Today's brief: four to read
Research
Papers, benchmarks, and what we'd build differently after reading them.
Research · Jun 19 · 9 min
68 Agent Papers Map Production LLM Engineering
Research · Jun 19 · 6 min
CUA-Gym Generates 32K Verified RLVR Tuples for Computer-Use Agents
Research · Jun 15 · 7 min
AgingBench Measures How Deployed AI Agents Degrade
Research · Jun 15 · 7 min
LAP Protocol Targets Agent-to-Instrument Gap in Labs
Tutorials
Code-first dispatches. Every code block runs before publish.
Tutorial · Jun 19 · 10 min
Building a LangGraph Agent That Reads Figma Layouts via MCP
Tutorial · Jun 15 · 12 min
Build a Reproducible CrewAI Multi-Agent Eval Harness with Braintrust
Tutorial · Jun 15 · 12 min
Eval Harness for a CrewAI Agent Using Braintrust and Verifiable Rewards
Tutorial · Jun 15 · 11 min
Multi-Agent Economy Simulation with vLLM, OpenTelemetry, and Phoenix Tracing
Tools this week View all
vLLM
High-throughput LLM serving with KV-cache management and OpenAI-compatible APIs.
Jun 19
High-throughput LLM serving with KV-cache management and OpenAI-compatible APIs.
LangGraph
Stateful, multi-actor agent graphs built on top of LangChain.
Jun 19
Stateful, multi-actor agent graphs built on top of LangChain.
OpenTelemetry
Vendor-neutral telemetry standard. The connective tissue under most agent traces we cover.
Jun 19
Vendor-neutral telemetry standard. The connective tissue under most agent traces we cover.
Claude Code
Anthropic's CLI coding harness. Hooks, MCP servers, traceable tool calls.
Jun 5
Anthropic's CLI coding harness. Hooks, MCP servers, traceable tool calls.