EP227：使用 Jev 的九大场景
ByteByteGo 通讯介绍 TypeSafe AI 的 Jev 系统一模型，列出模型路由、护栏、工具调用门控等九类替代 LLM 的决策场景。
中文处理结果
[网络研讨会] 如何不再当智能体的保姆（赞助内容）
智能体可以生成代码。但要让代码符合你的系统、团队约定和过往决策，才是难的部分。你最终会在纠错循环中浪费时间和 token。
更多的 MCP、规则和更大的上下文窗口让智能体获得了信息，却没有获得理解。领先的团队拥有一个上下文层，为智能体提供完成当前任务所需的确切内容。
欢迎参加 10 月 7 日的免费网络研讨会，了解：
- 团队在 AI 成熟度曲线上卡在哪里，以及为什么常见修复手段效果不佳
- 上下文层如何解决质量、效率和成本问题
- 现场演示：同一编码任务在有和没有上下文层时的对比
如果你想最大化 AI 智能体带来的价值，这场活动值得你花时间。
立即注册
本周系统设计速览：
- 使用 Jev 的九大场景
- LLM、RAG、AI Agent 与 Agentic AI
- 前 YouTube 工程师 45 分钟重建 YouTube（YouTube）
- MCP 与函数调用
- 如果 Claude Code 是一个汉堡……
- 重建 YouTube 直播课程今日开课
使用 Jev 的九大场景
Jev 是 TypeSafe AI 的第一个系统一模型（System One Model）。它比前沿 LLM 快 100 倍、便宜 100 倍。
这开启了许多人们通常因为大模型太慢或太贵而跳过的用例。
以下是使用 Jev 替代 LLM 的九大场景：
- 模型路由。Jev 将提示词作为输入，并将其路由到合适的 LLM。
- 护栏。先检测提示词中的安全风险，再将其传给 LLM。
- 工具调用门控。将智能体的工具调用归类到某个权限类别中。
- 收件箱分诊。将大量邮件分类（例如垃圾邮件、紧急、归档）。
- 重排序。根据查询（提示词）为段落打分，以便按相关性排序。
- LLM 评估。评估 LLM 的输出并返回一个范围内的分数。
- 批量标注。以 map-reduce 方式快速、低成本地为大表中的大量行打标签。
- 实时决策。需要在循环中快速做出决策的用例（例如交易）。
- 置信度门控。根据置信度对任何内容进行分类并采取相应行动。
底线是：用 LLM 做生成，用 Jev 做围绕生成的决策。
还有哪些地方可以用 Jev 替代 LLM？
LLM、RAG、AI Agent 与 Agentic AI
LLM：LLM 接收用户提示词，并从其学到的参数中生成响应。它通过一次预测一个 token 来完成。
RAG：在 RAG 中，用户查询先到达检索器，再到达 LLM。检索器从索引知识库中获取相关信息，并将其与查询一起传给 LLM。LLM 生成有依据的响应，但不保证正确性。
AI 智能体：它有一个目标，并跟踪当前任务状态。它可以规划下一步做什么、调用工具、获取结果、观察结果，并重复直到目标达成。这种反馈循环让智能体能够观察结果并相应调整行动。
原始正文摘录
EP227: Top 9 Places to Use Jev
[Webinar] How to stop babysitting your agents (Sponsored)
Agents can generate code. Getting it right for your system, team conventions, and past decisions is the hard part. You end up wasting time and tokens in the correction loops.
More MCPs, rules, and bigger context windows give agents access to information, but not understanding. The teams pulling ahead have a context layer to give agents exactly what they need for the task at hand.
Join us for a FREE webinar on Oct 7 to see:
- Where teams get stuck on the AI maturity curve and why common fixes fall short
- How a context layer solves for quality, efficiency, and cost
- Live demo: the same coding task with and without a context layer
If you want to maximize the value you get from AI agents, this one is worth your time.
Register now
This week’s system design refresher:
- Top 9 Places to Use Jev
- LLM, RAG, AI Agent & Agentic AI
- Ex-YouTube Engineer Rebuilds YouTube in 45 Mins (Youtube)
- MCP vs Function calling
- If Claude Code is a burger...
- Rebuild Youtube Live Course Start Today
Top 9 Places to Use Jev
Jev is TypeSafe AI’s first System One Model. It is 100x faster and cheaper than frontier LLMs.
That opens up a lot of use cases people usually skip because the big models are too slow or too expensive for them.
Here are the top 9 places to use Jev instead of an LLM:
- Model routing. Jev takes the prompt as input and routes it to a proper LLM.
- Guardrails. Detect security risks in the prompt first. Then pass it to the LLM.
- Gating tool-calls. Classify agent tool calls into one of their permission categories.
- Triage inbox. Classify lots of emails into categories (e.g., spam, urgent, archive).
- Reranking. Score passages against a query (prompt) so we can rank them by relevance.
- LLM evals. Evaluate an LLM’s output and return a score within a range.
- Bulk labeling. Label lots of rows from a huge table fast and cheap (map-reduce style).
- Real-time decisions. Use cases where a fast decision is needed in a loop (e.g., trading).
- Confidence gate. Classify anything based on confidence and act properly.
The bottomline is to use the LLM for generations and use Jev on the decisions around it.
What are other places to use Jev instead of an LLM?
LLM, RAG, AI Agent & Agentic AI
LLM: An LLM takes a user prompt and generates a response from its learned parameters. It does so by predicting tokens one at a time.
RAG: In RAG, the user query goes to a retriever before the LLM. The retriever fetches relevant information from the indexed knowledge base and passes it to the LLM along with the query. The LLM generates a grounded response, but it does not guarantee correctness.
AI agent: It has a goal and keeps track of the current task state. It can plan about what to do next, call tools, get a result back, observe it, and repeat until the goal is met. This feedback loop allows the agent to observe the results and adjust its actions accordingly.
Agentic AI: Putting one or more AI agents to meet a shared objective is what makes an AI system agentic. It is achieved through planning, tool use, and feedback. You add an orchestration layer, which coordinates work across multiple agents and workflows. Agents read and write to shared task states and can access tools, data, and the environment.
Ex-YouTube Engineer Rebuilds YouTube in 45 Mins
MCP vs Function calling
MCP and function calling have a lot in common. This confuses a lot of engineers, so here is a side-by-side comparison.
Both MCP and function calling are mechanisms that allow an LLM to have access to tools. The agent runtime sends the prompt to the LLM, the LLM decides which tool to use and emits a tool call request.
The agent runtime then handles tool call execution and returns the results back to the LLM to continue. The LLM finally produces a final output shown to the user.
What is different between the two is where the function is implemented, and how the agent handles the execution. In local function calling, the functions are implemented locally on the user's machine. The agent runtime executes them and receives the results.
In MCP, the functions can be outside of the user's machine, on some remote server. The agent runtime follows the MCP protocol and calls the corresponding server, the execution happens remotely, and the results are sent back to the agent runtime.
This allows your agent to connect to hundreds of thousands of tools that are implemented publicly and hosted remotely.
Over to you: What are the best MCP resources out there?
If Claude Code is a burger...
Before each model call, Claude Code assembles a context window from 9 distinct sources.
Think of it as a burger, each layer adds something different.
- System Prompt: Defines Claude's role, behavior, and tone. This sets the foundation.
- Environment Info: Git status, branch info, and current date. Pulled in via getSystemContext()
- CLAUDE.md: A four-level instruction hierarchy: managed → user → project → local. Plain-text Markdown, so users can read, edit, and version-control everything the model sees.
- Auto Memory: Contextually relevant memory entries prefetched asynchronously. An LLM scans memory-file headers and surfaces up to 5 relevant files on demand.
- Path-scoped Rules: Conditional rules that load lazily when the agent reads files
- Tool Metadata: Skill descriptions, MCP tool names, and deferred tool definitions.
- Conversation History: Carried forward across iterations.
- Tool Results: File reads, command outputs, and subagent summaries.
- Compact Summaries: When history grows too long, older segments are replaced by model-generated summaries.
Rebuild Youtube Live Course Start Today
Rebuild YouTube with AI, taught by a former YouTube engineer, kicks off on Saturday, September 26. Enrollment closes in 24 hours.
Check it out Now →
What you will learn
- Scope a realistic MVP. Decide which YouTube features to build and break the work into manageable tasks.
- Work with agents. Plan changes, review generated code, and recover from bad diffs or sessions that go off track.
- Build across the stack. Turn mockups into React pages and build a backend with Postgres, authentication, and video uploads.
- Add semantic search and related videos. Use multimodal embeddings and understand how this approach differs from production recommendation systems.
- Test and deploy your app. Check features with Playwright, deploy to Vercel, and track watch time in an admin dashboard.
Check it out Now →