AI Agents & Automation

What each AI agent does, the signals it reads, what it produces, and the human-in-the-loop controls you have over it.

How Velsano AI agents work

The three kinds of AI in the app — scheduled agents, on-signal agents, and on-request Copilot — and the human-in-the-loop model that keeps you in control.

Read the full guide →

Portfolio Intelligence Agent

Synthesizes many signals across your book and reasons about which accounts truly need intervention — not just threshold alerts.

Read the full guide →

Account Strategy Agent

Proactively builds 90-day account plans for accounts that have gone too long without a strategic review.

Read the full guide →

Predictive Intelligence (churn prediction)

Explainable churn prediction with transparent risk drivers and cross-account similarity — it can flag risk before health visibly drops.

Read the full guide →

Conversation Intelligence

Reads call transcripts and email threads to extract summaries, sentiment, action items, risk flags, and competitor mentions.

Read the full guide →

QBR Prep

Auto-drafts QBR sections about two weeks before each scheduled review, then hands them to you to finish.

Read the full guide →

Milestone Intelligence

Infers when AI-tracked milestones have likely been reached and queues them for your confirmation.

Read the full guide →

Predictive Risk Signal (legacy)

A narrower signal that flags accounts where the churn score is high but the visible health score still looks fine.

Read the full guide →

The full agent roster

Every governable AI agent at a glance, including the renewal, stakeholder, expansion, and VoC agents.

Read the full guide →

Autonomy & work styles

How much an agent does unattended — set by the account coverage model and CSM work style.

Read the full guide →

← Back to all docs