Subscribe
Sign in
Home
Podcast
Notes
Java
Java AI
Quarkus
IBM Bob
FaQ
Archive
About
Latest
Top
Discussions
AI Wrote the Code. Did It Create Value?
Replacing one bad AI number with a vague one will not fix how we measure AI. We need the full cost of each result we can verify.
Jul 26
•
Markus Eisele
1
Progress Users Can Trust for Long-Running Enterprise Jobs
Build an honest two-stage progress UI with Quarkus, PostgreSQL, Scheduler, SSE, cancellation, and state that survives a page reload.
Jul 24
•
Markus Eisele
3
1
Quarkus TOTP with Vault: What Production-Ready Step-Up Requires
Turn one valid TOTP code into a two-minute step-up JWT, then let Quarkus RBAC protect the sensitive operation and test replay against Vault.
Jul 22
•
Markus Eisele
2
1
Use skillsaw to Lint Bob Skills Before They Drift
Build a small invoice-processing Bob skill, add a reference file, wire CI, and test the behavior locally before the instructions spread across repos.
Jul 20
•
Markus Eisele
5
1
Put OPA in Front of Your Quarkus MCP Tools
Use structured policy input and caller context to decide which MCP tools a client can see and call.
Jul 17
•
Markus Eisele
1
Spec-Driven Development Needs an Exit Strategy
AI coding teams need small change briefs, native engineering artifacts, and enough judgment to stop Markdown specifications becoming a second codebase.
Jul 15
•
Markus Eisele
3
Build Your First Hardened Quarkus Image with Jib and Java 25
The final Quarkus service in this article has no Dockerfile.
Jul 13
•
Markus Eisele
3
1
Agentic Engineering Still Needs Human Judgment
After 510 daily posts on The Main Thread, this is a practical note on publishing cadence, Quarkus craft, and why agent-assisted work still needs…
Jul 11
•
Markus Eisele
6
4
Give IBM Bob a Memory of the Quarkus Codebase
Indexed Quarkus with codebase-memory-mcp, ran the same @ConfigMapping trace with grep vs graph tools, compared cost
Jul 10
•
Markus Eisele
2
1
Coding Agent Evaluation Is Not a Benchmark Slide
Measure whether the whole coding-agent workflow produces smaller wrong turns, better recoveries, clear test evidence, and work a human can trust.
Jul 9
•
Markus Eisele
3
1
Wanaku MCP Router: Getting Started on Your Laptop
Run a local Wanaku router, import an HTTP toolset, forward an upstream MCP server, and merge both into one agent catalog.
Jul 8
•
Markus Eisele
2
1
AI Agents and the Rockstar Developer Problem
Generated code arrives fast, but teams still need shared design, local conventions, change budgets, and review gates before output becomes software they…
Jul 7
•
Markus Eisele
3
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts