Loading post…
AWSUmesh KalaspurkarExplainer
How DHI Group accelerates generative AI workloads from idea to production using hackathons
Summary
DHI Group needed to move generative AI efforts beyond proofs of concept because its traditional software development lifecycle took months, while it sought faster delivery, technical validation, and broader AI literacy. AWS and DHI used a four-phase Hackathon Acceleration Package—preparation, enablement, a three-day build event, and a path to production—with workshops on Amazon Bedrock AgentCore, AI-DLC, and Kiro. Twenty participants formed three teams and produced prototypes for employer analytics, intelligent candidate matching, and a unified ClearanceJobs–AgileATS marketplace; DHI leadership committed to advancing all three toward production. The winning marketplace uses an MCP server, Amazon Bedrock AgentCore, Lambda functions, session memory, and Claude 3.5 Haiku to let recruiters search candidates and enrich profiles through natural-language requests. The post concludes that time-boxed, cross-functional hackathons can compress ideation, architecture, prototyping, executive alignment, and production planning when production criteria and preparation are established upfront.
Context
DHI Group wanted to accelerate generative AI adoption while avoiding a months-long traditional SDLC. The hackathon format was intended to validate feasibility, improve organizational AI literacy, produce shippable code, and create a repeatable route from experimentation to production.
Approach / What changed
AWS and DHI organized a Hackathon Acceleration Package with four phases: define business outcomes, provide generative AI and AI-DLC enablement, run a three-day hackathon, and create a production roadmap. The winning team built a unified recruiter interface using a ClearanceJobs MCP server, Amazon Bedrock AgentCore for orchestration, Lambda functions for tools and GitHub enrichment, AgentCore memory for session context, and Claude 3.5 Haiku for reasoning.
Takeaways
The event used preparation, enablement, a three-day hackathon, and a path-to-production phase to connect business goals with production planning.
Three teams built prototypes for employer analytics, intelligent candidate matching, and a unified ClearanceJobs–AgileATS talent marketplace; DHI committed to advancing all three toward production.
The winning recruiter experience uses MCP tools and an agent to search candidates, retrieve profiles, enrich results with GitHub data, and preserve session context across conversations.
FAQ
What did the hackathon teams build?
The teams built a real-time Employer Analytics Dashboard, an intelligent candidate matching system, and a unified ClearanceJobs–AgileATS talent marketplace. The projects addressed recruiter workflow, job-description interpretation, candidate experience, and system integration themes.
How was the winning recruiter experience implemented?
A ClearanceJobs MCP server exposed candidate search and profile retrieval as tools, while Amazon Bedrock AgentCore orchestrated them through an intelligent agent. A separate Lambda function enriched candidates with GitHub profiles, and AgentCore memory preserved session state and recruiter preferences.
What made the hackathon oriented toward production rather than demos?
The teams received pre-event enablement, worked on real business problems, and built prototypes with production-grade services. DHI leaders judged the final results and committed to a roadmap covering hardening, scalability, security, and integration.
Source and freshness
- Source
- aws.amazon.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.