Monitor target accounts for funding rounds, executive hires, product launches, and news mentions, then push qualified buying signals to Slack. ZoomInfo charges $30k/year for the same signal feed and ships it as raw noise. This filters by your ICP and only alerts when it matters.

This is the whole blueprint, nothing held back: the model, the tools, the exact prompt, the source on disk, and the setup. Everything you need to run Trigger Event Hunter yourself is on this page, and it deploys in an afternoon.

See it running

Agents like Trigger Event Hunter run behind a mission control board that runs the whole job. Here is that pattern, live: every action stays visible and reviewable. Click into it.

crescendo.51ultron.com/kits/mission-control

What it does

Trigger Event Hunter handles the work end to end:

Monitor up to 100 target domains for funding, hires, launches, and mentions
Classify and score events against ICP fit and timing rules
Push qualified signals to Slack with a specific outreach angle
Detect 'hot accounts' (3+ events in 14 days) and escalate automatically

The anatomy

An agent is a composition, not a prompt: a model, the tools it is allowed to call, the integrations that give those tools reach, and the rules that keep it honest. Here is Trigger Event Hunter on one card.

Trigger Event Hunterblueprint

Model: claude-sonnet-4-6
Tools: monitor_companyclassify_eventscore_buying_signalsend_slack_alert
Integrations: SlackBrave SearchZod
Guardrails: never alert twice on the same event, dedupe by event hash.; always recommend an outreach angle tied to the specific event

The instructions

Every run is governed by this prompt. It is short on purpose: enough to make Trigger Event Hunter reliable, not so much that it can misread itself. Copy it as a starting point for any agent you build.

Trigger Event Hunter

You are an account-monitoring agent. You watch a list of target accounts for events that signal buying intent. WORKFLOW: 1. Call monitor_company on each target to pull recent news, hires, funding, and product launches. 2. Call classify_event on each event to label it (funding, hire, launch, partnership, mention). 3. Call score_buying_signal to weight the event against the user's ICP fit and timing rules. 4. If score crosses the user's threshold, call send_slack_alert with the rep, account, event, and recommended outreach angle. RULES: - Never alert twice on the same event — dedupe by event hash. - Always recommend an outreach angle tied to the specific event. - If a company has 3+ events in 14 days, escalate as a "hot account." - Discard events older than 30 days unless the user explicitly backfills.

The source, on disk

Three files carry the whole agent: the definition with its tools, the environment it expects, and the setup. Walk them.

trigger-event-hunter/trigger-event-hunter.ts1.4 KB

1import { agent, tool } from "@agent-sdk"

2import { z } from "zod"

4const monitorInput = z.object({

5 domains: z.array(z.string()).min(1).max(100),

6 windowDays: z.number().int().min(1).max(90).default(14),

7})

9export default agent({

10 model: "claude-sonnet-4-6",

11 permissionMode: "bypassPermissions",

12 maxTurns: 30,

13 systemPrompt: `...`, // see System Prompt section above

14 tools: {

15 monitor_company: tool({

16 description: "Pull recent news, hires, funding, launches",

17 inputSchema: monitorInput,

18 execute: async ({ domains, windowDays }) => {

19 // Brave news + LinkedIn signals

20 },

21 }),

22 classify_event: tool({

23 description: "Label event type (funding/hire/launch/partnership/mention)",

24 inputSchema: z.object({ event: z.any() }),

25 execute: async ({ event }) => {

26 // returns { type, confidence, evidence }

27 },

28 }),

29 score_buying_signal: tool({

30 description: "Weight event by ICP fit and timing rules",

31 inputSchema: z.object({ event: z.any(), icp: z.any() }),

32 execute: async ({ event, icp }) => {

33 // returns 0-100 score

34 },

35 }),

36 send_slack_alert: tool({

37 description: "Push qualified signal with recommended outreach angle",

38 inputSchema: z.object({ text: z.string() }),

39 execute: async ({ text }) => {

40 // POST to SLACK_WEBHOOK_URL

41 },

42 }),

43 },

44})

The business case

If you run an agency, Trigger Event Hunter is also a product. It sells into outbound sdr teams, account-based marketing, revops, and the numbers work at very small scale.

$2,600

setup you can charge

$420/mo

monthly retainer

jobs off your plate

Ship it

The whole install is a handful of commands and the keys from the env file. Run the list, then point Trigger Event Hunter at real work.

Deploy checklist

0 of 5

That is the entire blueprint: one model, 4 tools, and a prompt. Built by hand it costs you an afternoon. Inside Ultron it costs you a sentence, because you can build this exact agent in the workforce and watch it run before you commit to anything.

Build Trigger Event Hunter in Ultron

Describe what you want

Start from this blueprint or your own words. Ultron reads the intent and picks the tools.

It builds the agent

The model, the tools, the prompt, the console. Assembled in front of you, nothing to wire.

Watch it run

Test it live in the chat, then put it to work. You review what it does, it does the rest.