Stage 4 of the agentic development lifecycle (ADLC) · run with
/diagnose.What goes in, what you type, what comes out
Diagnose takes the failures that Evaluate flagged and finds why
they happened — grounded in your real traces, not guesses — then ranks the fixes.
It runs up to five analyzer agents in parallel across slices of your traces; each returns findings
tied to specific runs, which Helix merges, de-duplicates, and ranks by expected impact.
Run it
Point Helix at what’s failing:- Run a root cause analysis on the Deep Research agent’s low-scoring runs and rank the fixes worth trying.
- Find the traces where the Refund Processing agent mis-read the dispute amount and surface the common pattern.
What you get
- Root causes, each tied to evidence from your traces.
- Ranked remedies — the changes most likely to move the verdict, in priority order.
helix -p "/diagnose …") gives you the report; approve from an interactive helix session.
Use it on its own
You don’t have to run the whole loop to use this stage. Once Helix is installed, point Diagnose at your agent’s traces and it returns evidence-grounded root causes and ranked remedies on its own — no spec, build, or evaluate pass required first.Next: Optimize
Apply an approved remedy and re-run the loop.