In Daniel Miessler’s LifeOS workflow, Jev answers a set of structured questions about the current prompt and the end of the preceding reply. Two learned models then use those answers, plus three basic prompt facts, to recommend a model lane and reasoning effort. The recommendation is advisory: it does not dispatch the task, and Daniel’s explicit instructions take precedence.
What Jev looks at before choosing
Jev does not simply classify a prompt in isolation. It receives the current prompt together with the last 800 characters of the preceding reply, when one exists, so it can interpret short follow-ups in context. In the reported evaluation, about three quarters of prompts had a previous reply attached.
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
AMD Ryzen™ AI Halo - Personal AI Desktop Computer - Developer Platform - Linux OS | $3,999.99 | Buy on Amazon |
| 2 |
|
GMKtec EVO-X2 AI Mini PC AMD Ryzen Al Max+ 395 Up to 5.1GHz, 16C/32T | $2,199.99 | Buy on Amazon |
As an Amazon Associate I earn from qualifying purchases.
Jev responds with structured choices or probabilities, not the answer to the user’s task. Its eighteen questions cover three areas:
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Repair Windows errors before they cause bigger problems3Fix the driver behind crashes, sound loss and screen glitches- Requested work and task characteristics: The original nine questions consider the kind of work, risk, breadth, automation potential, whether the approach is settled, and how much judgment or reasoning is needed.
- Effort: Five added questions assess breadth versus depth, the cost of subtle errors, interacting considerations, whether speed matters once the task is understood, and whether the user explicitly asks for depth.
- Conversation relationship: Four questions identify whether the prompt approves a proposal, acknowledges something, corrects or pushes back, or starts a new request.
Three additional facts go to the learned mappers: whether the prompt contains depth-related wording, its length, and whether a previous reply is available. Jev’s answers do not directly name the final model or effort; two small learned models map the answers and facts to those choices.
#1 Best Overall
- Built for Local AI Development: AMD Ryzen AI Halo is designed for local AI development and inference, featuring 128GB unified memory and support for up to 200B parameter models to build and run intensive AI workloads locally.
- 128GB Unified Memory: Features 128GB LPDDR5x unified memory at 8000 MT/s with 256 GB/s memory bandwidth, providing a shared memory pool across the CPU, GPU, and NPU to support larger AI models.
- AMD Ryzen AI Max+ 395 Processor: Features 16 cores, 32 threads, and Zen 5 architecture, paired with AMD Radeon 8060S integrated graphics featuring 40 RDNA 3.5 compute units and an AMD XDNA 2 NPU with up to 50 TOPS.
- Linux AI Developer Platform: Purpose-built for Linux-based AI development with full AMD ROCm software support and preloaded tools, models, and workflows optimized for local AI development.
- Compact, Connected Design: Includes a 2TB M.2 SSD, 10GbE LAN, Wi-Fi 7, Bluetooth 5.4, USB-C connectivity, and HDMI 2.1b.
How Glance turns those answers into a recommendation
Glance is the surrounding judgment and control layer. It asks Jev typed decision questions, then manages caller-specific thresholds, a daily budget, and a decision ledger. A new caller starts in shadow mode; moving to enforcement requires a recorded agreement rate, date, and Jev model. The LifeOS article describes its router as remaining in shadow, so its picks are advice rather than automatic hand-offs.
The design evolved from a single seven-lane choice, which agreed with an earlier Astra classifier on 57% of 662 prompts. The next version decomposed the decision into nine yes-or-no questions, initially mapped by hand and later by a small learned model. The mature version added effort and conversation-context questions.
Practical routing rules and exceptions
- Opus versus Sol: The stated rule is whether a pass/fail check can be written before work starts. If so, the work is treated as settled and Sol can handle it.
- Maximum effort: A Max-level task is routed to Opus at xhigh effort. Fable is used for second opinions.
- Explicit depth requests: Asking to “think deeply” or using similar wording forces Opus at xhigh effort.
- Prompts that bypass routing: Acknowledgements and slash commands skip the router. Prompts that look like credentials also skip routing.
- Privacy handling: Email addresses and phone numbers are redacted before Jev or Opus sees them.
- Fallback: If Jev times out or returns an incomplete answer, the Opus classifier is used. That classifier also selects thinking skills for depth prompts.
These rules describe the LifeOS workflow in Kai’s account of it. A separate Jev Codex implementation illustrates configurable safeguards such as eligible effort levels, task-capability and request-kind classification, routing preferences, effort ceilings, and usage policy; it should not be treated as a description of LifeOS’s code or controls. See the Jev Codex implementation and the Made with Jev guide for that separate context.
What the reported evaluation shows—and does not show
Daniel Miessler’s LifeOS team reported results in 2026 from 1,000 real prompts sampled from Daniel’s transcripts. Automated jobs, hook output, pasted notifications, and messages from other agents were excluded; prompts remained private on Daniel’s machine. The evaluation held out data by conversation and compared choices with majority-vote labels from three model labelers.
Rank #2
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 64GB pool, which is perfect for running LLMs such as Deepseek 32B, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 4% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
| Measure | Reported result | What it compares |
|---|---|---|
| Glance lane agreement | 90.1% | Agreement with majority-vote lane labels |
| Opus classifier baseline lane agreement | 75.2% | Same 1,000-prompt comparison |
| Always-stay-inline baseline lane agreement | 83.9% | Same 1,000-prompt comparison |
| Glance effort match | 70.0% | Agreement with majority-vote effort labels |
| Agreement among the three labelers | 79.4% | How often the labelers agreed on lane labels |
The 90.1% lane figure measures agreement with the labeling process, not whether the chosen model completed a task successfully. The 70.0% figure is the corresponding effort match. Because the labelers themselves agreed on lane labels 79.4% of the time, the reference standard was not perfectly consistent. The dataset is private, so the prompt-level labels and experiment cannot be independently reproduced from the published account. These results describe one dataset and should not be read as a guarantee for other users or routing systems.
The same LifeOS account reports about 0.3 seconds per prompt for Glance routing, compared with about 3.3 seconds for its Opus classifier. Those are author-reported timings for that implementation, not general latency figures.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.When the recommendation can be followed
Jev proposes a route; it does not dispatch work by itself. As Kai puts it, “The pick is advice: it never dispatches work by itself, and Daniel’s explicit instructions always win.” Glance’s thresholds and shadow-mode operation are part of the described control process, but the article does not establish that its recommendations reduce cost or improve task success beyond the reported label agreement.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →For context, see the LifeOS account of the Jev model router and its reported evaluation.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
