The Account Management Agent

The AI agent that researches each customer account and keeps its overview, health, sentiment, intelligence feed, and opportunities current

The Account Management Agent is the engine behind Customer Intelligence. Run it on a customer and it researches the account end to end — reading your CRM context, linked delivery projects, and existing intelligence, then augmenting with live web research — and writes back a refreshed account overview, health score, sentiment, signals, alerts, milestones, contacts, and revenue opportunities.

Account research on demand: Instead of an account manager spending an afternoon piecing together the state of "Acme Corp," they click run. Minutes later the account has a current overview, a health score with rationale, three new evidence-backed signals, and two scored expansion opportunities — each citing its source.

What the Agent Does

The agent treats each customer as an account of your organization and reasons about retention and growth from that perspective. In a single run it:

• Reviews the account's linked projects for delivery reality (status, meetings, tasks, documents)

• Reads existing intelligence already on file so it doesn't repeat itself

• Researches the company on the open web for recent, public signals (news, funding, leadership, hiring, product)

• Records signals, alerts, and milestones — each backed by a source

• Captures relevant contacts it discovers

• Writes an updated account overview

• Assesses customer sentiment (0-100 with rationale)

• Computes a health score

• Surfaces revenue opportunities with type, value, confidence, and a recommended action

Running the Agent

The agent runs per customer, on demand. When triggered, it kicks off as a background task so the request returns immediately — the run continues server-side and results appear on the account as they're written.

Runs are asynchronous. A run does real research and tool use, so it takes time. You don't need to wait on the page — refresh the account to see updated intelligence, and the account team receives a digest when the run completes (see Notifications & Digests).

What the Agent Gathers

Source	What It Provides
Linked projects	Delivery status, meetings, tasks, documents — the engagement reality behind the relationship
Existing intelligence	Prior signals and opportunities, so findings build on what's known
CRM context	Account, contact, and pipeline data synced from your CRM
Web research	Recent public information about the company
Assigned integrations	Any integrations assigned to the customer become part of the agent's tool surface for the run

Project-Aware Research

If a customer has linked Projects, the agent can search them as first-class delivery evidence. When an account has multiple linked projects, the agent can search every linked project — selecting which project to look in as it researches — so delivery context across the whole relationship informs the account picture.

Integration Scoping

Integrations assigned to a customer become available to the agent during the run, scoped to what the triggering user is authorized to use. This lets a run reach systems like CRM or collaboration tools where relevant, without ever exceeding the user's own permissions.

What the Agent Produces

Output	Where It Appears
Account overview	Customer detail Overview tab
Health score	Overview tile and the portfolio roster
Customer sentiment	Overview tile (with rationale) and the roster
Signals / Alerts / Milestones	Intelligence Feed
Contacts	Connections on the account
Opportunities	Opportunities tab

How health is calculated from these outputs — and how much sentiment, alerts, milestones, delivery, and pipeline each count — is configurable. See Health Score & Scoring Settings.

Next Steps

Goal	Documentation
Read what the agent records	Intelligence Feed
Work the opportunities it finds	Opportunities
Configure how health is scored	Health Score & Scoring Settings
Learn about AI agents generally	Agents