it_support · manufacturing · workflow
AutoScout24 builds a Bot Factory to standardize AI agent development with Amazon Bedrock
AutoScout24's AI Platform engineers were spending up to 30% of their time on repetitive support tasks—answering questions, granting tool access, and locating documentation—while separate engineering teams were building AI agents in fragmented, non-standardized ways that prevented enterprise-wide scaling.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Developer posts Slack message
A developer posts a message in a Slack support channel to initiate a request.
Tools used
Amazon BedrockAmazon Bedrock AgentCoreAmazon API GatewayAWS X-RayAWS Secrets ManagerIAM
Outcome
The team deployed a production-ready Slack support bot that is actively reducing the manual support load on the AI Platform Engineering team, addressing the 30% of time previously spent on repetitive tasks, and produced a reusable Bot Factory blueprint that allows other teams across AutoScout24 to build new agents faster without reinventing infrastructure.
Results
Time savedup to 30%
Grounding & classification
Source type: platform led case
26 fields verified against source quotes, 4 dropped as unverifiable.
agentic workflowai agentknowledge searchmulti agent workflowragknowledge basemetric backednamed customerproduction runtime claimedtools describedworkflow describedautomotiveemployee productivitytime savedplatform led caseback office opsit supportagentic task executionextract classify route