Map
Category market map
Maps every company in a category you define and colours each by hiring and news momentum.
- For
- Sales and marketing leaders
- You provide
- A category: industry, headcount, country and funding stage
- You get
-
- Treemap by sub-segment
- Size versus momentum quadrant
- Any cell as an account list
-
A market map for a Gong AE, not a slide.
-
So they know which of five-hundred accounts to call.
-
493 came from Trayo lookalikes, not hand typed.
-
Flip this, and only the 76 measured accounts stay lit.
-
Momentum ran on one sub-segment, on purpose, not everywhere.
-
Big and moving: the accounts worth calling this week.
The prompt
Paste it into any coding agent with the Trayo MCP connected.
- + any MCP client
Use Trayo to build a category market map. Let me name a category and its constraints — industry, headcount band, country, funding stage — then enumerate every matching company with exact filters and page all the way to the end, and widen the long tail with lookalikes seeded off the 20 clearest examples. Map the whole category, but run momentum discovery only over a sub-segment I pick, so the expensive half is bounded: for those companies, turn hiring and news event volume and recency over 90 days into a momentum score. Render an interactive treemap grouped by sub-segment, sized by headcount, coloured by momentum, plus a size-versus-momentum quadrant. Be explicit wherever a search was truncated or came back degraded, so I know which edges of the map are real and which are just where the data stopped. Let me export any cell as an account list. Known constraints for this build: enumeration is cheap to describe and expensive to run — `find` is metered per search and sits in the 7/min bucket, and discovery cost scales accounts × signals. Bounding momentum to a chosen sub-segment is what makes this finishable. `accounts/lookalikes` is unmetered and synchronous, so lean on it.
Take the tour
A narrated walkthrough of the app.
The building blocks
What this app asked Trayo for
Every name, number and email on the page came back from one of these. None of it was typed in.
Reads your workspace
What you sell, who you sell to, and the buyer personas already saved in Trayo.
Finds companies
Surfaces accounts that match your ICP, plus lookalikes of the ones already working.
Builds your account list
Imports, updates and organises accounts so the work survives the session.
Watches for buying signals
Standing watches for job changes, funding and the other moments worth a reply.
How it was built
The data behind each screen, and what's faked for the demo.
Built in 20 min · 4 capabilities · 22 live API calls
This is an internal account-mapping screen for a Gong AE working the mid-market. It takes one category — US-headquartered B2B tech, 201–1,000 employees, a Series B, C or D+ round on record — and shows every company Trayo holds inside it as a treemap: four industry sub-segments, each rectangle one company sized by headcount and coloured by 90-day momentum. Clicking a company opens its evidence; clicking a sub-segment or a quadrant turns that cell into an account list you can export as CSV. A Coverage screen lists every search that built the map with its filters, its row count and the truncation note Trayo attached, so you can see which edges are real.
Trayo supplied all of it. Six paginated POST /v1/find searches returned 45 companies, each paged to the end; one of the six came back genuinely empty rather than truncated. A first attempt that combined all four industries returned only 19 rows with filter_values_truncated and residual_scan_limit_reached, so it was split — the discarded attempt is still on the Coverage screen. One POST /v1/accounts/lookalikes call off the 20 clearest examples returned 500 companies, exactly its maximum, so the long tail is capped by the API and not by the category; 493 were new. Momentum came from one discovery run over the 76-company Computer and Network Security sub-segment, six of the workspace’s ten onboarded signals and a 90-day lookback: it settled with 76 of 76 accounts finished, no blocked signals, and narrowed 749 raw source results to 35 events at 24 accounts.
No human was available for the inputs, so the category, the momentum sub-segment and the 20 seeds were chosen here and are listed on the About screen. 462 of the 538 companies carry no momentum score — that is the bounded half of the job, and the treemap paints them grey to keep “not measured” apart from a measured zero. Lookalikes cannot be filtered on funding stage, so their Series B+ status is unverified and they are tagged as such. Every “Push to Salesforce” button is a preview: no CRM is connected, so it raises a toast naming what would have been sent. CSV export is real and client-side. brandFromWorkspace gave all three Gong colours a role with nothing left out, and reported four readability adjustments that the About screen prints verbatim.
More recipes
Board
Supabase Problem-intent board
Finds people posting about the problem you solve and drafts an opener that quotes their own words.
You provide: The problem you solve, in your own words
List
Vercel CSV contact enrichment
Turns a CSV of names and companies into people with title, LinkedIn, location, work email and an angle to lead with.
You provide: A CSV of names and companies
Brief
Ramp Pre-call dossier
Puts everything worth knowing about one prospect on one screen, with five bullets to read before the call.
You provide: A person's name and company, or an email address