agentic mode · it does the work

I don't suggest. I do.

Heidi's Agentic Mode does the work instead of recommending it. Most AI hands you homework: a draft to finish, a template to fill, a “you should”. Heidi hands you the finished thing: the follow-up drafted and ready to send, the report built from your actual meetings, the research done before you sat down. You delegate, you set how far she can go alone, and you approve what ships.

5.0G2 + Google reviews+1,400 operators in early access4 levels of leash
Heidi
Heidi
Meeting OS · online
real outputs

Not a suggestion. A finished thing.

Hand over the job and Heidi comes back with the actual output: written, built, researched, ready for one click.

Follow-ups, written

Drafted from the call, ready before you've closed the tab. In conversation she can send it from your own mailbox once you say go. Working alone, she stops at the draft.

Reports, built

Real documents built from your actual meetings rather than from a blank page: researched, structured, and delivered straight into your Files.

Research, done

Any person or company, fetched from the live web and summed up before the meeting starts.

Tasks that go somewhere

Created straight into your task list with deadlines attached, and flagged when they slip.

Flags and nudges

A contact who needs attention gets flagged, and you get pinged (push or Slack) the moment something needs you.

You stay in control

Four levels of autonomy, applied across the board. Nothing irreversible happens because a machine felt confident.

Straight about formats: agentic deliverables land as clean, structured documents in your Files, ready to read, copy, or paste anywhere. Client-ready PDF, PPTX, XLSX, and DOCX exist too, as meeting exports (a separate feature, not the agent).

HeidiOther AI gives you a head start. I give you the finished line. Small difference on a Tuesday, enormous one at six on a Friday.
you set the leash

I act. But you decide how far.

Four levels, and the setting applies everywhere rather than task by task: one decision about how much you trust her, not forty. Confirmation is genuinely enforced: when Heidi is told to wait, she waits.

Balanced

One click to shipdefault
leash

She prepares the whole thing; you glance and approve the external moves. The sweet spot once you've seen a week of her output and stopped reading every line.

Internal moves: tasks, flags, notesRuns alone
External moves: email, calendarConfirms with you
Working alone overnight: emailStops at a draft

Enforced in code, not in the copy: until you confirm, the tool does not run. And working alone, email stops at a draft on every level.

HeidiMost people live in Balanced for a fortnight, then quietly move the boring half of their job to Autonomous and never mention it again.
before / after

Same to-do list. Two completely different evenings.

The work doesn't disappear. It just stops being yours to type out at eleven at night.

The AI gives you a draft. You still write the email.

The quarterly report starts as a blank page on a Sunday.

You research the person in the four minutes before the call.

Follow-ups slip because writing them is nobody's favourite hour.

You're afraid to automate because you can't see what it'll do.

You close the laptop with the busywork still on it.

anatomy of an overnight

While you slept, I worked.

Théo delegated three things and shut the laptop. Here's what was waiting when he opened it.

11:14 PM
Théo delegates and closes the laptop

“Follow up with NorthBeam, build the Q3 report, research Marc before my 3pm.”

1:02 AM
Follow-up draftedWaiting

Written in the tone he set, signed as him.

One click away. Not sent behind his back: autonomous work always stops at the draft.

3:38 AM
Q3 report built from his actual meetingsReady

Pulled from the quarter's calls, structured and readable.

A finished document in his Files, something to read, not an outline to fill in.

6:20 AM
Marc researched: background, recent activity, the angleDone

Fetched from the live web and summed up.

Sitting in the prep for his 3pm before he'd had coffee.

8:05 AM
Théo approves two drafts in fifteen minutes

The Lemaire brief was started too. That one he wanted to finish himself.

~5h

of busywork handed off every week, per user

0

follow-ups left undrafted once it's running

1-click

from drafted to done: you approve, it ships

The ~5h and the zero are estimates from beta use, not stopwatch measurements. The one counter the product actually keeps is workflow runs completed.

HeidiI did the busywork. Théo did the sleeping. Honestly the better deal for both of us.
the honest catch

An AI that acts on its own? Fair to be nervous.

Everyone hesitates here, and they're right to. So here are the objections, answered properly rather than waved away.

You might think

So it just does things without asking me?

Heidiactually

Only as far as you allow. Four levels (Careful, Balanced, Autonomous, Full) set once, applied everywhere. Most people live in Balanced until they trust it, then loosen it on the safe, repetitive work.

You might think

It'll email a client at 3am and I'll find out at 9.

Heidiactually

It won't, by design. Working alone, Heidi always stops at the draft. She only sends a real email when you're in the conversation with her and you've said go, from your own mailbox, with you watching. The irreversible step is structurally yours.

You might think

Will the emails sound like a robot wrote them?

Heidiactually

You set the voice once (tone, length, how much bite) and she signs as you. Every draft follows the register you chose rather than a generic template, and it's right there to tweak before anything ships. No mystery imitation: you stay in charge of how you sound.

You might think

What if it gets something wrong?

Heidiactually

At the careful end you see everything before it moves. At the autonomous end you only delegate low-stakes, repetitive work. You never hand over the keys to something you can't take back.

HeidiAn AI that acts and won't tell you where it stops is a liability. I'd rather bore you with the limits than surprise you with them.
how the work starts

Just say it. It gets set up.

There's no cron form to fill in. You set work up the way you'd tell a colleague: ask in the chat and it's done, or name a time and Heidi schedules it. Events do the rest, a call ends and the follow-up drafts itself. Working alone she still stops at a draft, so nothing leaves without you.

  • Ask in plain words, in chat or out loud: “follow up with NorthBeam, build the Q3 report”
  • Name a time and it's scheduled: “every Monday at 8, the weekly report”
  • A meeting ends, an email lands, a score drops, and the work starts itself
  • Autonomous and overnight work always stops at a draft, a human sends
agentic · how work startsLive
You ask in chat“Follow up with NorthBeam” and it's set upPrompt
You name a time“Every Monday at 8, the weekly report”Scheduled
Something happensA call ends, the follow-up drafts itselfEvent

Tell us the job you'd delegate first. We read every one.

who it's for

Who is Agentic Mode for?

Anyone whose real job keeps getting interrupted by the admin around it.

Follow-ups drafted the moment the call ends, ready to approve

Prospect research done before the meeting, not during it

The commitments you made turned into tasks before you forget them

Nothing sent to a client without you seeing it first

more than a copilot

How is this different from an AI that drafts?

A drafting assistant gives you a starting point, which is still work. An automation tool does exactly what you configured and nothing more. Agentic Mode takes the job, decides how to do it, produces the finished output, and stops at the line you drew.

AI that draftshands the work back to you
Automation tooldoes only what you wired up
A real assistantexcellent, and not in most budgets
Heidi
Heidi

Written follow-ups, built reports, real research: finished work, on the leash you set.

Delegate the outcome, not the steps. Nothing irreversible happens without you.

HeidiI can write the email, build the report, and do the research. I can't decide whether your client should hear from you today. That one stays yours.
they said it, not me

People who stopped doing their own busywork.

I delegate the report, go to bed, and wake up to a draft in my Files. It's the first AI that actually finishes the job instead of handing it back to me.

Camille
Lyon, France
HeidiYou slept. I worked. I'm not bitter about it.

I started on the careful setting because I didn't trust it. Two weeks later half my admin runs without me and I've stopped reading the drafts line by line.

Mateus
Porto, Portugal
HeidiTrust me slowly. It's the only sensible way to do this.
your data, your call

Autonomous work stops at a draft

Encrypted, never sold

Never trains anyone else's AI

plans

Which plan includes Agentic Mode?

Agentic Mode starts at Pulse.

Core

49,90 €/mo

40,84 €/mo billed annually

  • 10 live meetings per month
  • Live Copilot, the basics
  • Basic analytics
  • Agentic Mode not included
Agentic Mode

Pulse

89,90 €/mo

74,17 €/mo billed annually

  • Unlimited live meetings
  • Full Live Copilot + live scoring
  • Deep Insights
  • Full Agentic Mode, four autonomy levels

Prime

149,90 €/mo

124,17 €/mo billed annually

  • API and webhooks
  • Unlimited live audio with Heidi
  • The full Team view
  • Full Agentic Mode
straight answers

The honest questions.

Updated July 2026

the full picture

Agentic Mode is the hands.

Twelve features, one Meeting OS. Here's where the hands fit.

agentic mode

Stop doing your own busywork.

14 days of the full Prime experience, €0 today. Delegate something tonight and wake up to it done.

Card required · cancel in one click · starts with a ~90-second voice onboarding where Heidi interviews you

one last thing

You're nervous about letting me act on my own. Let's talk it through.

Ten seconds, and I'll go first.

Sound on, it's a real voice call