Agent Logs: Trace Tool Calls, Retries, and Outcomes
Connect agent runs to their tool calls, permissions, retries, parallel work, and final outcomes through a clear execution record.
THE SIGNAL / TOPIC THREAD
Observability.
A thread worth following.
Choose signals that answer a real investigation question. These articles connect event context, timing, collection reliability, and the limits of what a record can prove.
A useful reading path
Use this collection when you need to connect a user-visible problem to the service, attempt, or delivery path behind it. Begin with the article closest to the system you operate, then compare how the same context travels across adjacent systems.
Articles tagged Observability
LLM Token Logging: Measure Usage, Latency, and Cost
Build an interpretable record of LLM usage, timing, retries, and cost estimates while preserving incomplete accounting states.
Email, Phone, CRM, and Calendar Logs: Follow the Event
Connect email, phone, CRM, and calendar activity with explicit event identities, channel-specific outcomes, and a workflow you can actually reconstruct.
AI Logs API: A Practical Guide to Useful Events
Design AI events that connect requests, model attempts, validation, and outcomes without filling logs with sensitive content.
Server and Linux Logs: Build a Reliable Collection Pipeline
A practical approach to collecting server and Linux events, preserving useful context, and handling gaps, retries, and sensitive data.
iOS and Android Logs: Debug Mobile Apps Responsibly
Design mobile diagnostic events that explain lifecycle and network failures while minimizing personal data and device overhead.