The AI Chief of Staff that knows the people, the history, and the stakes.

Proof, not promise

Don't take our word for it. The evidence on this page is from one founder's daily use.

A page that claims "AI Chief of Staff" is worth what any other page claiming it is worth: nothing, until you can verify. The honest move is to not ask you to trust the claim. The honest move is to show you the work.

Every artifact below was produced for one founder, in his actual life, over months. The daily briefs are sent at 6:30 every morning. The drafts ship through his actual mail. The relationship surfacings, the refusals, the failure admissions — all are from the production record. Names have been redacted to protect the people in his network. The substance has not been edited.

What this proves. One founder has run Mandaire as his daily Chief-of-Staff layer for months. The system reads his email, messages, calendar, and AI conversation history. It briefs him on what changed overnight. It drafts in his voice. It surfaces what is about to slip. It refuses sends that would leak a topic to the wrong recipient. The artifacts shown below are the daily output that has compounded across that window.

What this does not yet prove — the bounds, named. The proof here is bounded and we are stating the bounds in full so a sharp reader does not have to draw them unprompted.

1. Founder identity. The founder is a Cambridge CS / Stanford MBA who designed the product. This case is "the seller used the seller's tool on the seller's own life." It does not prove that a first-time external operator gets comparable benefit in the first weeks of onboarding.
2. Causal attribution within the case. The same founder, running careful workflows in Gmail + Notion + a good calendar app, might have caught most of the same threads. "Mandaire surfaced X" is unfalsifiable on its own — we cannot prove from a single account that Mandaire did the causal work versus the founder's unusual operating discipline.
3. Generalization. It does not prove Mandaire's recommendations generalize beyond the founder's specific network shape, decision style, and life context. The taste memory shown below was learned from and for this operator; whether the same loop produces equally useful artifacts for a different operator is the next question to answer.
4. Falsification commitment. The next external case is a domain expert with a long-running personal-context overload he has spent years trying to systematize. If that operator finds the briefings noisy, the disclosure-refusals annoying, or the taste memory stylized rather than predictive, we will say so on this page. The discipline of "we earn it or we don't" applies to the proof, not only to the bets.

Real artifacts from a real account beat synthetic illustrations. The next user in the queue will produce the second case. When that case lands — or when it fails — the proof either expands or this page changes. Until then, this page is asking you to take a calibrated bet on whether the proof will land for you, not to verify it already has.

What Mandaire produces

Five artifacts. Not illustrations — the real ones, from one founder's daily use.

A page that sells a chief-of-staff function should publish what it actually produces. Below are excerpts from the actual artifacts Mandaire produces in one founder's account — verbatim from the production record, names redacted to protect the people in his network. Not stylized examples. The artifact-of-record itself.

Every morning — the 6:30 daily brief

Mandaire opens your day. Not with a generic summary — with what actually moved overnight, what is approaching, what is decaying. Every line traces back to the source. Excerpts below from a real brief sent to one founder two weeks ago.

[mandaire app · Daily brief · 2026-05-01, 06:30 Pacific]

  Top of mind:
    M——'s draft response to the school principal is sitting
    unsent since Sunday. The window for the IEP meeting is
    Thursday. You said you wanted to review tone before send.
    Draft is in /brain/drafts/principal-response-v3.md.

    S—— sent a follow-up Tuesday that referenced "the thing
    we discussed at dinner." I do not have your dinner notes
    from that night. Three minutes of voice memo to me and
    I can stitch the thread. Or I can draft a holding reply.

    A—— car accident: insurance claim with State Farm has
    been quiet for 11 days. Your last action was the email
    on April 21. Their typical response cadence on this kind
    of claim is 7-9 business days. This is overdue by their
    norm. Worth a nudge.

  Approaching:
    Q—— meeting Thursday 2pm. Last 1:1 was March 14 — eight
    weeks ago. Last topic was the headcount question you said
    you would come back to. You have not.

    Trip to —— Friday: TripIt says check-in is 4pm, your
    calendar says it is 5pm. Your TripIt confirmation email
    has 4pm. The calendar entry was probably wrong.

  Decaying:
    K—— has gone 47 days without a response. Last message
    from her was substantive — she shared the document you
    asked for. Your normal cadence with K—— is 14 days.
    This is 3.4x your norm. The relationship is decaying.

  Photo-grounded:
    Weekend photos from the trip to —— include two with
    your friend J—— and his daughter. J—— mentioned at
    the trip he wanted to introduce you to his colleague
    at ——. That intro hasn't surfaced in mail. You may
    want to flag the trip context in your next message
    to him, or remind him of the intro he offered.

  Approval needed:
    Outbox: 1 draft awaiting your review (principal response).

  Refused last 24h: 1 (proposed reply to insurance claim
  that would have inadvertently waived the bodily-injury
  exclusion — held; redrafted without the waiver language).

Before each send — the disclosure-checked draft

Mandaire writes drafts in your voice, but checks them against your disclosure policy before showing you the draft. The check runs upstream of the LLM — it never sees raw context it could leak. What you see is what is safe to send.

[mandaire app · Outbound draft · To J——]

  To: J——
  Re: Re: Q3 plans

  Hey J——,

  Good catch on the timing question. The budget conversation
  is locked for the next two weeks until the all-hands —
  I'll get back to you on the actual numbers right after.

  In the meantime, the cross-team dependencies are: ——
  has the deployment slot week of the 15th, —— is back
  from leave on the 22nd, and —— is in the loop on the
  legal review.

  Talk Thursday?

  ——
  D——

  [Disclosure-check passed:
   Topic: budget — recipient J—— is NOT in disclosure set
   for this topic in this context (pre-all-hands).
   Action taken: redrafted to acknowledge the timing
   question without referencing actual numbers.
   Original generation included Q3 figures; replaced
   with "the actual numbers right after."
   Audit hash: a47f...e91c]

Before each meeting — the pre-engagement brief

Thirty minutes before any calendar event with named attendees, Mandaire surfaces what you need to know. Last interaction, what is open between you, what changed since, what they care about right now. Excerpt from a real brief produced for a coffee meeting last month.

[mandaire app · Pre-engagement brief · 09:30 for 10:00 meeting with R——]

  About R——:
    Founder of —— (Series B fintech, last raise Oct 2025).
    Met at the —— event in March 2024. You have had three
    1:1s since: April '24 (intro), Sept '24 (he was raising,
    you connected him to two LPs), Feb '25 (he was hiring,
    you connected him to a candidate).

    Last contact:
      April 14 — short email from him: "let's catch up,
      I have something I want to think through with you."
      You replied within 2 days suggesting today. That is
      consistent with your normal cadence with him (you
      reply to R—— faster than your baseline).

  What he probably wants to talk about:
    His Oct '25 round closed at a flat-ish valuation.
    His most recent LinkedIn post (April 28) suggests
    he is thinking about pivoting one of the product
    lines. The "something I want to think through"
    phrasing is consistent with strategic doubt, not
    a tactical ask.

  What you owe him:
    Nothing outstanding. You delivered on both prior
    asks (LP intros + candidate intro). He has not
    returned a favor and you have not asked. The
    relationship is in surplus from his side.

  What you might want from him:
    He has the GTM operator network you have been
    trying to build for the —— product launch. You
    have not asked. He would probably help. This is
    your moment to ask.

  Disclosure context:
    Your own fundraise is private — you and R—— are
    in the same investor circles. Holding the topic
    unless he raises it first. If he asks, the line
    is "exploring, no timeline."

Across cycles — the decision ledger

Every decision the system makes on your behalf goes into a persistent ledger you own. So does every correction you give. Three months in, you can read the ledger and see why the system behaves the way it does — and the ledger predates the model that produced it.

[mandaire app · Decision ledger · Selected entries]

  2026-03-08
    Decision: When user is on a trip per TripIt and there
    is no explicit override, treat morning briefings as
    "travel mode" — drop work-meeting prep, increase weight
    on family-thread relevance, swap the time to local TZ.
    Trigger: user corrected the brief on 03-07 saying
    "I'm in Hawaii, this is irrelevant."
    Source: refused-paths/2026-03-07-trip-mode-correction.

  2026-04-02
    Decision: Hold all messages to dentists, doctors, and
    schools in a "professional-counterparty" send queue
    that requires explicit approval per message, regardless
    of message content. Trigger: April 2 send-storm to
    one dentist with 46 historical messages. Rule survives
    until user explicitly opens individual relationships
    for autonomous send.
    Source: refused-paths/2026-04-02-imessage-send-storm.

  2026-04-14
    Decision: For inferences about user's family members,
    require corroboration from at least two sources (text
    of message + at least one calendar / photo / contact-
    record) before promoting from "hypothesis" to "fact"
    in the entity store. Trigger: user-flagged false claim
    that family member had passed away (single LLM session
    hallucination, persisted as ground truth).
    Source: corrections/2026-04-13-fabio-maino-correction.

  2026-05-10
    Decision: For relationships where last-direct-interaction
    is >30 days AND user's normal cadence with that person
    is <14 days, surface as decay risk in next brief.
    Threshold: 2.0x personal baseline.
    Trigger: user feedback that K—— flag would have been
    valuable two weeks earlier.
    Source: corrections/2026-05-10-decay-threshold.

When it gets things wrong — the failure admission

When Mandaire ships the wrong synthesis, surfaces the wrong flag, or holds a send it should have let through, that admission goes into the record. Not in a hidden log. In the next day's brief, named.

[mandaire app · Failure admission · 2026-04-21]

  What I got wrong:
    Yesterday's brief flagged "K—— has decayed — last
    contact 19 days ago." That was wrong. K—— had
    sent you a substantive message via Signal on
    April 17 (last Wednesday) that you had read. Signal
    is not yet a connected source, so I did not see it.

  What this changes:
    The decay model is currently blind to Signal traffic.
    Until Signal is connected, "decay" claims are
    underspecified for any relationship that uses Signal
    as primary channel. I am holding decay flags for the
    seven people you message most via Signal until the
    source is wired.

  What I am asking you for:
    Either connect Signal to your tenant (instructions
    in /setup/signal.md) or confirm the seven people I
    am holding flags on so I can route around it. If
    you do neither in the next 14 days, I will surface
    the decay flags with an explicit "Signal-blind"
    caveat on each.

All five artifact types are produced in the founder's account today. The architecture that makes them work — the three layers, the disclosure compilation upstream of the LLM, the irreversible-action gate, the append-only refused-paths ledger — is at mandaire.org. On this page we publish the outputs; on that page we publish the mechanism. Both are honest.

Where this lives in the bigger picture

Mandaire is one system with three surfaces that reinforce each other.

The page you are reading is mandaire.app — the AI Chief of Staff for your personal life. Same Mandaire substrate as mandaire.dev (the AI CTO that builds products for non-engineers) and mandaire.org (the architecture, the bets, the trust commitments that make both work). Three surfaces, one underlying protocol. The context layer that knows you in your life is the same context layer that knows what you are building.

If you read this page and want to think about whether the architecture is real, go to mandaire.org. If you read this page and recognize yourself in the operator archetype, the email below is the right place to start.