For a small agency juggling client work, these are the strongest picks:
Kanbo#1 for boards and client portals in one place, priced per seat. Trellis#2 if you run retainers: time tracking and a budget per client. Fieldnote#3 when your team lives in docs.
mentioned
yes
rank
#2
cited
#1
UK agencies tend to shortlist these:
Kanbo#1 for client-facing boards, Fieldnote#2 for small teams on a budget, and Orbitly#3 once you plan resources across several clients. Trellis#4 is worth a look for retainer work.
Agencies most often shortlist Orbitly#1, Kanbo#2 and Plotwise#3. Orbitly stands out for resource planning across several clients; Kanbo for its client-facing views.
mentioned
no
rank
—
cited
no
Popular choices for agencies include Kanbo#1, Trellis#2 and Orbitly#3. Trellis is often recommended for tracking budgets per client.
Here are three solid picks for a small agency:
Kanbo#1 for client boards your clients can see, Trellis#2 for retainers and a budget per client, and Fieldnote#3 if you want something lightweight.
mentioned
yes
rank
#2
cited
#2
For UK agencies, Trellis#1 is a popular choice for retainer work, with Kanbo#2 and Orbitly#3 close behind.
Three tools come up most for small agencies:
Trellis#1 for retainer work, with a budget per client. Kanbo#2 for client-facing boards. Fieldnote#3 if your team works mostly in docs.
mentioned
yes
rank
#1
cited
#2
Three tools come up most for small agencies:
Trellis#1 for retainer work, with a budget per client. Kanbo#2 for client-facing boards. Fieldnote#3 if your team works mostly in docs.
Individual developers or teams — not official partnerships
One command. Your agent does the rest.
All five calls are MCP tools. Ask your agent where you stand and it runs the rank check, on the same key and the same billing as REST.
Claude CodeCodex
5 tools
1
Run one command, then sign in
$ npx fetchlayer
◇ Agents
│ Claude Code and Codex
◇ Signed in as you@company.com
◇ Connected
│✓ Claude Code ✓ Codex
It opens a sign-in page in your browser. New here? Signing in creates your free account.
2
Ask
›Does ChatGPT recommend Trellis for best project management software for small agencies, and who does it name instead?
fetchlayer.chatgpt_ai_rank
Asked five times, five credits. Trellis was named in 4 of 5 answers at an average rank of 2.3, and cited in 2. Kanbo was named every time and ranked first in four.
No key to copy and nothing to install. New accounts are free, with no credit card.
A dedicated platform from $400/mo, plus $500 for each ~21 req/s. Every other platform on the same key. 99.95% uptime, 24-hour support on Slack or Telegram.
How much does FetchLayer's AI visibility API cost?
FetchLayer's AI Visibility API returns ChatGPT answers, the brands they mention, the pages they cite and your rank among the recommendations as JSON over REST or MCP. A request is one ChatGPT answer, and each request costs one credit: $1.99 per 1,000 requests pay-as-you-go, or $25 a month for 15,000, with 30 free requests and no card to start. A request that fails is not billed. The same key covers 36 other platforms, and every route is also a tool on FetchLayer's MCP server at https://mcp.fetchlayer.dev, for Claude, ChatGPT, Cursor and other MCP clients.
What is an AI visibility API?
It answers the question SEO tools answer for Google, but for AI assistants: when someone asks ChatGPT the question your buyers ask, does the answer name you, does it cite your pages, and where do you sit among the options it recommends? Send a prompt and your brand, and you get that back as structured JSON — mention counts, the sentence around each mention, the citations, your rank among the recommendations, and the competitors the answer put forward instead. This is the measurement side of what SEO now calls answer engine optimization or GEO.
What is the difference between being mentioned and being cited?
They are two different outcomes with two different fixes, and most AI brand monitoring collapses them into one number. An answer can name your brand in its prose while none of your pages are among the sources it links — you are part of the consensus but not the evidence. Or it can cite one of your pages without recommending you at all — your content is being read, but someone else gets the recommendation. Every route reports both separately: mentioned beside citedAsSource, and in a rank check, rank among the recommendations beside citationRank among the cited sources. There is a third state worth watching, retrieved: ChatGPT read one of your pages while searching and then cited someone else.
Do I need an OpenAI account or an OpenAI API key?
No. You send your FetchLayer key and a prompt, and you get back the answer people see — the real consumer-facing answer, not an API completion. There is no temperature or system prompt to choose, because the people asking have none of those either; only Duck.ai lets you pick the model. FetchLayer is not affiliated with, endorsed by, or sponsored by OpenAI.
Answers change every time. How can you track anything?
By measuring the variation instead of pretending it is not there. Ask the same prompt once and you have an anecdote; ask it several times and you have a rate. /ai-rank takes a runs count and reports mentionRate, averageRank, bestRank, worstRank, citationRate and averageCitationRank across those runs, with the same figures for each competitor. A brand mentioned in 5 runs out of 5 is in a different position from one mentioned in 1 — and a single answer cannot tell those apart. Keep the prompt, country and web-search mode fixed when comparing week to week, and read the aggregate rather than any one run.
How do I know which prompts to track?
Start with /prompt-discovery. Give it a topic or your brand name, and it returns the prompts it asked, the web searches ChatGPT actually ran while answering them, and prompts it suggests people use. The two lists are labelled and kept apart, because they are different kinds of evidence: observed_search_query means ChatGPT really ran that search, so those are the queries your pages have to rank for to be readable by it; generated_prompt means ChatGPT wrote that prompt when asked, which is a suggestion, not an observation. Feed the ones that matter into /ai-rank.
Can I compare several brands across several questions at once?
Yes — /visibility-report takes a list of prompts and a list of brands and returns share of voice per brand, plus a per-prompt breakdown of mention rate, average rank and citation rate. Extra brands are free, because every brand is read out of the same answers; it is the prompts and runs that cost credits. The request is bounded by answers: prompts × runs must be at most 10, so ten prompts at one run each is fine. For wider tracking, run several smaller reports on a schedule and store the results.
What comes back from one answer?
The answer as Markdown and as plain text, the pages it cites — each with position, URL, title, domain, the label shown on the citation, and the sentence that cites it — every inline citation, the web searches it ran, and every page it looked at while searching, each flagged with whether it was cited. That last list is useful on its own: a page can be read and never cited. Null means the answer did not show a field, not zero.
How does billing work?
One credit per answer ChatGPT generates, which is exactly what pagesScraped reports. /ask and /mentions cost 1; /ai-rank costs its runs; /prompt-discovery costs one per prompt asked, plus one more while it also asks for suggested prompts; /visibility-report costs prompts × runs. Matching, ranking and aggregation cost nothing extra, and an answer that could not be produced is never billed. Asking several assistants at once (providers) bills the sum of the answers they produced, and a Bing request where Bing shows no AI overview is still one answer.
How long does a request take?
A single answer typically takes 20 to 40 seconds rather than milliseconds. A request’s answers are generated alongside each other rather than one after the other, so asking for more runs costs more credits but not proportionally more time: a two-run rank check typically takes 30 to 55 seconds, and a visibility report 40 to 80 seconds, longer when demand is high. Set your HTTP client timeout to at least 60 seconds for a single answer, 120 seconds for a rank check or prompt discovery, and 180 seconds for a visibility report.
What is not available?
You cannot turn web search off: the assistants offer no such setting, so webSearch is auto or on, and usedWebSearch reports what it did. Some answers state which model produced them and some do not, so model is null rather than guessed. Some answers do not show the searches behind them, and then searchQueries and retrievedPages are null rather than empty, with notes saying so. And nothing here measures traffic, spend or clicks — it measures what the assistants answer, not how many people saw it.
Can my AI agent use it?
Yes. All five routes are MCP tools on the same FetchLayer MCP server, named chatgpt_ask, chatgpt_mentions, chatgpt_ai_rank, chatgpt_prompt_discovery and chatgpt_visibility_report. Tool calls use the same key and are billed exactly like REST, so an agent running a five-run rank check still pays five credits.
Which assistants are covered?
ChatGPT, Bing, Duck.ai, Gemini, Google AI Overviews and Meta AI today: set provider to bing for the AI overview Bing shows above its results, to duck_ai for Duck.ai — where model picks the model that answers (GPT Luna (the default), Claude Haiku, GPT mini, Mistral Small (no web search), gpt-oss or Gemma) — to gemini for Google’s Gemini, to google_ai_overviews for the AI Overview Google shows above its search results (not AI Mode, and not Gemini), to meta_ai for Meta AI, which runs on Muse Spark, the same Meta model as Muse, or send providers: ["chatgpt", "bing", "duck_ai", "gemini", "google_ai_overviews", "meta_ai"] to ask them all in one request and get one result per assistant. Bing and Google do not show an overview for every search; when they show none you get answerShown false and null mentions and ranks rather than a false “not mentioned”. Gemini links its sources on some answers only, so read retrievedPages as well as sources. Perplexity, Google AI Mode, Copilot, Grok and DeepSeek are coming soon, on the same requests — no new shape to learn. Without provider, every request asks ChatGPT exactly as before.
FetchLayer is not affiliated with, endorsed by, or sponsored by OpenAI, Microsoft or any other assistant named here. Brands in the examples are invented.
Used by developers at
Individual developers or teams — not official partnerships