Setting Up A System For Faster Customer Service Replies

𝗧𝗟;𝗗𝗥: Northwestern Mutual transformed its internal developer support by leveraging agents on Amazon Bedrock. By deploying a 𝗮 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝗼𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝗳𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸, they 𝗿𝗲𝗱𝘂𝗰𝗲𝗱 𝗿𝗲𝘀𝗽𝗼𝗻𝘀𝗲 𝘁𝗶𝗺𝗲𝘀 𝗳𝗿𝗼𝗺 𝗵𝗼𝘂𝗿𝘀 𝘁𝗼 𝗺𝗶𝗻𝘂𝘁𝗲𝘀 and freed support engineers to focus on complex issues. 𝘊𝘰𝘯𝘵𝘪𝘯𝘶𝘪𝘯𝘨 𝘵𝘩𝘦 #𝘖𝘶𝘵𝘤𝘰𝘮𝘦𝘴𝘞𝘪𝘵𝘩𝘈𝘞𝘚𝘎𝘦𝘯𝘈𝘐 𝘴𝘦𝘳𝘪𝘦𝘴 𝘣𝘢𝘴𝘦𝘥 𝘰𝘯 𝘤𝘶𝘴𝘵𝘰𝘮𝘦𝘳 𝘵𝘢𝘭𝘬𝘴 𝘧𝘳𝘰𝘮 𝘳𝘦:𝘐𝘯𝘷𝘦𝘯𝘵 24. Founded in 1857, Northwestern Mutual is a leading financial services company offering a suite of financial planning, wealth management, and insurance solutions to over 5 million customers. 𝗣𝗿𝗼𝗯𝗹𝗲𝗺: Their chat-based developer support system had long response times stretching to hours, particularly during weekends and holidays. Support engineers were spending valuable time answering routine questions and performing simple tasks like user unlocks. This prevented them from focusing on more complex technical issues that required their expertise. 𝗪𝗵𝗮𝘁 𝘁𝗵𝗲𝘆 𝗱𝗶𝗱: • Implemented Amazon Web Services (AWS) Bedrock Agents to build a multi-agent orchestration solution for automating internal support workflows. • Designed five specialized agents focused on:   * Documentation retrieval.   * User account management (e.g., unlocking accounts).   * Repository management.   * Pipeline failure analysis.   * Evaluating responses for accuracy and utility. • Used Bedrock Guardrails to mitigate risks like hallucinations or inappropriate responses. • Introduced a human-in-the-loop confirmation process before executing actions to ensure compliance with internal rules • Built the entire solution on a serverless architecture , leveraging SQS for queuing messages, DynamoDB for managing state and Lambda for orchestration. They piloted and deployed this multi-agent solution in three months and established a secure, scalable framework capable of handling more complex workflows in the future. 𝗕𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗢𝘂𝘁𝗰𝗼𝗺𝗲𝘀: • Improved Efficiency: Reduced support request response times from hours to minutes and automated repetitive tasks, allowing support engineers to focus on complex issues. • Enhanced User Experience:  Provided developers with immediate, accurate responses to basic queries and automated tasks like account unlocking and renaming accounts. Watch Heiko Zuerker of Northwestern Mutual present at re:Invent to see a great example of how you can successfully implement agents in a highly regulated Industry. cc: Mark Roy Michael Y. Liu https://lnkd.in/eM6i_T-x

Let’s say your support center is getting hammered with repeat calls about a new product feature. Historically, the team would escalate, create a task force, and maybe update a knowledge base weeks later. With the tech available today, you should be able to unify signals from tickets, chat logs, and social mentions instead. This helps you quickly interpret the root cause. Perhaps in this case it's a confusing update screen that’s triggering the same questions. Instead of just sharing the feedback with the task force that'll take weeks to deliver something, galvanize leaders and use your tech stack to orchestrate a fix in real time. Don't have orchestration in that stack? Start looking into this asap. An orchestration engine canauto-suggest a targeted in-app message for affected users, trigger a proactive email campaign with step-by-step guidance, and update your chatbot’s responses that same day. Reps get nudges on how to resolve the issue faster, and managers can watch repeat contacts drop by a measurable percentage in real time. But the impact isn’t limited to operations. You energize the business by sharing these results in a company-wide standup and spotlighting how different teams contributed to the OUTCOME. Marketing sees reduced churn, operations sees lower cost-to-serve, and leadership sees a team aligned around outcomes instead of activities. If you want your AI investments to move the needle, focus on unified signals, real-time orchestration, and getting the whole business excited about customer outcomes....not just actions. Remember: Outcomes > Actions #customerexperience #ai #cxleaders #outcomesoveraction

Stop relying on 7 tools and a dev team for simple tasks. We improved our entire ops stack by deleting half of it. How? We rebuilt systems entirely in Process Street: Every ops team knows this pain. You start with Jira... add Slack. Then Zapier... custom scripts. Before you know it, you're managing 7 tools and paying 5 invoices. And still waiting days for dev support when anything breaks. The breaking point for us? A simple routing rule change that took 2 weeks. 2 weeks. For logic that should take 2 minutes. That's when we burned it all down. Our entire ticketing system now runs on ONE platform. No developers. No middleware. Just this: Email hits inbox → AI extracts urgency/type → Code task checks customer tier → Routes to right team → Auto-escalates if needed. The "code"? Simple JavaScript anyone can write. The results? Support managers now change routing rules in 5 minutes instead of filing IT tickets. Response times dropped from hours to minutes. We killed 3 redundant tools. But here's what really matters: While your competitors beg IT for simple changes, your team ships improvements daily. While they juggle 7 tools, you run everything in one. While they burn cash on bloated stacks, you operate lean. Your stack is holding you back. And you know it. Every day you wait is another day lost to tool chaos, developer bottlenecks, and competitor advantages. Want proof this works? Process Street can show you how to rebuild YOUR most painful workflow - no developers required. But only if you're ready to take control back from IT.