OBSERVABILITY
9 items
6 posts, 3 tools
Pydantic AI V2 explained through v2.68.0: ModelFallback on refusals and max_tokens cutoffs, RequestInput approvals, typed output, Conversation storage, caching, graphs, evals, MCP Apps and Logfire, with checked code.
Cloudflare's Agent Development Lifecycle (ADLC) ships agent tracing with session replay, CI/CD as Workflows, and local OpenTelemetry traces for agent builders.
ORCA-bench puts five frontier coding agents on live oncall root cause analysis with real telemetry. The best scored 10% on hard tasks, far from oncall-ready.
A trending Codex SQLite WAL bug is a useful warning for every local coding agent: logs, disks, background processes, and telemetry paths need budgets too.
Open-source LLM engineering platform: tracing, evals, prompt management, and datasets. Self-hostable, OpenTelemetry-native, with 50+ framework integrations.
Claude Code token burn is an observability problem. Why coding agents need cache-hit telemetry, spend ceilings and repro-grade usage logs, not a quota bar.
Error monitoring and performance tracing with release tracking, session replay, and first-class Next.js support.
Interactive TUI dashboard that shows exactly where your Claude Code and Cursor tokens are going, in real time.
Local OpenTelemetry traces for AI agents: use OTLP and Vercel AI SDK telemetry to get receipts for model calls, tool use, latency, errors and cost.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.