Articles, notes and updates on the agent, the tools, and the craft of building software with AI.
Elyra's @elyracode/semantic-index brings local semantic code search to the agent — find code by what it does, not what it's called, without your source ever leaving the machine.
The model that wrote your code is the worst reviewer of it. Elyra's /review gets you a cold, independent second opinion — no conversation history, optionally a different model entirely, scoped to exactly the changes you care about.
Elyra 0.9.3 ships extension_write — the agent can now author its own extensions, with your sign-off.
Elyra's /bisect borrows git's binary-search debugging and points it at the agent's own turns — finding the exact one that introduced a regression.
A terminal text editor was doing the same expensive work three times per keypress. The fix was easy — and a bigger, faster fix was sitting right next to it. This is about why I walked away from the bigger one.
Elyra v0.9.2 makes /update bring your whole setup — the agent and every extension — current in a single step. Plus two quieter reliability fixes.
Elyra Conductor 0.7.4 adds a runbook recorder — press record, do the work in your terminal, and Conductor hands you a runbook draft of exactly what you ran.
How Elyra Conductor 0.7.0 teaches your shell to narrate its own lifecycle — real command lines, exit codes, and a per-project test badge — without ever touching your prompt.
Elyra Conductor 0.6.3 teaches the database browser to tunnel through SSH, splits a crowded header into two calm rows, and lets you export a whole table — not just the page you can see.
Elyra Conductor 0.6.2 lets you hand a query result, a single row, a table's schema, or a piece of SQL straight to an Elyra agent — as text, pre-filled, ready for your question. A fireside look at why 'askable' was the missing verb, and how it stays on the right side of the line.