Meet Caddi in personILTACONAug 23–27Booth 159Future ProofSep 14–17Booth 248 · Zone 1
New Loop Studio is live

Agent that builds back-office agents.

Caddi discovers your most repetitive back-office work and automates it across every tool your firm uses. You train the agents over chat & screenshare, and leadership governs every run.

Schedule DemoTry for free
SOC 2 Type II150+ integrationsEvery run logged

Loved by ops teams in law and finance

Am Law 100Barron's Top 10 RIAThe Planning Center
“Helps make our internal lives easier and the systems we already have talk to each other.”
Matt Mercer, COO, The Planning Center
Beveridge & DiamondPalacePortner & Shure
“Caddi focuses on applying AI to real business workflows in ways that are useful and effective.”
Jordan Portner, COO, Portner & Shure
Knight Law Group
Our customers →
01Discover

Caddi finds the work worth automating.

It reads the systems you already run, ranks what actually repeats, and counts every step of it.

See Discover in the product
LoopyEARLY ACCESS+ New chat
What should I automate?

I read your systems. Three keep coming back.

  • Triaging the morning inbox1,204 / moHigh · 91%Build
    • 1,204messages readOutlook
    • 418envelopes openedDocusign
    • 412matters matchedClio
    • 412files filed to the matterNetDocuments
    • 212remittances posted to payableQuickbooks
    • 6exceptions raised for reviewTeams
  • Reconciling trust payments940 / mo5 stepsHigh · 88%Build
  • Opening a new matter386 / mo5 stepsHigh · 84%Build

Email triage, then. Walk me through it.

Send a message to Loopy…
02Teach

You teach it the way you teach a new hire.

Screenshare the job and narrate it. Caddi pokes at the edge cases as you go, and you tweak it back in the chat.

See the recorder
Whitmore · Docusignapp.docusign.com/documents/details
DocusignAgreementsTemplatesReportsStartAgreementsInboxSentCompletedAction requiredFoldersWhitmore HoldingsRidgelineAgreementsCompletedDownloadAsset Purchase AgreementEnvelope 4f21c8 · completed 09:04D. WhitmoreWhitmore Holdings08:58A. SerraRidgeline Systems09:04
Caddi
Inbox Triage CaptureRecording. Work through your script.
  • 1Open your inbox and read down it. Say what tells you which kind each message is.Microsoft Outlook
  • 2Open a Docusign notice. Show how you get to the executed copy, and check both signatures.Docusign
  • 3File one to the matter. Show the naming, and what happens when a version is already there.NetDocuments
12 rules captured so farStop Recording
LoopyEARLY ACCESS+ New chat
LoopyWhat if only one party has signed?Hold it. Never file a half-signed one.

Sounds good. Built.

03Govern

Every run on the record. No black box.

Deterministic code does the work, so the same input takes the same path every time, and every run replays: what it decided, why, and which permission it used.

See run history
2,164 today · 1 held
  • DoneEmail triage411 filed to the matterNetDocuments · create09:14
  • DoneClient intake38 packets to SalesforceSalesforce · create09:02
  • HeldEmail triage1 held, one signature onlyDocusign · read08:47
  • DonePayment recon940 payments matchedQuickBooks · create08:30
Same inputsame pathflat costAI where the work needs judgment. Code everywhere it has to be exact.
Automations by teamLast 30 days
  • Finance9 live312 hrs
  • Talent6 live214 hrs
  • IT5 live188 hrs
  • Marketing3 live96 hrs
150+ integrations

Caddi agents use all your existing tools.

See all →
Why Caddi

Building it is easy. Keeping it running is the job.

The demo is the easy part. What decides this is whether the thing still runs in month nine.

ReliabilityMaintenanceCost
Reliability

Deterministic code runs the work. AI only where it needs judgment.

Not an agent re-deciding every step, then drifting by Friday.

Maintenance

It flags what drifted after a run and proposes the fix. You approve it.

Not improvising mid-run, with nobody able to say why the output changed.

Cost

One predictable price. No token meter running behind the work.

Not $10k a month of tokens on agents that break by Q2.

Why Caddi
Trust and security

Built to be handed to your security team.

For a regulated firm this is not a feature alongside the automation. It is the precondition for deploying any of it.

Top 5 security FAQs
Is our data used to train models?

No. OpenAI and Anthropic calls run under zero-retention terms, and every other provider is set to no training and no retention.

What can an agent actually reach?

One scope per system, under the access the person already had. No standing admin.

Can it decide something on its own?

No. Code runs the work, and changing a process takes a human approval.

Can we prove what it did?

Every run replays decision by decision, with the permission each one used.

How fast can we stop it?

Pause a loop or pull its connection. It stops mid-queue, not at the end.

SOC 2 Type IIScoped permissionsReplayable run recordsYour data stays yours
Trust Center
Get started

Put the agent to work on your first process.

See it run on your own workflows, and talk it through with the people who build it.

Talk to us

Schedule a demo

Thirty minutes on your own workflows. Security and governance answered up front.

Schedule a demo
Self serve

Try Caddi for free

Show Caddi one process and watch it build the agent. Your first 14 days are free, then $100 per user per month.

Try for free