- Home
- AI use cases
- Relationship intelligence
AI use case · built in Our own sales desk
A sales desk that reads, remembers and reminds
Relationship businesses run on who you know and when you last spoke. We built a desk that turns screenshots into records, drafts considered replies, and makes sure no conversation goes quiet by accident.
The problem
Most firms keep their relationships in three places at once: a CRM nobody updates, a spreadsheet someone does, and a partner's memory. Typing a LinkedIn profile into a CRM takes minutes per person, so it doesn't happen, and the follow-up promised in a meeting slips.
The work that wins business (a thoughtful comment, a timely email, a reason to call) is exactly the work that gets squeezed out by data entry.
How it works
Each step is done by whichever is right for it: a model where something has to be read or drafted, tested code where a rule applies, and a person where a decision is made.
- 01InputScreenshotsProfiles, search results, company pages, several at once
- 02AIClaude reads themName, role, company, country, sector and size, never a guessed link
- 03Rules in codeDe-duplicateSame URL or same name at same firm is flagged; only empty fields are filled
- 04A personYou correct and saveNothing is written until you confirm the list
- 05OutputPipeline and roundNext check-in dates, and who to engage today
AI reads, plans or draftsTested code applies the rulesA person reviews and decides
Live today
What it already does
Labelled honestly: AI where a model does the work, Rules where tested code does.
- AIScreenshot to recordPeople and companies read from LinkedIn screenshots by Claude on the server, about a cent per image, with nothing stored by the model.
- AIReply draftingFive reply formats (appreciate, compliment, encourage, curious question, view and question) drafted from the post itself.
- RulesGuardrails in codePolitical, religious and personal posts are skipped whatever the model says; a reply that pitches, links, tags or argues cannot be copied.
- RulesOne person, many conversationsThe same contact can be at a different stage for each business you run, each with its own value and next step.
- RulesNeed-to-know accessAn assistant can work the daily round with her own login and see names and timing only, never notes or addresses.
What AI adds next
Builds we can scope on the same foundations, each kept inside the same rules and the same review step.
Voice note to pipeline
Talk for thirty seconds after a meeting. The note is transcribed, the promised next step and date pulled out, and a stage change suggested for you to accept.
Pre-meeting briefing
One page before every call: who they are, what their firm has announced, every touch so far, and the open question from last time.
Signal watch
Companies House and CRO filings, funding rounds, senior hires and refinancings at your targets turned into a reason to get in touch, with the source linked.
Warm-path finder
Before a cold approach, see who in your own book already knows someone at the target, and how recently you spoke to them.
Emails in your voice
Follow-ups drafted from the conversation history and your past emails, held for approval, never sent automatically.
Quiet-deal alerts
Conversations that have gone longer than usual without a reply are flagged, with the likely reason and a suggested next move.
Through the lens of your sector
The same build answers a different problem in each business. Pick yours.
- The problem
- A fund raise means hundreds of LPs, family offices and placement agents met at conferences and on LinkedIn, tracked in a spreadsheet that is out of date by the next roadshow.
- Live today
- Conference attendee lists and LinkedIn searches screenshotted in batches and turned into a clean investor list, each with a check-in date.
- What AI adds next
- Signal watch on LP allocations and team moves, and a briefing pack before each investor meeting.
- Stays with a person
- Who gets a call from the partner, and what is said.
- The problem
- A commercial finance broker juggles a lender panel and a borrower pipeline. Relationship managers change jobs and the contact goes stale.
- Live today
- Lender and borrower contacts kept per business line, with each conversation at its own stage.
- What AI adds next
- Alerts when a lender contact moves firm, and a deal summary drafted to send to the lenders most likely to say yes.
- Stays with a person
- Which lender sees which deal, and the credit judgement.
- The problem
- Agents, developers, contractors and funders all matter, but the useful moment to call is when a site, a planning decision or a refinancing comes up.
- Live today
- Developer and agent contacts added from screenshots, grouped by target company.
- What AI adds next
- Planning applications and charge registrations at target companies turned into prompts to get in touch.
- Stays with a person
- The relationship itself, and the decision to pursue a site.
- The problem
- Founder-led sales: the founder is the pipeline. Everything lives in their inbox and nothing survives a busy month.
- Live today
- A pipeline the founder can update in seconds, and a daily round of who to engage.
- What AI adds next
- Warm-path finder for introductions to investors and customers, and voice notes after every demo.
- Stays with a person
- The pitch, the price and the product promise.
- The problem
- Accountants, lawyers and advisers win work from referrals and visibility, and business development time is the first thing to go in a busy season.
- Live today
- A daily LinkedIn round that keeps you visible to referrers in ten minutes, with replies that never sell.
- What AI adds next
- Briefings from public filings before a pitch, and reminders tied to client year ends.
- Stays with a person
- Advice, fees and every word that goes out under the partner's name.
Other AI use cases
Bookkeeping and filing
Monthly uploads, bank matching, VAT and corporation tax workings and statutory accounts, with a tamper-evident audit trail.
See the use caseWealth ProfilerClient onboarding and KYC
A household captured once, checked against KYC and AML rules, and turned into a balance sheet, risk profile and investment policy.
See the use caseManagewise WorkspaceOperations inbox and compliance
Every email tagged to the right building, replies drafted with that building's context, and every statutory deadline and arrears run in one place.
See the use caseFinance StudioFinance content studio
Record once; get edited, illustrated and captioned videos with sourced news cards, ready for every channel.
See the use caseWant your version of this?
Tell us how the work is done today. We will tell you which parts a model should do, which parts need rules around them, and what a pilot on your own data would look like.