Give Juma a URL and what you've noticed. Get a diagnosis of the SEO ranking drop: query data, competitor gaps, and why your Google ranking dropped.
Paste a URL and describe what you've noticed, and Juma pulls query-level data, scrapes the top-ranking competitors, and maps the SERP features in play for that page. The Flow traces each SEO ranking drop back to specific evidence and returns a structured diagnosis with the data attached.
Once the diagnosis identifies a SERP presentation problem, this step produces rewrites with character counts and reasoning. Run it when the page has ranking but low CTR. This step generates:
Each option includes a rationale so the team can explain the change to a client.
When the diagnosis identifies a competitor gaining ground, this step runs a side-by-side comparison against that specific page. Use it when the drop traces back to one site overtaking you on a key query. This step covers:
Every finding ties back to the query and impression volume it affects.
The competitor at [URL] is now outranking us for the main keyword. Do a full side-by-side: content depth, structure, schema markup, backlink profile, freshness signals. Tell us exactly what they have that we don't.
A Juma Project is a shared space where the team stores everything Juma needs to know about a client. Create one project per client, add context as you go, and Juma will use what's relevant every time the team runs a flow. If the project already exists from other work, just add the SEO-specific items below.
Add a short description in the project's info field that tells Juma what each file contains and when to use it. For example: "Target Keywords: priority terms from Q1 planning, focus on these first. Competitor URLs: main organic competitors, always compare against these. Past Audit: March 2026 audit, use as performance baseline."
This Flow replaces 3 to 5 hours of manual diagnostic work with a single prompt. It pulls query data from Google Search Console, scrapes 3 competitors, maps SERP features, and returns a prioritized fix list together. The analyst's time shifts from data collection to decision-making.
That estimate assumes the analyst has GSC access, knows how to pull query-level data, and has a process for formatting the comparison output. For teams without a standardized audit workflow, the time runs longer. Running this diagnosis manually across 10 pages that dropped in a single month would take a full week of analyst time.
The diagnosis pulls every query currently driving impressions to the page, along with position, CTR, and impression volume for each. It benchmarks CTR against position norms so the team can distinguish a ranking problem from a SERP presentation problem before deciding which fix to apply.
A page at position 3 with a 2% CTR when the norm is 9% has a different problem from a page that dropped from position 3 to position 9. The first needs a better title and meta description. The second needs content or authority improvements. The query data tells the team which kind of fix applies before they spend time on the wrong one.
The diagnosis also surfaces queries where the page earns impressions but no clicks. These are usually queries where a featured snippet or AI Overview answers the question directly in the SERP. Knowing which queries face zero-click competition changes how the team weighs content improvements against SERP presentation fixes.
The most common causes are content depth falling behind a competitor, a SERP feature now answering the query directly, or a title and meta that no longer match search intent. Juma checks each against real data and names the specific cause instead of listing every possible reason.
The diagnosis also checks for less obvious causes: a competitor that published a more comprehensive version of the same content, an algorithm update that shifted ranking signals during the drop period, or a site-level change like a URL migration or an accidental noindex tag. Each leaves a different fingerprint in the query performance data.
Matching the cause to the fix is where the diagnosis saves the most time. A page stuck at position 16 has a content or authority problem, not a title tag problem. A page at position 4 with 2% CTR has a presentation problem. The diagnosis separates these before the team applies the wrong fix.
SERP feature analysis determines whether the right fix is a ranking improvement or a citation play. A page competing with a featured snippet needs a restructured direct answer. A page competing with an AI Overview needs citation optimization, not more content. Getting this wrong wastes the fix effort on the wrong problem.
For a query where a featured snippet holds position zero, the most effective fix is restructuring the page's answer to compete for that snippet. That means a concise definition in the first paragraph, a structured list or table where relevant, and a heading that mirrors the search query. Adding more words to the page without restructuring the answer will not move the snippet.
For queries with AI Overviews, the goal shifts to earning a citation rather than ranking in the traditional organic results. The diagnosis flags these queries separately so the team knows which pages need citation optimization and which need standard ranking improvements. Treating all query types the same produces weaker results for both.
Yes. The diagnosis distinguishes between gradual decline and sudden drops because they have different causes. Gradual decline usually signals content freshness or topical coverage problems. A sudden drop more often points to an algorithm update or a competitor publishing something competitive around the same time.
For gradual declines, the diagnosis looks at publish date, content depth relative to current top results, and whether the queries driving impressions have shifted toward different intent. A query that used to return a how-to guide but now returns a comparison page signals that the content type, not just the quality, needs to change.
For sudden drops, the diagnosis cross-references the timing against known algorithm update dates and checks whether a specific competitor gained rankings around the same time. Both types of drop get a diagnosis built around their specific evidence rather than a generic checklist of possible causes.
