Case studies
Engagements, end to end.
The estate, the constraint, the pipeline stage by stage, and what shipped. Written at the level of detail a Head of Data would need to decide whether we have done this before.
Six engagements
Written to be checked, not skimmed.
Each one names the decisions the engagement actually turned on, the model or the chunking strategy, the contract or the permission model, and how the result was measured. That is the level at which a technical buyer can tell whether a supplier has done this before.

Water & utilities
Making thirty years of asset documentation answerable at a UK water utility
A retrieval pipeline over 380,000 asset documents: drawings, condition reports, permits and handover packs, with permission inheritance preserved from the source document management system.
UK regional water utility, ~4,500 staff · 16 weeks
Read the engagement
Central government
Assembling regulatory evidence from casework correspondence in central government
An extraction and evidence-assembly pipeline over eleven years of casework correspondence, built to a standard where every extracted fact traces to a source passage and a pipeline version.
UK central government agency, ~2,000 staff · 20 weeks
Read the engagement
Financial services
Putting a measured error rate behind claims-evidence retrieval at a specialist insurer
An evaluation harness, adversarial suite and assurance pack retrofitted to a retrieval system already in production, so the firm could state its error rate rather than describe its intentions.
UK specialist insurer, ~1,200 staff · 12 weeks
Read the engagement
Professional services
A two-year AI roadmap grounded in what the document estate could actually support
Fourteen candidate use cases screened against real corpora and against whether anyone could define a correct answer. Six survived; the sequence was chosen so the first delivery paid for the second.
Mid-market UK professional services firm, ~600 staff · 7 weeks
Read the engagement
Financial services
Replatforming a twelve-year-old warehouse without a reporting freeze
A migration run as two platforms in parallel for its whole duration, with a data contract on every source feed and cutover taken one reporting consumer at a time rather than one platform at a time.
UK building society, ~3,400 staff · 34 weeks
Read the engagement
Central government
Making a data platform trustworthy enough to publish from
Contracts, column level lineage and freshness SLAs added to the platform behind an official statistics publication, after a release had to be corrected because a source system quietly changed what one column meant.
UK government department, ~6,000 staff · 22 weeks
Read the engagement
Get in touch
Talk to us.
A first conversation runs about forty-five minutes and covers three things: what your estate actually looks like, whether anyone can define a correct answer or an agreed number, and whether your permission model resolves per user. Any one of them can rule the work out, and we would rather tell you in week one.
- Prefer email
- hello@vectisflow.com
- Response time
- One working day, from a person who has read it.