.png&w=256&q=75)
🤓 Latest Submissions
Bob Pipeline Doctor
Bob Pipeline Doctor is a CI/CD failure triage dashboard built for developers who lose time manually reading pipeline logs, tracing impacted files, and deciding what is safe to fix before merging. The project uses IBM Bob as a repository-aware development partner to transform a failed pipeline into a structured remediation report. In the MVP, a controlled GitHub Actions failure fixture is exposed through a local read-only MCP ingestion pattern. IBM Bob analyzes the failure context, identifies the likely root cause, maps impacted files, recommends safe remediation steps, suggests missing tests, and summarizes merge confidence with explicit risks and unknowns. The goal is not to automatically fix or deploy code. Instead, Bob Pipeline Doctor keeps humans in the review loop while reducing the time needed to understand CI/CD failures. The dashboard presents the diagnosis, evidence, impacted files, remediation checklist, recommended tests, safety boundaries, and IBM Bob session evidence in one clear command-center interface. For the hackathon, the project focuses on a reproducible local workflow with no credentials, no live private repository access, and no unsafe automation. Future versions could connect the same MCP pattern to GitHub Actions, CircleCI, Buildkite, or other CI/CD platforms.
17 May 2026
SpecSmith
SpecSmith is an agentic QA system that helps teams find what they forgot to test before bugs reach production. Developers often build from PRDs, GitHub issues, and OpenAPI docs, but test planning is still manual, inconsistent, and easy to miss. SpecSmith turns those raw specs into a structured Forge Report with risk-ranked findings, a linked test matrix, executable test drafts, a coverage score, and a gap report. The product is built around a QA workflow with specialized agents: Spec Parser, Risk Mapper, Test Planner, Test Writer, and QA Reviewer. The public demo uses a fast OpenAI-compatible API mode optimized for reliability: it makes one real model call, reads the actual input spec, and generates a context-aware Forge Report. The full 5-agent pipeline is also implemented and validated separately, including Qwen 72B validation evidence documented in the repository. SpecSmith is not just a generic test generator. It connects requirements, risks, tests, and coverage gaps so engineering teams can understand what matters before they ship. The AMD Developer Cloud path is documented for a future vLLM/Qwen deployment on MI300X once credits are approved.
10 May 2026
