Relevance AI
Relevance AI
Google CalendarGmailHubSpotSlack

Scheduling that makes the judgment calls

The Meeting Scheduler books qualified meetings in minutes, decides whose time bends when calendars collide, and holds the booking when a request does not qualify.

Demo requested on website
Meeting Scheduler

New demo request from Sarah at Ridgeline. Checking who is asking before I book.

Looking up the account and its owner2s

Known account, mid-market ICP fit, owned by Alex. This one deserves a fast booking.

Reading both calendars for mutual availability3s
Proposing three times to Sarah2s

Sarah picked Thursday 2pm and asked to add four colleagues, including their VP Eng.

Sending the invite to all 5 guests with agenda1s
Booked: Thursday 2pm, 45 minutes, all 5 stakeholders invited including their VP Eng. The invite carries the agenda and the Zoom link, the CRM shows the meeting on the deal, and I will chase anyone who has not accepted by Wednesday morning.

How it works

Demo requested on websiteReply: “yes, let’s talk”Lead hit MQL thresholdRep: “book Ridgeline this week”
Booked · Thu 2pm · 5 guestsMeeting logged on the dealReconfirm set · Wed 9amDoubtful request flagged

Triggered by demo requests and email

Website demo requests, reply emails and handoffs from other agents all start a booking run within minutes of arriving.

Decides what a booking link cannot

It qualifies who is asking, weighs whose presence matters, and when calendars collide it decides whose time bends, asking before it moves anything.

Books into your calendar and CRM

Invites go out with agenda and link, the meeting is logged on the deal, and unaccepted invites get chased so booked means attended.

Without Relevance

With Relevance

A demo request waits hours for a rep to notice, then days of back-and-forth.

The agent replies within minutes and has the meeting on both calendars the same day.

“Does Tuesday work?” threads that run five emails deep.

The agent reads both calendars, proposes times that genuinely work, and confirms in one exchange.

Five attendees, three timezones, and a rep playing calendar Tetris.

The agent weighs whose presence matters most and finds the slot the decision-makers can actually make.

A booking link happily double-books the rep or grabs their focus block.

When calendars collide, the agent decides whose time bends, and it knows a renewal outranks an internal sync.

Meetings quietly die because nobody reconfirmed.

The agent chases unaccepted invites and reconfirms the day before, so booked means attended.

A booking link books anyone: students, competitors, spam.

The agent checks who is asking before it books, and flags the doubtful ones instead of filling the calendar.

Held to a quality bar, on every run

Every booking is checked against eval test cases before an invite goes out. If a run fails the bar, it never ships.

Meeting Scheduler

Pass rate · last 14 days

Sampling 2% of live runs · 95% passing this week

Qualifies before it books96%
Conflicts resolve by deal weight93%
Timezones are never fumbled94%
Booked means reconfirmed91%

Train your agent like an employee

Onboard it with your playbooks and correct it in plain English. It learns the lesson for good, and nothing changes until you approve it.

Meeting Scheduler
Instructions updated
Tool added
Timezone and availability lookup
13 evals added
Qualifies before it booksConflicts resolve by deal weight+11 more
Publish version 4
PDFScheduling Rules.pdf240 KB
Book meetings the way our RevOps team runs the calendar.
Read Scheduling Rules.pdf. Updated my instructions, added a timezone and availability lookup tool, and wrote 12 evals to check every run.
Never bump an internal meeting for a first discovery call. Only renewals and late-stage deals outrank internals.
Understood. I updated the conflict eval, so a run that moves an internal for an early-stage discovery now fails.
Teach it something new…
Ask

Built for enterprise teams

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

Monitoring

Real-time visibility into every agent’s activity, performance, and cost.

RBAC

Control who can use, build, edit, and deploy agents.

Data residency

Multi-region deployment keeps your data within your required geography.

Version control

Full version history on every agent. Roll back to any previous state.

Audit logs

Every action, every decision, every tool call logged and exportable.

Human-in-the-loop

Set approval gates on any action or allow agents to ask questions.

SSO / SAML

Enterprise single sign-on with SAML 2.0. Centralize identity & access.

PII masking

Detect and redact personally identifiable information.

SOC 2 Type IIGDPROTEL & Delta Sharing
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 sales agents

Web
News
Hiring
Funding
New account

Research & Enricher

Researches prospects from live, dynamic sources.

$48k ARR · renews soon
Raised SSO last call
Evaluating 2 competitors
Champion: VP Eng

Pre-meeting Prepper

Surfaces context for reps before every meeting.

Call ended
  1. 1
    Logged call notes
  2. 2
    Sent pricing PDF
  3. CRM stage updated

Post-call Actioner

Logs notes and fires follow-ups after each call.

Hi Sarah, saw Ridgeline just closed its Series B. Scaling support headcount fast?

EmailLinkedIn

Outbound Prospector

Personalizes multi-channel prospect engagement.

$1.2M
Commit
$2.0M
Best
$4.8M
Pipeline
Commit call · $8.0M

Forecast Roll-up

Rolls deal signals into a clear pipeline call.

Budget confirmed
Timeline agreed
Legal review pending
Advance to close

Deal Reviewer

Reviews deals against criteria and flags any risk.

Ridgeline AI

Proposal Builder

Drafts tailored proposals and quotes in minutes.

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
  • Chained into multi-step processeslike n8n
  • Kept alive through long-running worklike Temporal
  • Traced at every step of every runlike Langfuse

Put the Meeting Scheduler 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.