Jobs
0
Grounded analysis · heuristic compose · optional Groq or OpenAI
Command center
Run a bundled scenario, then inspect incidents, anomalies, and the grounded report. Use the model trace, facts vs rewrite, and closed-book Q&A when you walk an interviewer through it.
Jobs
0
Incidents
0
Anomalies
0
No jobs yet. Run Checkout cascade for a full report, Healthy baseline for an empty ledger, or Degraded partial for a sparse-data completion.
Jobs are in-memory analysis runs for this API process. Incidents are correlated candidates. Anomalies are raw detector hits. A healthy window can complete a job with zero incidents — that is a success, not a missing chart. Degraded partial is for missing-signal resilience: the run summary will warn, the board will still render.
Interview walkthrough
01 · What this is
This is an AI systems project, not a trained model. Detectors are z-score and MAD. Correlation and RCA are graph heuristics. The LLM is optional last-mile rewrite.
02 · Facts vs rewrite
Left column is immutable detector output. Right column is a narrative over that JSON. Toggle heuristic vs Groq on the same incident — the facts do not move.
03 · Model trace
Every run records provider, model, tokens, latency, cache hits, and fallback. If Groq 404s, the board still has a heuristic report instead of a blank page.
04 · Closed-book Q&A
Ask what checkout CPU was versus baseline and it cites the pack. Ask about weather or a service that was not in the run and it refuses. That refusal is the product.
01
API health on :8000, then a bundled scenario. Checkout cascade is the noisy path. Healthy baseline is the empty-ledger control.
02
Fourteen detector hits should collapse to one incident. If they do not, correlation failed — that is a bug, not a preference.
03
Primary service is a ranked guess. Evidence rows are facts. Contain the origin, not every downstream waiter.
04
Paste the engineering section into the ticket. Facts stay attached to detector ids so the next shift does not re-litigate the window.
05
reviewed, then approved or rejected with a name and a note. Only approved reports may leave through a webhook.
Restarting uvicorn clears jobs. JSON under artifacts/ui/ remains. Re-run a scenario to refill the console.
Jobs pass data/knowledge/runbooks and incidents. Citations appear when snippets overlap the evidence bundle.
Compose is heuristic over the evidence bundle. Groq or OpenAI is an optional rewriter. The model trace on Overview tells you which one actually ran.
Identical compose inputs reuse output. Delete the cache directory if you change heuristic copy and need a fresh narrative.
Host allowlist, HTTP and private-network flags default off. A file path is enough for every bundled scenario.
The API returns 400 without a reviewer. Webhooks only fire for approved reports after URL policy checks.