scores every page after each crawl and the Updated column shows when each page’s text last changed, or from a workflowrun across a section; chat works from the same index and reads the shortlisted pages in full, so that’s where we dig in. Two days of work, surfaced as a conversation.
Two things matter in the audit stage. First, Morrison leads with the crawl - it knows what the site actually says, not just what the rankings show. Second, the model is chosen per question, and we can switch mid-conversation when a different angle helps: a reasoning-heavy model for “why is this cluster underperforming”, a fast one for “list the URLs targeting this entity”. The consultant stays in the driver’s seat; Morrison handles the reading.
The output that tends to pay back hardest is not the cluster map itself but the intent-drift report - a pass that compares what each ranking page sets out to do against what the current results reward. Intent shifts quietly; rankings drop noisily. Catching the shift before the drop is the difference between a planned refresh and a panic refresh.
3. Brief - what does this page need to be?
Briefing is one of the more fragile steps of the pipeline. A brief is a translation between strategy and writing, and the translation breaks easily - a brief thin on structure, or one so prescriptive it leaves no room for craft. Both cost time in revision.
A brief built with Morrison’s Universal Brief Builder Skill lifts the floor without flattening it. It reads the live results, the client’s existing pages and the internal links, and returns a brief that’s structurally complete: title direction, headings, entities, internal links, voice notes, source candidates. The writer takes that and adds the part no tool should be writing - the angle, the editorial voice, the argument the page is actually making.
The most useful step in this stage isn’t the brief itself. It’s the cannibalization check we ask for before the brief is drafted - which, where the pattern fits, can quietly turn a meaningful share of “new page” requests into “refresh this one instead.” Morrison searches the indexed site for any page already targeting the same intent and either points the request to a refresh of the existing URL or proposes a sharper angle that doesn’t compete with the page already ranking.
A working principle Morrison makes easy to enforce: no new page enters the pipeline without a corpus check. The discipline used to require a senior consultant’s time; now it’s one line in the brief request. Where it’s part of the flow, a decent share of the wins are pages that don’t get written. The result is a sharper plan - fewer pages, each doing more work, and internal-link suggestions for every new brief.
The other quiet win is coverage of what Google’s AI Overview for the target query already draws on. There is no special markup or eligibility checklist for AI Overviews: Google says a page needs to be indexed and eligible for a snippet, and that normal SEO best practice applies. So the useful question is content, not structure: which entities and questions does the overview and People Also Ask cover that our draft doesn’t? Answering that doesn’t guarantee a citation - nothing does - but it stops the predictable mistake of shipping a page that skips what searchers clearly want answered. The crawler access and measurement side is covered in how to get cited by ChatGPT, Perplexity and Google’s AI Overviews.
4. Produce - drafting and refining
Morrison isn’t where our writers draft. They write in their document of choice; Morrison sits next to the draft - a chat the writer can ask anything, against the same crawl, brand voice doc and live results the brief was built on. It is, in our experience, the cleanest setup: the document is the writer’s, Morrison is on call. Canvas now also gives drafts a place beside the chat when you want one.
The questions writers actually ask, day to day: does this paragraph match the voice doc? What’s an internal link target for the methodology section? Is this claim supported, or do we need a source? Does this cover what searchers are shown for the query?Each one used to mean five minutes of context-switching and three open tabs. With Morrison on call, each one becomes a sentence and an answer. For writers who lean into the workflow, twenty asks an article isn’t unusual - and the day reshapes itself.
The most overlooked feature on this surface is the model picker. Some tasks need depth - voice fit, originality, contradictions across the site - and some need speed - link-target lookups, definition rewrites, quick fact checks. The writer picks the model per message, and the chat keeps its context across switches. It takes about a week to internalize which model fits which question, and pays back from there.
The other thing we’ve learnt: Morrison earns its place by being the second pair of eyes that’s available at 11pm on the Thursday before a Friday ship. Writers don’t want a chatbot; they want a senior editor on call who has read the brief, the site and the voice doc, and who can give a useful answer in under a minute. That’s the bar.
5. Publish - the QA gate before it ships
Quality enforcement traditionally rests on senior review. Senior review is irreplaceable for judgment - the angle, the argument, the brand sensibility. But a lot of what senior reviewers actually check is mechanical: voice fit, metadata, schema, internal links, compliance language, originality. A custom publish-gate Skill we wrote collapses the mechanical layer into one call. (Custom Skills are written in plain language and shared across the organization, so the whole team runs the same gate.)
The gate isn’t there to replace the editor. It’s there so that when the editor reads the draft, they’re reviewing what they’re best at - the substance - and not catching a title that will be cut off in the results. The five things it catches most often, in order: voice drift in the closing section, a new page with no internal links pointing to it, a meta description over our house length limit (Google itself sets no length limit and truncates to fit the screen), unsupported claims in the body, and schema fields the template forgot to fill. None of those are interesting problems. All of them used to slow down a release.
For regulated-industry clients - financial advisors, healthcare, a couple of legal-adjacent brands - the compliance pass has become the most valuable single thing we run. Where it’s part of the publish flow, nothing on a regulated engagement leaves without it. The pass reads the draft against the client’s specific compliance brief (disclaimers, restricted language, mandatory citations) and either clears the page or returns the offending lines with the required edit. It’s the kind of check that used to live in a senior’s head and now lives in a Skill anyone on the team can run, with sign-off still where it belongs.
6. Refresh - keeping the corpus alive
Half of the value of a content operation isn’t what you write next; it’s what you do with what you’ve already shipped. Most agencies don’t refresh well because prioritization is thankless work - reading 200 posts, scoring them, defending the ranking. So refresh sprints either run on instinct or don’t run.
Refresh prioritization is a custom Skill we wrote. It ranks the blog’s declining posts into a queue with a one-line rationale per page. The score is composed: ranking decay from Search Console, freshness against the current results, conversion contribution from GA4, and how well the page still matches the query’s intent. Search Console covers every post; chat then reads the top candidates against their live results. When a refresh sprint comes around, the prioritization can be briefed in one sitting - the consultant reads the top 20, accepts most, argues with a couple. From there, Morrison’s Content Refresh Brief Builder Skill turns each accepted page into a refresh brief.
GA4The second custom Skill in this stage - decline diagnosis - is the one clients ask about most. Why is this page slipping? used to have a vague answer. With the live results joined to the ranking history and the page content, the answer typically lands as a paragraph and a fix. Most of the time it’s one of four things: an AI Overview now answers the query above the page; the intent has shifted from informational to commercial; a competitor shipped a sharper page; or the page itself stopped being updated and the results started favouring fresher entries.
Refresh is also where Morrison most often catches the merge case. Two pages quietly competing for the same query, neither winning. The prioritizer flags them as a cannibalization pair, the team picks the canonical, redirects the other, and the consolidated page does what neither was managing alone.
7. Govern - keeping the site honest
The least glamorous part of running content at scale: cannibalization, orphan pages, stale claims, internal contradictions. Every long-running site accumulates these the way a codebase accumulates dead code, and unless someone’s job is to clean them up, they compound until the next migration.
Governance is the stage where Morrison most clearly does work that wouldn’t otherwise get done. Cannibalization and contradiction checks can run as a baseline on retainer clients - a weekly cannibalization check and a monthly sweep of key facts, such as pricing, for contradictions, as automationsthat email the result, and an orphan and dead-end-link audit each quarter, run by hand, are typical cadences - and what surfaces is almost always real, and almost always includes a couple of items the team would not have found on their own. Stale claims are the most quietly damaging: a product spec stated one way on a launch page and a different way on the FAQ a year later, both still indexed, both contradicting the client’s newest source of truth.
Governance isn’t about catching mistakes. It’s about a site that gets quietly more correct over time, instead of slowly drifting away from accurate. The team review stays the same - a consultant reads the surfaced items, decides what needs an edit and what’s acceptable variation - but the surfacing can be ambient rather than a project. That’s a difference clients feel even if they can’t name what changed.
What hasn’t changed
Almost more important than the list above is the list of things we still do exactly the way we did before:
- Strategy. What a client should be doing this quarter, and why, is still decided by a consultant in a room with the client. Morrison informs the decision; it doesn’t make it.
- Editorial voice. Voice is set by editors. Morrison checks copy against the voice - it doesn’t create the voice.
- The angle of a piece. A brief can be structurally complete and still need a writer to work out what the piece is actually arguing. Morrison doesn’t argue.
- The client relationship. No surprise here. People hire people.
Morrison informs every one of those; it makes none of them.
What this means for the people on both sides
For our clients, this is the experience we care most about getting right: same team, same judgment, deeper and faster and more ambitious work. Without the quality compromise that usually rides along when an agency adopts AI loudly.
For our consultants and writers, the experience matters just as much: the job got more interesting. The extractive part shrank. The judgment part grew. People are doing more of the work they’re best at.
What we’re still figuring out
- Where Skills end and the consultant begins. Some Skills got too ambitious early on and tried to do an entire step in one call. The good ones are sharper now - one job per Skill, chained together rather than overloaded.
- How much chat, how much automation. Conversation is best for exploration and judgment; recurring questions are best as an automation that runs on a schedule; the same steps on every page of a section are a workflow. Drawing those lines per client is still an ongoing calibration.
- Picking the right model. The fastest path to better output is often the model picker, and we’re still building the intuition for which model fits which task. Our writers are leading on that one.
- What we shouldn’t automate. The honest answer is “more than we initially thought.” Some of the highest-leverage decisions in content ops are deliberately slow.
For the general version of this operating model, without the agency context, see AI for content operations and how to scale content production without sacrificing quality.
Where we’re taking this
Our vision for Morrison is straightforward: the everyday work companion for people whose job touches a website. The same goal for our consultants and content team as for everyone else - do more, in less time, at higher quality, on the work that actually matters.
For Bonzer, half a year in, that had already made us a different agency. The same people, doing deeper, faster, higher-quality work, with a new instrument on the bench. The clients notice.
If you run content for a website - whether you’re an in-house team, an agency, or one of those founders who somehow ends up owning the blog - Morrison is open to every team. Start a 14-day free trial on your own site.
Sources and further reading
CEO, Morrison
Ulrich is CEO of Morrison and founded Bonzer in 2017, growing it into one of Scandinavia's leading SEO agencies with 900+ clients across Copenhagen, Oslo, and Stockholm. At Morrison he leads strategy, operations and go-to-market, bringing years of hands-on SEO and content work to the platform side of the business.