Procurement · Production

Duvo builds AI procurement agents on Claude, delivering €2.8M+ in annualized savings for Rohlik Group

The problem

Enterprise operations teams know exactly which processes need to run but cannot execute the full volume — procurement, supply chain, and category management work spans heterogeneous systems with no clean APIs, creating 'abandoned work' worth millions in aggregate that never gets touched.

First attempt

Traditional automation could not handle enterprise stack heterogeneity — no clean APIs, years-long IT backlogs, and exception handling that required judgment made prior approaches unworkable. Before the Agent SDK, critical context disappeared between agent handovers.

Workflow diagram · grounded in source
1
Abandoned work identified
Trigger
Operations teams know exactly what needs to happen but cannot get to all of it, leaving high-value processes unexecuted.
▾ source quote
“operations teams that know exactly what needs to happen but can't get to all of it”
2
Agent logs into systems and extracts data
Ai action
A single agent logs into a supplier portal and extracts delivery status for purchase orders.
▾ source quote
“log into a supplier portal, extract delivery status for 50 purchase orders, cross-reference against SAP”
3
Cross-reference and discrepancy detection
Ai action
The agent cross-references data against SAP, identifies discrepancies, and checks contract terms.
▾ source quote
“cross-reference against SAP, identify discrepancies, check contract terms”
4
Escalate or auto-correct decision
Routing
The agent decides whether to escalate the issue or auto-correct it.
▾ source quote
“decide whether to escalate or auto-correct”
5
Human approval for high-risk actions
Human review
High-risk actions require human approval before the agent proceeds.
▾ source quote
“High-risk actions require human approval”
6
Emails sent and outcome logged
Output
The agent sends follow-up emails and logs the outcome, all within a single session.
▾ source quote
“send follow-up emails, and log the outcome—all in one session”
7
Decision persistence and judgment accumulation
Feedback loop
When a human responds to an approval request, the agent persists that decision for future runs.
▾ source quote
“When a human responds, the agent persists that decision for future runs. Over time, the system accumulates the operational judgment that used to exist only in people's heads”
Reported outcome

Rohlik Group achieved €1.45M in annualized savings in the first week from continuous price monitoring across 120+ SKUs and 15+ suppliers, growing to €2.8M+ across three months.
Promotional setup dropped 65-70%, supplier onboarding chasing fell 50-70%, product availability rose from 78% to 93%, inbound delivery confirmations jumped from 52% to 90%, and annual supplier negotiations shortened by one month with approximately 80% of the process automated. Across enterprise deployments, Duvo frees up 40% of team capacity on average.

Reported metrics
Annualized savings — first week€1.45M
Annualized savings — three months€2.8M+
Promotional setup time reduction65-70%
Supplier onboarding chasing reduction50-70%
Show all 12 reported metrics
annualized savings — first week€1.45M
annualized savings — three months€2.8M+
promotional setup time reduction65-70%
supplier onboarding chasing reduction50-70%
product availability improvement78% to 93%
supplier negotiation process automatedapproximately 80%
inbound delivery confirmations52% to 90%
team capacity freed40%
annual supplier negotiations shortenedone month
SKUs monitored continuously120+
suppliers monitored continuously15+
time from first conversation to production with measured savingseight weeks
Reported stack
ClaudeAgent SDKMCPcomputer useSonnet 4.6Opus 4.6SAP
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://www.anthropic.com/customers/duvo
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Rohlik Group achieved €1.45M in annualized savings in the first week from continuous price monitoring across 120+ SKUs and 15+ suppliers, growing to €2.8M+ across three months.

What tools did this team use?

Claude, Agent SDK, MCP, computer use, Sonnet 4.6, Opus 4.6, SAP.

What results were reported?

Annualized savings — first week: €1.45M; Annualized savings — three months: €2.8M+; Promotional setup time reduction: 65-70%; Supplier onboarding chasing reduction: 50-70% (source-reported, not independently verified).

What failed first in this deployment?

Traditional automation could not handle enterprise stack heterogeneity — no clean APIs, years-long IT backlogs, and exception handling that required judgment made prior approaches unworkable.

How is this procurement AI workflow structured?

Abandoned work identified → Agent logs into systems and extracts data → Cross-reference and discrepancy detection → Escalate or auto-correct decision → Human approval for high-risk actions → Emails sent and outcome logged → Decision persistence and judgment accumulation.

Related procurement cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the Procurement cases →