Marketing AI | Process automation | CRM
AI implementation that ends in working software
Most AI projects stall at the slide deck. We build and deploy AI into the workflows your team already runs: qualifying inbound leads, automating repetitive marketing and reporting work, and keeping your CRM honest. Systems in production, owned by your team, built for regulated and technical companies.
What we implement
We start with one workflow, not a transformation programme. The candidates are usually the same: work your team repeats every week, decisions that need context nobody has time to look up, and data that quietly rots between systems.
Qualify | Route | Respond
AI tools for marketing
Assistants that answer real questions about what you do, qualify inbound enquiries against your own criteria, filter the traffic that was never going to convert, and hand your team a shortlist with the context already attached. Built on retrieval over your approved content, so the answers stay inside what you actually claim.
Reporting | Research | Repetitive work
Process automation
The reporting pack someone rebuilds every month, the research pass before every call, the campaign checks nobody has time to run. We automate the process end to end and give you the dashboard that replaces the spreadsheet, including how the numbers were filtered and why you can trust them.
Enrich | Route | Keep clean
CRM and data automation
A CRM is only as good as what reaches it. We wire the pipeline from first touch to record: enriching and de-duplicating leads, classifying and routing them to the right owner, syncing between the systems you already pay for, and flagging the records that have gone stale before your team acts on them.
Running in production
CSI, a clinical-trial logistics company serving pharma and biotech sponsors, needed inbound enquiries qualified before they reached the team, and misrouted visitors filtered out. We built a retrieval-based assistant over their approved content that classifies each enquiry and hands off the qualified ones with structured metadata. Because the industry demanded it, the architecture uses a zero-retention model tier and UK hosting, and the assistant is built to decline anything outside its approved scope. Full story in the CSI case study.
RoutePerfect, a travel-technology company, needed reporting it could trust. We built an analytics platform with a self-serve report builder over a dataset filtered to genuine human sessions, so the team stops arguing about whether the numbers include bots and starts using them. Full story in the RoutePerfect case study.
We also build and run Sorbet Brains, our own AI product suite. That is first-party work rather than a client engagement, and we mention it for one reason: the patterns we implement for you are ones we operate ourselves, not techniques we read about.
For the wider argument about why businesses are becoming systems that machines act on, see The Agent-Ready Web.
How an engagement runs
1. Map. Where the time actually goes, and which workflow has the clearest payback.
2. Prototype. A working version your team can use within weeks, not a specification.
3. Harden. Access control, data residency, evaluation, and the legal review that regulated buyers require.
4. Deploy and hand over. In production, documented, with someone on your side owning the controls.
5. Next workflow. Only once the first one has earned it.
What we do not do
We do not run company-wide AI transformation programmes, write speculative strategy decks, or deliver generic staff training. We are a small senior team that ships specific systems into production. If your problem genuinely needs a large consultancy, we will tell you early rather than bill you to find out.
Frequently asked questions
What does AI implementation actually mean here?
Working software, not strategy decks. We build and deploy AI into the workflows your team already runs: qualifying and routing inbound leads, automating repetitive marketing and reporting work, enriching and maintaining CRM data, and turning internal knowledge into something your team can query. Each engagement ends with a system in production that someone on your team owns.
Do you have AI running in production for real clients?
Yes. For CSI, a clinical-trial logistics company serving pharma and biotech sponsors, we built and deployed a retrieval-based AI assistant that qualifies inbound business enquiries, filters misrouted traffic, and hands off qualified enquiries with structured metadata. For RoutePerfect, a travel-technology company, we built a reporting and analytics platform with a self-serve report builder over a bot-filtered dataset.
How is this different from an agency reselling ChatGPT?
We write and operate the systems: retrieval pipelines, embeddings and vector search, evaluation, access control, data residency, and monitoring. We also run our own AI product suite, Sorbet Brains, so the patterns we implement for clients are ones we maintain in production ourselves rather than techniques we read about.
What about data privacy and compliance?
It is usually the first question in regulated industries, and it shapes the architecture. In practice that has meant zero-retention model tiers, hosting in a specific jurisdiction, keeping the data store under the client's control, and building the system so it declines to answer outside its approved scope. We design for your legal review rather than around it.
What do you not do?
We do not sell company-wide "AI transformation" programmes, speculative strategy decks, or generic staff training. We are a small senior team that ships specific systems. If your problem needs a large consultancy, we will say so.
How does an engagement start?
With one workflow, not a roadmap. We map where time actually goes, pick the process with the clearest payback, and build a working prototype your team can use. If it earns its place, we deploy it, hand over the controls, and move to the next workflow.
Start with one workflow
Bring the process your team repeats most. We will tell you honestly whether AI is the right answer for it, and what it would take to put it into production.
