Modern Projects

Implementation

Custom AI agents to handle real work

Get in Touch

What every build includes

  • Built on your systems

    What we build works in the email, files, CRM and models your team already uses. Your data stays where it is.

  • Scoped permissions

    Each system sees only what its users can see, and acts only with the access you grant it.

  • Human review

    You decide which steps run on their own and which wait for a person to approve.

  • A record of every run

    Each step is logged with its sources, so your team can check what was done and why.

Our Agents

Investments

Deal Intake Agent

Proactively processes every new opportunity, underwrites it using the firm's template and assumptions, and passes it off to an employee.

Trusted broker inbound received
  1. Adding to DealCloud and setting up a folderAdded to DealCloud · opportunity #4821, folder ready
  2. Pulling market data and researching rentsPulled 14 comps · avg rent $38.20/sf
  3. Building an underwriting modelBuilt the model · 5-yr hold, 7.1% unlevered IRR
  4. Sending the findings to the VPSent the summary and model to the VP

Development

Site Sourcing Agent

Watches for zoning changes that fit the firm's criteria, tracks down the parcel owner and their contact details, and sends the first outreach.

New zoning change detected
  1. Cross checking with deal criteriaMatched criteria · mixed-use, 2.1 acres, transit-adjacent
  2. Locating parcel ownerLocated the owner · 1420 King Holdings Inc.
  3. Pinpointing contact informationFound the principal · phone and email verified
  4. Sending outreach to ownerSent the intro email to the owner

Investment Banking

Buyers Log Agent

Keeps a sale process moving: updates the buyers log as NDAs come in, provisions data room access, and drafts counterparty emails for the team to approve.

Fully executed NDA detected
  1. Updating the buyers logUpdated the buyers log · buyer 12 of 31 NDA-executed
  2. Provisioning data room accessProvisioned access · 2 users invited
  3. Drafting email to counterpartyDrafted the confirmation with the data room link
  4. Waiting for approval from teamSent to the deal lead for sign-off
  • Outlook
  • CoStar
  • Excel
  • DealCloud
  • Altus Group
  • OneDrive
  • Urbanation
  • Google Drive
  • Teams
  • Yardi
  • PowerPoint
  • Box
  • GeoWarehouse

Automated workflows built where you already work

Common questions

  • Work that repeats often, starts from a clear trigger and ends in a clear output. Examples are reading deal packages into your pipeline, extracting rent rolls and operating statements, and tracking loan covenants. Work that depends on judgment we cannot check stays with your team.

  • The systems your team already uses, such as Microsoft 365, Box, Google Drive, DealCloud, Yardi, CoStar and Altus Group. We connect through their APIs. Your systems stay the system of record.

  • We map the workflow with the people who do it now and agree what a correct result looks like. We build the agent in your accounts and test it on your past cases. Then we run a pilot on live work, with a reviewer checking each output.

  • Before launch, we test the agent against a set of your past cases. Each output links to its source documents. Outputs that fail a check go to a reviewer. A step runs without review only after it meets the agreed accuracy on live work.

  • Only the data and actions you approve, within the permissions of the people it works for. Actions with an outside or financial effect wait for a person to approve them. Every run is logged.

  • You do. It runs in your accounts, and we hand over the code, configuration and documentation. Your team or another provider can run it without us.

  • We scope one workflow at a time. Each scope states the current baseline, the acceptance criteria, what is excluded and the timeline. We fix issues for 30 days after launch.

Find out what AI could take off your team's plate

Book a Call