Krenels

Engineering and creative consultancy

Krenels works with tech, real estate, education and service companies. We are creative technologists: we solve the problems that hold a business back, and build things your users are glad to open.

Start a conversation What we do

Companies we built for

Models and where they hold up

We study new models as they ship and run them through a live business process to find the point where they stop being useful. What survives that goes into client work, and the write-up goes into Forge with the numbers we measured along the way.

Read Forge

Software people avoid using

We do not build things that are unpleasant to use. Friction and bad UX kill adoption, waste people’s time and drain their attention, which makes them defects worth fixing before anything ships. If a form throws away everything you typed the moment it fails validation, we did not build it.

Working inside a large organization

A large organization comes with systems nobody wants to touch, data that disagrees with itself, a team that has already sat through two failed rollouts, and a quarter that still has to close. We plan the work around all of that, and the first cycle has to produce a result someone in the business can name out loud before the rest gets built.

Vitaly Krenel

Vitaly Krenel

13 years in engineering. Launched and rebuilt products for fresha.com, reprally.com, Harvard Caselaw and Grably.us (ex Speechki.org). Writes about the approach we use in the work.

What we have already built

Proposal and short-list generation

A manager sets the parameters, gets a proposal already shaped around the client, and edits it from there — 20 minutes for a finished proposal that used to take 70 hours.

Interactive special products

We build interactive pieces for sales offices and websites, like a live map of every project across an island where the client picks the estates themselves.

Lead qualification and routing

Incoming requests are qualified inside the chat and routed to the right manager without manual sorting, so response time comes down to 5 minutes and the manager opens a client profile that is already filled in.

A CRM agent that keeps your data

The agent reads the conversation, tags the lead, and moves the deal stage and history in the CRM. Managers stop filling fields by hand and the data stays current on its own.

Automated stories

Property stories are assembled from your own data — 500 updates a month keeping projects in front of the broker network.

See all products

Case studies

Four projects written up in more detail: what the team was doing before we arrived, what we built in place of it, and which numbers we can stand behind afterwards.

International real estate brokerage, 7 regions

Offer and story studio

Brokers put every client proposal together by hand: they searched the live inventory for units that were still available, pulled the good ones into a slide deck, and rewrote the surrounding text for the particular buyer. It ran into days of work per offer, and how the result looked depended on who was assembling it that week.

  • Assembling an offer went from 70 hours of work to 20 minutes.
  • 41 seats across 7 regions, 22 of them opening the tool in a given week.
  • The broker still picks the units and reads the offer before it goes out.

CRM relaunch + legacy displacement (complex monolith rework)

A CRM that had been growing for 15 years carried the whole sales operation, and the rules of the funnel were distributed across views, processors, creators, models and signals. Nobody could say why a given lead refused to move to the next stage without reading the code, and one funnel served residential, commercial and investment products at the same time.

  • Funnel rules collected into one declarative layer, so a refused transition returns a stated reason.
  • Deal, Person and Company added above the lead, with the legacy lead system left read-only and intact.
  • A head of sales configures a new funnel and its data requirements without a release.

Krenels, internal

Background agent factory

Delivery speed was capped by how often an agent had to stop and wait for a person. We read a week of session logs and counted the stops: 16 times in three days a run was blocked on a password or an access token, 10 of 18 long background runs died when a laptop lid closed, and around 33 test runs a week were driven by hand.

  • Agents run on a server around the clock and are addressed from Telegram, so a long run no longer depends on somebody’s laptop staying open.
  • The repeating parts of delivery became skills: take a task, run the regression, restore context, turn a discussion into a tracked issue with a notification.
  • Agents work in isolated git worktrees, so several run against one repository without competing for ports or shared config.
  • Capacity moved from one project per developer to two, against a target of three to four.

European developer, regional sales office

AI-native CRM for a regional office

The regional office worked in the head-office CRM, which had been built for a different market and a different way of selling. So the office kept its own copy of everything that mattered — project data, client matching, the numbers for the weekly report — and the two versions drifted apart between updates.

  • A CRM shaped around the way this office sells, with head-office reporting fed out of it by agents.
  • A project database with matching, so a rep can ask what fits a client and get the answer in the system.
  • Agents keep the developer portals and the head-office CRM in step, so nothing is entered twice.
  • Voice control for the stretch of the day a rep spends away from a desk.

Read the case studies in full