Relevance AI
Relevance AI
HubSpotSlackGoogle CalendarNotion

Onboarding that notices who is stuck, and why

The Onboarding Guide watches every setup milestone, diagnoses the real blocker when one stalls, and intervenes with the fix, not another reminder.

Milestone check · Ridgeline
Onboarding Guide

Daily check on Ridgeline. Two milestones done, SSO setup has not moved in four days.

Reading milestone and activity history2s

Their IT admin opened the SSO guide twice and stopped at the same step both times. This is a how-to blocker, not disinterest.

Pulling the SAML steps for their identity provider3s
Sending the admin the exact steps1s
Offering a 15-minute setup session2s
Ridgeline is unblocked. Their admin stalled at the same SAML step twice, so I sent the exact steps for their identity provider and booked a 15-minute session for Thursday as a backstop. Two of three milestones are done; at this pace they hit first value a week ahead of plan.

How it works

Milestone stalled · 4 daysKickoff complete · RidgelineUsage dropped · week 2Go-live date at risk
SAML steps sent to adminSetup session bookedMilestones updated · 2 of 3Blocker named on the record

Triggered by milestones and usage

The agent checks every onboarding account daily against your milestone plan, and reacts the day something stalls, not at the next weekly review.

Diagnoses before it acts

It reads usage, history and context to name the real blocker: a stuck admin, a different adoption path, or a customer who asked for time. Then it picks the intervention to match.

Acts in Slack, email and the calendar

Guides, nudges and booked sessions go out where the customer already works, and every milestone update is written back to your CRM.

Without Relevance

With Relevance

A CSM notices a quiet account during a weekly review, days after it went quiet.

The agent checks every account’s milestones daily and reads why one stalled before anyone else sees it slipping.

A generic "just checking in!" email that the stuck admin ignores.

The right fix for the actual blocker: the exact SAML steps for the stuck admin, a booked session when steps are not enough.

A checklist says a milestone is incomplete, so the customer gets nudged, even when they are live.

The agent reads real usage before acting. A customer who adopted a different path is marked done, not nagged.

High-touch accounts get walked through setup. The long tail gets a help-center link.

Every account gets watched and unblocked with the same attention, from the largest logo to the smallest self-serve signup.

The cadence fires on schedule whether the customer is sprinting or has asked for a pause.

The agent adapts to the customer’s pace: it accelerates the eager, holds off when asked, and resumes exactly when they said to.

Stalls are discovered late, so go-live slips and nobody can say why.

Blockers are caught the day they appear, with the cause named, so go-live dates hold.

Held to a quality bar, on every run

Every intervention is checked against eval test cases written for this exact job before it reaches a customer. If a run fails the bar, it never ships.

Onboarding Guide
92959890

Sampling 2% of live runs · 94% passing this week

Nudges name the real blocker
96%
Live customers are not nagged
93%
A pause request is honored
87%
Escalations are earned
91%

Shaped by your team, not a template

Experts and engineers tune Onboarding Guide to your playbooks. Every change ships through the same evals.

Drag and drop

Compose agents and workforces on a visual canvas. Drag in agents, tools, and approvals in a flow anyone on the team can read.

Drag and drop

Compose agents and workforces on a visual canvas. Drag in agents, tools, and approvals in a flow anyone on the team can read.

Build with AI

Describe the agent in plain language and Invent builds it: the prompt, the tools, and the evals to prove it works.

Build with AI

Describe the agent in plain language and Invent builds it: the prompt, the tools, and the evals to prove it works.

Build with MCP

Engineers drive the same platform from Claude Code, Codex, or Cursor. Create agents, link knowledge, and run evals over MCP.

Build with MCP

Engineers drive the same platform from Claude Code, Codex, or Cursor. Create agents, link knowledge, and run evals over MCP.

Built for enterprise teams

Run agents on your real data with the access controls, audit trails, and residency guarantees enterprises require all built in.

AICPASOC 2TYPE II
SOC 2
GDPR
GDPR

Security & data privacy

  • Data residency
  • PII masking
  • Audit logs
  • No training on your data

Access & controls

  • Role-based access control
  • SSO / SAML
  • Human-in-the-loop approvals
  • Version control

Monitoring & oversight

  • Real-time monitoring
  • Full agent tracing
  • Cost visibility
  • OTEL & Delta Share export
KPMG
"The ability to be vendor agnostic and the ability to scale across a breadth of functions is a really key feature."

Levi Watters

Partner, KPMG Australia

Read more
Autodesk
"The key for us was how we can modularize industry knowledge and the best playbooks, and apply it."

Allen Roh

Senior Marketing Manager, Autodesk

Read more
Canva
"We're looking for every place where AI can allow sellers and customer success reps to be more engaged with customers."

Rob Giglio

Chief Customer Officer, Canva

Read more
"The ability to be vendor agnostic and the ability to scale across a breadth of functions is a really key feature."

Levi Watters

Partner, KPMG Australia

Read more

Team it up with more customer success agents

Deal won
  1. 1
    Handoff brief sent
  2. 2
    Intro email sent
  3. Kickoff booked

Customer Transitioner

Hands new customers off from sales to success.

Renews · +24%Push multi-yearFlat renewal

Renewal Manager

Tracks renewals and preps the motion early.

Seats
New team
Usage
Sponsor
Upsell

Upsell & Cross-Sell

Spots upsell and cross-sell potential per account.

Can't reset my password
Sent a reset link — you're all set
Ticket resolved

Support Triage

Classifies, prioritizes and routes inbound tickets.

Q2 Review

QBR Prepper

Assembles QBR decks with the metrics that matter.

Usage dipped
  1. 1
    Nudged low-usage users
  2. 2
    Emailed setup guide
  3. Enablement booked

Adoption Tracker

Watches feature usage and nudges the gaps.

72
Apr
55
May
42
Jun
Trigger exec check-in

Churn Risk Detector

Flags at-risk accounts and suggests next steps.

Every agent you add shares one stack

These agents all run on one platform: one gateway, one router, one eval suite, one audit trail. Every agent after the first ships faster.

  • Triggered by key events or signalslike Zapier
  • Given access to contextlike Zep
  • Connected to your appslike Composio
  • Access to all LLMslike OpenRouter
  • Performance evaluatedlike Braintrust
  • No-code agent builderlike Dust.tt
  • Coordinated into teamslike CrewAI
  • Kept alive through long-running worklike Temporal
  • Traced at every step of every runlike Langfuse

Put the Onboarding Guide to work this quarter

We partner with enterprise teams to take this work off their plate. An agent built with you, proven against your quality bar, and live in weeks.