ai-agents(27)
- / Date/ Name
- Claims Are Not Evidence: Building a Supervisor That Disbelieves Its Workers
- Green CI lied to me four different ways
- An AI reviewer's silence is not a yes
- Say the word and I'll X
- Green CI is a grammar check, not a fact check
- Agents flag merge-readiness. Humans merge.
- Gate the boundary, not every merge
- My agent's 'green' was a lie until I ran the real test
- The daemon was running. The socket wasn't there.
- Put the dumb checks in the blocking path
- Silence is not approval
- Agents reason on whatever state exists when they look
- A comment count is not a merge verdict
- 'Say the word and I'll run it' was the tell
- Byte-slicing a Claude agent's context payload poisoned every retry
- My agent-to-agent message ledger came back out of order. Clock skew was the bug.
- My Claude Code balancer was rotating accounts when it should have waited 30 seconds
- My Claude Code rescue daemon was running on the accounts it rescued
- Agentic engineering, part 1: building skills that ship code for you
- Agentic engineering, part 2: adversarial code review that loops until clean
- Agentic engineering, part 3: tracing every code path before it becomes a bug
- Agentic engineering, part 4: nine skills that replaced my dev process
- I built a bug-hunting loop that doesn't quit: the BugBot methodology
- Why the same code looks different from every angle: BugBot lessons learned
- Implementing the GCC paper: giving AI agents persistent, structured memory
- Architecting extensible AI agents: a modular core with pluggable skills and SSE communication
- Porting GPTResearcher to Semantic Kernel: building an enterprise-ready research agent