Agent Ops playbook
Agent Tool Failure Triage
Daily clustering of tool-level failures across execution step outputs, filing one ticket per novel failure cluster.
Daily, reads execution step outputs for tool-level failures (a tool erroring, an MCP server failing to connect, a sandbox checkout failing, a git provider call rejected, a run hitting its iteration ceiling without finishing), clusters them by cause, and files a ticket per novel cluster with the failing tool, the frequency, the affected playbooks, and the likely fix.
- Identifier
agent-tool-failure-triage- Version
- 1.0.0
- Steps
- 3
- Triggers
- 1
- agent-ops
- tool-failures
- triage
- observability
- automated
- daily
When it runs
schedule.daily- Schedule
- Every day at 07:00 UTC
0 7 * * * - Timezone
- UTC
The pipeline
The graph below is the one the workflow opens with in the builder, same steps, same layout, drawn on the same canvas. The run playing through it is a simulation; the branches and conditions are real.
- 01Daily Schedule (07:00 UTC)
triggerThe event that starts the run.
- 02Triage Tool Failures
agent.runOne agent works the task with its toolkit.
- 03File Failure Triage Ticket ⚠️ SET YOUR TICKET INTEGRATION
ticket.createOpens a ticket on the connected tracker.
The agent
Tool Failure Triage Agent
- Base type
- Senior Developer
- Temperature
- 0.2
- Max iterations
- 50
- Tools
- 7
Memory · 2
memory_writeWrite Memory · writememory_readRead Memory · read
Terminal · 1
run_terminal_cmdRun Terminal Command · write
Filesystem · 1
read_fileRead File · read
Code search · 1
code_searchCode Search · read
Tickets · 1
create_ticketCreate Ticket · write
Status · 1
update_statusUpdate Status · write