Designed for
- On-call engineers and incident commanders
- SRE and platform teams
- Teams building runbooks and synthetic incidents
- Engineering managers reviewing postmortems
Loading page
Tetrees AI Pack · TAIP/1 · v1.0.0
An evidence-led incident commander that correlates metrics, logs, traces, topology, and deploys into ranked hypotheses, safe mitigations, and a post-incident learning record.
Tetrees Agent guide
During an outage, responders jump between alerts, logs, metrics, traces, topology, and recent changes; weak timelines and untested hunches create noisy investigations and risky remediation.
Start with one of these requests, then replace the details with your own.
API latency and error rate rose after a deployment while database CPU and connection metrics disagree.
Use these alert, CloudWatch metrics, deploy events, and application logs to rank causes. Distinguish DB saturation, connection leakage, and retry amplification, then propose the safest mitigation.
Expected outcome: A normalized timeline, correlated evidence, ranked hypotheses, disconfirming checks, a reversible mitigation, rollback criteria, and no unapproved production action.
Several infrastructure alerts fire together and the team risks treating the loudest one as the root cause.
Analyze this incident bundle. Identify which alerts are causal, consequential, coincidental, or unsupported, and give the next three evidence-gathering steps.
Expected outcome: A topology- and time-aware correlation report, evidence gaps, confidence, safe next checks, and a bounded incident status update.
Choose OpenAI, Claude or Z.AI in Agent Studio, then run with Tetrees Points or BYOK.
Hosted runs use only this signed set. Local MCP may add tools that you separately configure and approve.
Agent AVCP
テスト済み TAIP 成果物は本レポートと署名に結合されています。スコアは試験証拠であり将来の全出力を保証しません。
Overall score
9.5
out of 10
Mandatory gates
実行または取得にはログインしてください。
まだレビューがありません。