The intent leaderboard
A ranked intent leaderboard of 81 real Trayo accounts that fired two or more distinct ICP signals in the last 90 days, each row showing the actual job-change events as proof.
- Built in
- 28 min
- Capabilities
- 6
- Live API calls
- 40
The prompt
Paste it into any coding agent with the Trayo MCP connected.
- + any MCP client
Use Trayo to build an intent leaderboard. Let me set a target number of companies, then keep working until you find that many companies with two or more distinct signal events in the last 90 days — one event is noise, two is a pattern. Define the signals from my ICP, run discovery across candidate accounts, and keep widening the candidate set until the target is met or you can show me you have exhausted what is findable. Rank by how many distinct events fired and how recent they are. Every row shows the actual events as proof, never a score alone. Tell me plainly if you stopped short of the target and why.
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.
- Researches an account
A live snapshot per company — size, stack, why-now signals and why it fits.
- Finds the right people
Named stakeholders at an account, matched to the buying roles you care about.
- 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.
Take the tour
The same run as the video above, one stop at a time.
- 01
Today we're building an intent leaderboard for Wiz's sellers. It ranks any account in our Trayo workspace that fired two or more distinct buying signals in ninety days, because one event is noise and two is a pattern. Every row shows its proof.
- 02
Here's the leaderboard itself, built from those moves.
- 03
Ten ICP rules over the new title and the employer left behind produced 637 signal events at 156 accounts. 81 cleared the two-signal bar.
- 04
Salesforce sits on top with eight signals. Open the row and you get the full event list, and Trayo's why-now research.
- 05
Who to call comes from Trayo's stakeholder search, so the row ends with actual people.
- 06
Push to Salesforce is a stub, tagged demo. The toast says exactly what would have been sent.
How it was built
The data behind each screen, and what's faked for the demo.
A Wiz seller sitting down to plan their week, or getting ready to work a named account, opens this and sees a ranked list of accounts where something has actually happened. Each row shows how many distinct buying signals fired in the last 90 days, and underneath it the events themselves: the person who moved, their new title, the employer they left and the date Trayo detected it. Opening a row gives the full event list, Trayo’s “why now” research and the stakeholders to call. The rule behind the list is that one event is noise and two is a pattern, so nothing appears unless at least two distinct signals fired.
It replaces the routine of checking a handful of tabs and a spreadsheet to guess which accounts are worth a call this week. Nobody has to read job-change feeds account by account, decide what counts as a security hire, and then remember to redo it a month later. The ranking is by number of distinct signals, then by how recent the newest one is. Every row shows its evidence, so the seller can judge a claim for themselves instead of trusting a score.
I started from the workspace. GET /v1/workspace returned a saved Wiz buyer profile and ten signal definitions, so I didn’t have to invent an ICP. POST /v1/find turned that profile into a pool of 1,000 companies, and I imported 382 of them as accounts, spread evenly across the size range so I wasn’t only taking the largest names. Then I ran Trayo’s discovery with the workspace’s own ten signals over all 382 accounts on a 90-day window. Both runs settled with zero events, no error, and nothing in blockedSignals. I created three deliberately broad replacement signals (any security job posting, any company news, any director-level joiner) and ran them over brand-new accounts with a 365-day window, over both MCP and POST /v1/discoveries. Those settled in three seconds, also empty, on a workspace where monitoring.enabled is false. So I switched to people movement. POST /v1/job-changes/search, run once per account at director level and above, returned 6,131 real moves inside the window. I wrote ten ICP rules over the new title and the employer the person left, and they turned those moves into 637 signal events at 156 accounts. 81 of those accounts cleared the two-signal bar, against a target of 12. Salesforce, Capital One, Barclays and Fiserv lead with eight signals each. For the top 14 I ran POST /v1/stakeholders/search and POST /v1/research/company, and I saved the top 12 back to a Trayo list.
The limits are these. Trayo’s discovery never produced anything for me, so every signal on the page comes from a single source: hiring and executive movement. The leaderboard is blind to breaches, migration announcements and open job postings. Push to Salesforce, share to Slack, draft email and book a meeting are stubs. Each is tagged “demo”, and clicking one shows a toast stating exactly what would have been sent. The job-change events, the signals built from them, the research, the stakeholders and the saved list are real Trayo data from a real workspace.