» Tag
agents
90 postsAI Agent Faked a Test Log, Then Trusted It: The Provenance Gap
Lilian Weng's new survey on self-optimizing agent harnesses shows fake test logs and how provenance vanishes when trajectories get compressed into summaries.
Python library verifies OpenAI's signed AI agent traffic (RFC 9421)
regent-httpsig is an open-source Python library that verifies and signs OpenAI-style AI agent HTTP traffic per RFC 9421 and Web Bot Auth drafts.
Favur Evals: a public benchmark for which AI model codes best
Favur Evals is a public, vendor-independent leaderboard comparing AI models on real software engineering tasks across eight measurable dimensions.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comHow I Cut Agent Token Costs 60% With a 4-Layer Infrastructure Fix
An engineer's 4-layer infrastructure fix — span tracing, tiered caching, prompt compression, and complexity routing — cut agent token bills by 60%.
Inside OpenAI's Agent Loop: How Harness, API, and Inference Cut Costs
OpenAI engineers detail how harness, API, and inference layer optimizations cut cost and latency in agentic systems like Codex and ChatGPT Work.
Back-End Engineering in 2026: APIs Give Way to Agent Orchestration
Back-end engineering in 2026 shifts from stateless APIs to agentic systems: orchestration, async tasks, tool governance, and reasoning traces.
WANDR Benchmark Tests AI Agents on Wide-and-Deep Research Tasks
WANDR benchmark evaluates AI research agents on wide-and-deep data collection tasks using reference-free, evidence-verified grading across 500 tasks.
From Single Agent to Orchestration: When Multi-Agent Systems Pay Off
When to move from a single LLM agent to multi-agent orchestration, the production patterns that matter, and a Rust coordinator/worker example.
memlineage v0.1.0: A Two-Layer Defense Against LLM Agent Memory Poisoning
memlineage v0.1.0 is an open-source Python library defending LLM agents against memory poisoning via cryptographic provenance and behavioral detection.
Building an LLM Wiki: Persistent Memory for AI Agents Over Live Sources
How one team built a self-updating LLM Wiki memory layer for AI agents, tackling live source drift and comparing grep, BM25, vector, and LLM retrieval.