← back to work
// case_study /09 · caseworker · 2025 · 7 months · ai agents · embedded

Caseworker

A copilot that actually lives inside the agent's CRM - reads the case, the handwriting, and the policy tree, then drafts the next move.

By · Principalled with Embedded team
sector
Customer Support · Regulated CX
engagement
AI Agents · Embedded Build
duration
7 months · 2025
outcome
−47% average handle time on piloted queues
// the brief

A regulated CX operation wanted to cut handle time without cutting accuracy - and without ripping out the CRM their reps already lived in.

The copilot had to read the open case, the historical correspondence, the scanned handwritten forms, and the policy decision tree, then suggest the next action with a citation an auditor could follow.

We embedded inside the existing CRM, ran a smart sub-tree LLM over the policy graph, and added handwriting OCR for the legacy intake forms. Reps see suggestions inline; every accepted action writes back into the CRM with provenance.

// what we built

Embedded copilot, auditable steps.

[01]react · ts
CRM embed
Native panel inside the existing CRM. No swivel-chair, no new app.
[02]trocr · paddleocr
Handwriting OCR
Fine-tuned recogniser for the legacy intake forms in the case history.
[03]llm · graph
Policy sub-tree LLM
Routes each case through the relevant slice of the policy graph; cites the leaf.
[04]py · eventbus
Action write-back
Every accepted suggestion writes back to the CRM with full provenance for audit.
// outcomes

The receipts.

−47%
average handle time
100%
actions traceable to policy
7mo
pilot to production rollout
3
queues live at handover
0
CRM swap required
+18
NPS, piloted reps
"

The reps stopped asking IT to remove it after week two. That's the metric I actually cared about.

Johan — CEO, Caseworker
// faq · caseworker

What clients ask about Caseworker.

Cutting handle time on regulated case work without cutting accuracy and without ripping out the CRM the reps already lived in. The copilot had to read scanned handwritten forms and cite the policy leaf an auditor could follow.

// next case studies
match cuts · 2025 · 6 months · vision + vlm engineering
Match Cuts
22 personalized reels per match
auto-qto · 2025 · 8 months · vision + vlm engineering
Auto-QTO
92% symbol recall on real plan sets
lloyd score · 2025 · 9 months · spatial ai + llm
Lloyd Score
AIS grade ghost-fleet sims