Glean 拾遗
中 EN
Submit a link
Daily · timeline

A few picks a day.

Mon, Jul 27, 2026 3picks
← 07-26
Calendar ▾
2026 · 07
MoTuWeThFrSaSu ··12345678910111213141516171819202122232425262728293031
has picks today
06:00

Ultrareview: Deep code review with remote sandbox agents

Ultrareview：Claude Code 远程多 Agent 深度代码审查

Ultrareview is a deep code review feature from Claude Code that launches a fleet of reviewer agents in a remote sandbox to find bugs in your branch or pull request. Compared to local review, it offers higher signal (each finding is independently verified), broader coverage (parallel agents), and no local resource usage. Use /code-review ultra from the CLI; supports base branch, PR number, and plain-word descriptions. Non-interactive subcommand claude ultrareview is available for CI. Billing: 3 free runs for Pro/Max, then $5–$25 per review. Diff limit: 500 files / 8,000 lines. Runs in 5–10 minutes. Useful before merging substantial changes.

code.claude.com · 9 min · Agents · Claude Code · Code Review · Developer Tools
06:00

Why Harness Engineering Is So Hard

LLM护套工程为何如此困难——从测试到迭代的真实痛点

Based on five months of real-world experience (104 commits), this article dissects the structural difficulties of turning LLM demonstrations into reliable products. Key challenges include: inability to write deterministic tests (same input yields different output each time), silent and graded failures (1% error hidden in 99% correct output), debugging natural language paragraphs instead of code (a single adjective can be a bug), the additive instinct trap (prompt growing from 20 to 200 lines causes contradictions), examples steering harder than rules, unstable model foundation (vendor updates silently shift behavior), slow and expensive feedback loops, and invisible work (outsiders think it's just writing prompts). The author argues that harness engineering (prompts, validators, evals, guardrails) is the true moat, with difficulty stemming from the probabilistic nature of the substrate, which cannot be engineered away but only absorbed. Recommended for LLM app developers, AI engineers, and tech leads.

x.com · 16 min · AI Engineering · Developer Tools · LLM · Prompt Engineering
06:00

Agent Harness Engineering vs. Loop Engineering vs. Graph Engineering

Agent 架构三层次：Harness、Loop 与 Graph 工程区分

A practical guide distinguishing three architecture layers for AI agents: Agent Harness (code, config, runtime around the model), Loop (repeated work-feedback cycles), and Graph (explicit workflow topology). The author explains what each layer owns, common mistakes, and how to choose the right lever when debugging. Includes a symptom-to-layer mapping table and a production-ready checklist. Essential reading for teams moving agents from demos to production.

x.com · 17 min · Agent Architecture · Agent Engineering · Agents · AI Engineering · LLM