TangentFlow
Check a site Monitor Methodology
Sign in Monitor your site

Agent visibility · any site

Do AI agents recommend
{your site}?

Paste any website. We find its market, ask AI agents live buyer questions, and show who they recommend — you or your competitors. Tracked categories get weekly measurement with 95% confidence intervals.

    Free · 30 live agent answers · who gets recommended in your market →

    Why it matters

    Buyers ask AI agents first.
    Are you in the answer?

    Today

    • ✕No idea whether agents recommend you — or quietly send buyers to competitors
    • ✕One screenshot of one answer, N = 1
    • ✕SEO rank trackers that can't see inside AI assistants
    • ✕No clue what on your site agents can't read, or why they pick someone else

    With TangentFlow

    • ✓Who agents recommend for your market — you or your competitors — from live answers, with the reasons they give
    • ✓Where agents look: the exact lists and review pages they pull into answers, and whether you're on them
    • ✓An Agent Readiness score, ranked fixes, and paste-ready artifacts — plus a content calendar that writes and publishes the articles agents cite
    • ✓Weekly re-probes and experiments, so you know whether a change actually moved mentions
    How it works

    Find. Fix. Publish. Track.

    One URL in — who agents recommend instead of you and why, what to change, the articles that earn a place in the answer, and proof that it worked.

    1 · Find

    Who do agents recommend — and where do they look?

    We read your site, infer the market it serves, ask AI agents 30 live buyer questions about it (never naming a brand) and run a second pass with web search on. You see who came up, how often, the reasons they're credited with that you never are, and the exact lists agents pulled from.

    market: all-in-one business platform for photographers
    Dubsado 10/30 · Honeybook 9/30 · Squarespace 7/30 · you 1/30
    credited: “built for small service businesses”, “~$20–30/mo”
    agents cite: agiled.app · flothemes.com · picflow.com — you're on 2 of 6
    2 · Fix

    Can agents read you — and cite you?

    17 readability checks (robots, llms.txt, structured data, pricing in text, identity, freshness) with ranked fixes and the score impact of each. Then the fix pack, generated from your own pages and this probe: llms.txt, JSON-LD, a homepage answer block, /pricing.md, an honest comparison page naming the competitors agents actually recommend, an FAQ with schema — and a get-listed brief for every list you're missing from.

    • Agents can't read your pricing+9 pts
    • No llms.txt brief for AI crawlers+6 pts
    • Missing from “9 Best Studio Management Software…”brief
    3 · Publish

    The articles agents cite, on a calendar

    Topics come from your visibility data, not keyword volume: the buyer questions agents are asked in your market, the reasons competitors get, the lists agents cite. Drafts are written from your own pages only — no invented numbers, competitors named fairly — checked by quality gates, and delivered to your CMS on schedule through a signed webhook or WordPress. You approve every post unless you say otherwise.

    tue · “Best client galleries for photographers in 2026” · roundup · gates pass
    thu · “Pixieset vs Dubsado (2026)” · comparison · needs review: unverified number
    4 · Track

    Know when a change worked

    Register your site: weekly readability audits, your own market question set re-asked on a schedule, and experiments — “I changed X on this date” — compared before and after with the same statistics as our public index. Every published article is measured against the questions it targeted. Movement is reported only when the numbers support it; otherwise we say “not yet significant”.

    • published /pricing.md + comparison pagemoved up · p=0.02
    • “Pixieset vs Dubsado” · 3 target questionsnot yet significant
    • Raw answers stored verbatim, foreveraudit
    Measured categories

    Some markets we measure every week, with error bars.

    For these categories a frozen corpus of buyer scenarios runs weekly — share of recommendation with 95% confidence intervals, public for everyone. Any other site gets the live probe in its own market.

    Project Management

    18 tracked brands. Live weekly cycles with the full statistical stack.

    LIVE · corpus v1.0 · explore the index →

    CRM Tools

    Salesforce to Attio: who do agents actually tell buyers to pick? 16 tracked brands.

    corpus staged · measurement starts soon →

    Developer Tools

    Observability & monitoring first: which platforms do agents suggest? 16 tracked brands.

    corpus staged · measurement starts soon →

    TVs under ₹50,000

    Consumer, not SaaS: which TV do agents tell Indian buyers to get? 20 tracked brands.

    LIVE · corpus v1.0 · explore the index →
    Get started

    Start with your URL

    Check your site now — free

    1. Paste your URL above. We find your market.
    2. 30 live agent answers: who gets recommended, and why.
    3. Where agents look, your Agent Readiness score, and the top fixes.
    Check my site

    Get in front — and stay there Recommended

    Register your site: the full fix pack and get-listed briefs, a content calendar that drafts and publishes the articles agents cite, weekly audits, your own market questions re-asked on a schedule, experiments, and alerts when something moves.

    subject: yoursite.com — weekly agent check
    +5 mentions vs last week — holds up (p=0.03).
    2 checks regressed: sitemap, freshness.

    Your buyers already asked an agent.
    Find out what it said — then fix it.

    Free check for any site — and free monitoring, fix pack, content calendar and weekly reports during early access. Placement is never for sale; mentions are never promised.

    Check my site Read the methodology

    TangentFlow — agent visibility for any site. Find out who AI agents recommend in your market and where they look, fix what they can't read, publish what they cite, and track it weekly.

    corpus v1.0 · frozen weekly cycles · 95% CIs · FDR-controlled

    Product

    Check a site Monitor Measured categories Methodology

    Company

    Contact How we measure

    Principles

    Placement is never for sale and mentions are never promised. We sell the analytics and the fixes — never positions. Raw answers stored verbatim, forever.

    © 2026 TangentFlow · tangentflow.com

    tangentflow

    Sign in

    We email you a link — no password to remember.

    TangentFlow  
        No completed cycles yet. Data appears after the first weekly cycle finishes.
        Site analysis

        Analyzing —

          Observed brand

          Agents mention — — but it isn't tracked yet

          Mentions this cycle
          —
          Share of recommendation
          —
          —
          Low data: fewer than 30 mentions this cycle — treat these numbers as directional, not settled.

          Track this brand

          Get the full dashboard — confidence intervals, win/loss reasons, weekly movement — when this brand joins the tracked set.

          Or run a free live probe right now →

          ← Back to dashboard
          Not yet in agents' answers

          — has an agent-visibility gap

          Who agents recommend instead

          Measure it properly

          Absence in one cycle is a data point, not a verdict. Get notified when this brand appears in agents' answers — or request tracking with full weekly measurement.

          Or run a free live probe right now →

          ← Back to dashboard
          —

          Agents recommend — in — of buyer scenarios

          Share of recommendation
          —
          —
          Category rank
          —
          —
          Listed first
          —
          —
          Caveat rate
          —
          of your mentions carry a downside
          △
          Model update detected. The control task set shifted beyond threshold, so movement across that boundary reflects model changes, not your market position. The trend below marks the epoch.

          Competitive field — every score wears its error bar

          Share of recommendation. Whiskers are 95% Wilson intervals: overlapping whiskers means the ranking between two brands is not settled.

          You Field 95% interval

          Trend — recent cycles with confidence band

          Shaded band is the 95% interval. Movement inside the band of the prior cycle is reported as noise, never as news.

          Where you win

          Agents' stated reasons when recommending you.

            Where you lose

            Reasons agents give when picking a competitor or steering away.

              Share by buyer intent

              Displacement scenarios ("we're leaving tool X — what should we switch to?") are the highest-commercial-value slice.

              Methodology. Every task in a frozen, versioned corpus of realistic buyer scenarios runs 10× per model per cycle. Headline proportions carry 95% Wilson intervals; week-over-week movement is only labelled significant at p < 0.05 (two-proportion z-test with Benjamini–Hochberg false-discovery control across brands). A control task set flags model-update cycles so you never mistake a model change for a market change.
              Agent Visibility Score · published by TangentFlow · tangentflow.com