Guides / illustrated walkthrough
Jev Log Triage with Expanso Edge
Follow an Expanso Edge and Jev log-triage demo using synthetic events, from deterministic filtering and selective classification to notify, review, and outage-buffer paths.
Quick takeaway
The video frames its example as a production logging scenario, but the interface labels the records “Synthetic demo events” and the buckets “local demo files”; this is not live production telemetry. It shows Expanso shaping and filtering the stream, then adding Jev for selected context-dependent decisions while most events stay on deterministic paths. Results can go to notification or review, and the presenter demonstrates buffering during a Jev outage. Queue limits, delivery guarantees, and independent cost or accuracy benchmarks are not provided; verify them in your own deployment.
Video source
Expanso
Step-by-step walkthrough
- 1
Start with the raw log destination and its missing context
The presenter uses a standard production logging pipeline to explain the problem, but this screen labels the records “Synthetic demo events” and the destination “local demo files.” It is not connected to live production logs. The example illustrates how structured records can lack diagnostic context and how moving every line can add cost; it is not evidence that every raw bucket is wasteful. Decide which fields, aggregates, and retention periods your own team needs.
The demo uses synthetic events and a local raw-log file.Watch at 0:32 - 2
Prepare the baseline Expanso Edge pipeline before adding Jev
The presenter opens the `Edit Pipeline: log-triage` form while preparing the baseline flow for deployment. This frame shows the pipeline name, description, and configuration sections; it is not a deployment-health screen. The video later reports the deployment running, but verify runtime status and output separately in your own environment before adding an external model dependency.
This frame shows pipeline settings, not deployment health.Watch at 1:04 - 3
Keep routine log shaping on a deterministic path
The Pipeline YAML view has `pipeline-logging.yaml` selected. Its visible configuration normalizes values against closed sets, fingerprints and counts events, and archives routine records; the screen itself says “No model needed.” It also identifies the YAML as checked-in source configuration, not a file read back from Expanso Cloud. Treat this as the deterministic baseline; the presenter adds Jev for selected decisions later in the walkthrough.
The checked-in baseline YAML shapes and archives logs without a model call.Watch at 2:34 - 4
Route high-signal decisions to notification or human review
This live-flow screen still uses synthetic demo events and local demo files, not production records or outcomes. It shows Jev adding likelihood information to selected decisions, with notification and review paths for events that may need attention. Expanso still owns deterministic gates and destinations, and the video does not define universal probability thresholds. Set thresholds from labeled examples, preserve an ambiguous or low-confidence path, and test actions before enabling paging.
Synthetic events illustrate notification and review branches.Watch at 3:34 - 5
Buffer work when the Jev connection is interrupted
The review screen is part of the same synthetic-event demo and shows a local `review.jsonl` file. The presenter demonstrates breaking the Jev connection, holding pending decisions in Expanso’s buffer, and draining them after connectivity returns. This is a resilience pattern, not a delivery guarantee for every deployment. Before production, confirm queue capacity, retention, replay ordering, duplicate handling, and buffer-full behavior against Expanso documentation and a failure-injection test.
Test outage recovery with your own queue and replay policy.Watch at 4:44
Frequently asked questions
Does Jev classify every event in this log-triage demo?
No. The synthetic events mostly stay on deterministic Expanso paths; only selected records go through Jev. Filtering before inference keeps the model focused on decisions that need context.
What does Jev add to log triage?
It provides typed classification decisions and probabilities for selected unstructured events. Expanso still handles the pipeline, deterministic gates, and destinations such as notification or review.
What happens if the Jev connection goes down?
The video demonstrates Expanso buffering pending decisions and draining them after the connection is restored. It does not specify queue capacity or delivery guarantees; check your deployed configuration and test recovery behavior.
Does this video provide a production benchmark or alert threshold?
No. It is a workflow demonstration, not an independently measured latency, cost, or accuracy benchmark. Choose alert thresholds from your own labeled events and monitor false positives, misses, and queue behavior.
Related guides
NOC/SOC Alert Triage with Jev
The incident-level sibling: rules first, one typed route question, and a 0.85 confidence policy gate for alert triage.
ReadJev Model: Choice, Score, and Noul
Choose a typed output for event categories, severity scores, or yes/no gates.
ReadJev API Examples: curl, Python, and JavaScript
Inspect request payloads and read the typed answers returned by Jev.
ReadJev API Errors and Rate Limits
Plan retries and diagnose upstream errors without inventing undocumented limits.
ReadJev Lead Enrichment with Treg
See another selective classification workflow, this time for lead enrichment.
ReadUse Jev Decision Nodes in Heym
Follow a Heym language-check workflow and inspect runtime model routing.
ReadMore video walkthroughs
- Jev Classification Quickstart: OpenRouter API, Primitives & Real Probabilities
- Jev Architecture Explained: Why 70ms Decision Models Beat LLMs for Workflow Automation
- Ultra-Fast Browser Agents with Jev: 178ms DOM Loops & Dual Model Orchestration
- Open Jev Models Are Here: Semif, Nimble, Decider, DiffusionGemma & Laya Hands-On
- Jev vs LLM: Will Jev Replace LLMs? Krish Naik's Whiteboard Explainer
- Jev Trader Tutorial: Build a Subsecond AI Trading Bot on Monad
- Jev Model Router: Build a Privacy-Gated LLM Router with Jev & OpenJev
- Jev Tutorial for Beginners: State, Questions & the TypeScript SDK
- Run Jev Locally: Kev, SemIf & Von on Your Own GPU (OpenJev Guide)
- Jev RAG Reranker: Policy-Steered Reranking for Retrieval-Augmented Generation
- When to Use Jev: An Engineer's Audit of Claims, Gates, and Failure Modes
- LangChain + Jev Integration Tutorial: Routing, Guardrails & Evals
- Jev MCP Server: Connect Jev Decisions to Claude Code & Cursor
- Jev vs Luna: Independent Benchmarks Put "Better, Faster, Cheaper" to the Test
- Jev Agent Harness: Where the Decision Gate Sits in Your LLM Loop
- Jev Playground Walkthrough: The Hotdog Lesson, Criteria, and a Four-Console Token Test
- Jev Text Classification API: Zero-Shot CLI & REST with classifier.dev
- Jev API Examples: First Request, curl & All Three Question Types
- Jev Lead Enrichment with Treg: ICP and Signup Scoring
- Use Jev Decision Nodes in Heym for Model Routing
- Laya Tutorial: Open-Source AI Routing With Calibrated Probabilities (Laya vs Jev Setup)
- Train Your Own Jev: Fine-Tune a Jev-Style Decision Model for $5–$17 (What You Can and Cannot Train)
- Jev Tips: 8 Best Practices for Better Decisions (State, Questions, Criteria & Thresholds)
- Jev Context Compaction: Prune AI Agent Memory Without Generative Summaries
- Jev as an LLM Judge: Confidence-Gated Cascades at 0.36% of the Cost
- TypeSafe Computer Use: Local Desktop Automation with Jev, Step by Step
- Jev Resume Screening: Build an AI Resume Evaluator with the Jev JavaScript SDK
- Jev + Claude Code Guide: Voice-Controlled Browser Automation with Typed Decisions
- Jev + Codex: Install the TypeSafe Skill and Triage a Real Gmail Inbox
- Jev vs Ollama: Can Local AI Replace Hosted Jev Without Sending Your Data Away?
- Build Your Own Jev: Train a Free Open-Source Zero-Shot Classifier (That Plays Doom)
- CUA-S1-Forms: a 706K-Parameter Jev-Like Model That Fills GUI Forms on Your CPU
- NOC/SOC Alert Triage with Jev: Rules First, One Typed Question, a Policy Gate
- Ollama Decision Models: Run tev1 and Nimble Locally (Tested on an 8 GB Card)
- Jev Guardrails in Production: A Five-Step Playbook for Decision Automation
- A Session Drift Guard for Pi Agent: Let the Jev Model Propose, Let Code Decide
- 50 Tev1 Use Cases: What a Local Decision Model Can Actually Do (Tested on an 8 GB Laptop)
- Jev, Hands-On: Where the Official Claims Meet Independent Remeasurement
- Jev Ticket Classification in a Real App: the After-Insert Hook and the Calculated Field
- OpenJev RLCD: Run the Open-Source Calibrated Decision Model Locally (Full Guide)
- Clef-Flash vs Jev: I Tested Cloudflare's Decision Model Locally in Ollama (Q4_K_M)
- Clef-Flash Tutorial: Install and Run Cloudflare's 9B Multimodal Decision Model Locally on Ubuntu
- CLM-8B: the Contrastive Decision Model That Scores 1,024 Options in 44 ms (13x Faster Than Jev)
- Nox 4B Tutorial: Run the Decision 2.0 Model Locally and Put It Through Four Real Decisions (One Ends in a Fail)
- Julia-1 Tutorial: Install the Open-Source Jev Replacement in Pure Python (and Watch It Beat If-Statements 9 to 2)
- OpenJev 0.8B on CPU: I Built a Ticket-Routing Inbox and Calibrated the Thresholds
- Jev n8n Integration: the JevGate Community Node, Step by Step (Plus a Plain-HTTP Fallback)
- NanoJev Tutorial: Install the 0.6B Open-Source Jev Replica and Watch It Route Decisions at 47 ms
- PPLX Decider Tutorial: Perplexity's Open 27B Decision Model, Its Decisions API, and a 12-Ticket Triage Run
- AutoTrust JEV-27B Tested Locally: Four Arms, 72 Cases, and One 0.969 Score That Was Wrong
- Clef 27B Locally: Watch Cloudflare’s Multimodal Decision Model Read an Image, a Video and an Uzbek Newspaper in One Pass
- Ollaya Guide: Install the "Ollama for Decision Models" Runner, Read Every Vendor-Reported Number, and Run the CPU Test It Leaves Open
- Strands Decider 2B Tutorial: Install the AWS Strands Decision Model on an 8GB Laptop — and Keep Its Failures In
- Liquid AI Open d1 Locally: d1-3B and d1-omni-600M on a MacBook Air M5 — Guardrails, Screen Checks, Voice Routing and Document Triage, Every Number Frame-Checked
- Image Decision Models for RPA: Watch Two Open Models Review an Unsigned W-8BEN With No OCR
- GLiNER2.5-Decide (340M) vs Jev (4B): Which Decision Model Actually Wins? A Frame-by-Frame Selection Guide
- Decision Models on Jetson: Jev vs Strands Decider 2B vs Laya vs d1-3B — Skill Master Scores, Thor Latency and JevBench, Every Number Frame-Checked
- Microsoft Decision-1 Tested: 146 Independent Tests, a 93% Mean, 124/125 When Confident — Every Number Frame-Checked
- Wire Jev into an Azure AI Foundry Agent as the Evaluation Layer — OpenAPI Tool, TypeSafe Connection, Triage Instructions and an Honest First-Run Failure