Argus — Autonomous Intelligence Agent

Describe what you want to stay ahead of, in plain English. Argus figures out what to watch, gathers from the right public sources on a schedule, remembers what it already told you, reasons over what changed, and delivers a prioritized, cited briefing: the few things that matter this cycle and what to do about them.

Named after the hundred-eyed giant who never slept. One agent, a hundred eyes on everything you care about.

It's not a competitor monitor, a risk monitor, or a market researcher — it's all of them, because those are just different missions. And it's the brain of a nervous system: it can orchestrate specialized actors as "organs", or research directly.

Quick start

1. Fill in the input — set the fields in the input tab (prefilled with a working example).
2. Click Start — the Actor runs and writes one record per item to the dataset.
3. Get your data — export to JSON, CSV or Excel, or pull it via the API.

What makes it different

• Universal — any monitoring job, defined in natural language. One actor, any domain.
• Stateful memory — it keeps per-mission memory across scheduled runs, so it says "the three things that matter" instead of repeating the same list every cycle.
• Materiality, not noise — the reasoning core surfaces only what's material to your mission, with a recommended action and sources on every finding.
• Agent-native — callable by other AI agents via Apify's MCP server, and able to orchestrate other actors as sub-runs.

How it works

Mission (plain English) → Plan (which capabilities to invoke) → Gather (web research + optional actor organs) → Remember (per-mission state) → Reason (diff vs. memory, rank by materiality) → Brief (prioritized, cited) → deliver to dataset / webhook / MCP.

Capabilities (organs)

Built-in: live web research. With useActors on, Argus can also invoke: Competitor Pulse, Analyst Agent, Sentinel (sanctions/adverse media), Equity Analyst, Signal Radar, AI Share of Voice — as sub-runs, then synthesize their output into one briefing.

Input

Field	Type	Description
mission	string	Plain-English description of what to watch. Required.
missionId	string	Stable ID → Argus keeps memory per mission across runs (defaults to a slug of the mission).
useActors	boolean	Let Argus orchestrate the specialized actors as organs (default false = web research only).
maxCapabilities	integer	Cost cap — capabilities per cycle (default 4).

{
  "mission": "Keep me ahead of competitors Linear and Asana, and watch the project-management market for new entrants.",
  "missionId": "pm-watch",
  "useActors": true
}

Output

One briefing record per run: headline, findings[] (title, detail, severity, isNew, recommendedAction, sources), newFindings count, dismissed noise, and capabilitiesUsed.

Pricing (pay-per-event)

Event	When	Price
mission-cycle	per scheduled run (plan + reason)	$0.25
capability-run	per capability invoked	$0.15
material-finding	per NEW material finding surfaced	$0.20
briefing-generated	per delivered briefing	$0.50

Who it's for

Founders, strategy/competitive-intelligence teams, analysts, investors, compliance teams — and AI agents that need a standing, cited intelligence feed as a tool.

Notes

• Requires an OpenAI API key (OPENAI_API_KEY).
• Schedule it (daily/weekly) with a stable missionId so its memory compounds and it only reports what's new.

Related actors

• Signal Radar — AI Account Intelligence & ICP Scoring — Turn company domains into ICP-scored, signal-tagged account intelligence from public
• Analyst Agent — Autonomous Research & Monitoring — Give it a question; get a structured, cited analyst-grade report. Plans sub-questions
• Competitor Pulse — AI Competitor Intelligence Monitor — Watch competitors holistically — pricing, website, hiring, tech, news and