Moving Google's A2A codelab agent to a2a-sdk v1.0 and Cloud Run
Migrating the CrewAI burger agent from Google's A2A codelab to a2a-sdk v1.0, deploying it to Cloud Run, and connecting a TypeScript client to it.
Migrating the CrewAI burger agent from Google's A2A codelab to a2a-sdk v1.0, deploying it to Cloud Run, and connecting a TypeScript client to it.
A text-to-SQL agent broke a written rule against adding rows by hand. GROUP BY ROLLUP and scalar subqueries fixed it by deleting the step, not the rule.
A Claude Code routine translates, checks, and merges a drafted article on this blog end to end, with no machine needing to stay on.
Two disposable GitHub issues test Claude Code's cloud routines: labeling one produces a real PR from a sandbox, but the routine has no AskUserQuestion tool.
AIMock mocks the whole AI stack on one port (LLM, vector DB, MCP, A2A), so an agent test suite runs in under three seconds with identical output every time.
Why MCP alone is not enough between agents: peer refusal, Agent Card discovery, task state, and why A2A v1.0 offers gRPC while MCP stays on HTTP.
How Python's yield differs from return, and how an async generator passed as a prompt streams input into a long-running AI agent, with the Node.js equivalent.