Subscribe
Sign in
Home
Podcast
Notes
Java
Java AI
Quarkus
IBM Bob
FaQ
Archive
About
IBM Bob
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.
16 hrs ago
•
Markus Eisele
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
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
IBM Bob Cost Control Starts With Context Hygiene
Use .bobignore, narrower MCP toolsets, targeted @ mentions, and fresh chats to keep IBM Bob focused and cheaper to run.
Jun 23
•
Markus Eisele
1
1
Using JaCoCo and AI to Prioritize Test Coverage in Quarkus Teams
Watch now | Use a JaCoCo report to show IBM Bob where your Quarkus codebase still needs tests, prioritize the gaps that matter, and generate coverage…
Jun 22
•
Markus Eisele
and
Alex Soto Bueno
1
5:00
Quarkus Test Data: Teach Bob Datafaker and Instancio
Replace hardcoded agent fixtures with synthetic data, a Bob skill, seeded boundary tests, and REST proof in a NebulaTrack Quarkus walkthrough.
Jun 11
•
Markus Eisele
4
2
1
IBM Bob Needs a Context Budget Before It Needs More Tools
How GitHub MCP tool definitions, git diff, and gh output compete for IBM Bob's 200k context window, and how to keep the budget under control.
Jun 6
•
Markus Eisele
3
2
1
How to Keep a Shared Bob MCP Server From Acting Like One User
How delegated access, time-limited tokens, and audit-ready identity keep shared MCP infrastructure from turning into a service account.
Jun 4
•
Markus Eisele
1
1
My IBM Bob Day Demo Failed. Quarkus Agent MCP Got Better.
A dead Podman session is a rude demo partner. It is also a very efficient way to find out whether your agent tooling understands the difference between…
May 6
•
Markus Eisele
3
The Browser Can Open the Page. Chrome DevTools Tells Me Why It Broke
How I connect Bob to a dedicated Chrome session so it can debug with console logs, network requests, and performance traces instead of guessing from the…
May 4
•
Markus Eisele
1
AI Agent Reliability Starts With Better Task Framing
Why clear goals, context, routines, and stop conditions work better than walls of "don't" when you use IBM Bob and other AI coding agents.
May 2
•
Markus Eisele
4
The Java Agent Skills Kit
A repo-local way to give Bob repeatable workflows for architecture review, modernization, dependency risk, LSP navigation, and test-first change in…
Apr 28
•
Markus Eisele
6
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
