Before
Page Speed38/100
Bounce Rate82%
Conversions0.4%
After
Page Speed98/100
Bounce Rate24%
Conversions+340%
L
Logic Layer Solution
logiclayersolution.uk
before
after
We Build Digital Experiences
That Drive Growth.
150+
Projects
98%
Satisfied
8yr
Experience
All work
Legal SaaS · 2025

Axiom — semantic search for law firms

Semantic search platform that lets law-firm associates query 30 years of internal precedent, contracts, and matter files in natural language.

Client
Axiom Legal
Industry
Legal tech
Duration
19 weeks
Year
2025
Next.jsVector DBOCR
app.axiom.io / dashboard
Axiom
Overview
Fleets
Alerts
Logs
Team
Settings
Fleet overview
Real-time · all regions
Live
P75 latency
340ms
−92%
Active fleets
1,284
+22%
Uptime
99.99%
Throughput · 24h
By region
Top events
event_1156
event_2290
event_3424
Fig. 01 — Production UI · 2025Axiom Legal
Year
2025
Category
Legal SaaS · 2025
Stack
Next.jsVector DBOCR
Scope
  • OCR pipeline (PDF + scans)
  • Vector embedding store
  • Search UI + result ranking
  • Matter-scoped RBAC
  • Audit logging
The challenge

What they needed to solve.

Axiom's customers (top-50 UK and US law firms) were running fee-earner research across PDF folders, archived emails, and Sharepoint. Average research time per matter was 6 hours. Internal precedent was unsearchable.

Our solution

How we approached it.

A semantic search platform with OCR ingestion, vector embeddings of every paragraph, and citation-grade results with provenance back to the original document. Custom RBAC keeps every matter visible only to authorised teams.

Web design

Design decisions.

Palette
#171717
#fafaf9
#dc2626
#1d4ed8
#525252
Typography
  • AaSöhne — UI
  • AaGT Sectra Text — citation body
  • AaSöhne Mono — clause numbers
Layout system

Citation-grade UI — every result shows a paragraph excerpt with its full document path and access trail. No 'AI summary' without source.

Design highlights
  • Citation provenance for every result
  • Snippet-first results, full doc on demand
  • Audit trail of every search per fee-earner
Before · After

What changed.

app.axiom.io / dashboard
Axiom
Overview
Fleets
Alerts
Logs
Team
Settings
Fleet overview
Real-time · all regions
Live
P75 latency
340ms
−92%
Active fleets
1,284
+22%
Uptime
99.99%
Throughput · 24h
By region
Top events
event_1156
event_2290
event_3424
After
app.axiom.io / dashboard
Axiom
Overview
Fleets
Alerts
Logs
Team
Settings
Dashboard
Last updated 04:12
Refresh
P75 latency
4.2s
Active fleets
412
Uptime
97.1%
Activity
By region
Top events
event_18
event_216
event_324
Before
Drag to compare ←→
Fig. 02 — Drag handle to reveal before / afterAxiom Legal
app.axiom.io / dashboard
Axiom
Overview
Fleets
Alerts
Logs
Team
Settings
Dashboard
Last updated 04:12
Refresh
P75 latency
4.2s
Active fleets
412
Uptime
97.1%
Activity
By region
Top events
event_18
event_216
event_324
Before

PDF folders + Sharepoint + email archives, no semantic search, no audit trail, 6 hours research per matter.

Research / matter
6 hrs
Precedent reuse
Low
Audit coverage
None
Search index size
0 docs
app.axiom.io / dashboard
Axiom
Overview
Fleets
Alerts
Logs
Team
Settings
Fleet overview
Real-time · all regions
Live
P75 latency
340ms
−92%
Active fleets
1,284
+22%
Uptime
99.99%
Throughput · 24h
By region
Top events
event_1156
event_2290
event_3424
After

Semantic search across 30 years of firm history, full audit trail, citation-grade snippets, matter-scoped RBAC.

Research / matter
38 min
Precedent reuse
4.1×
Audit coverage
Full
Search index size
2.4M docs
Results

What we measured.

01Avg. research time per matter from 6h to 38min
02Internal precedent reuse up 4.1×
03Adopted by 11 top-50 law firms in year one
04Zero unauthorised document accesses in 14 months