Blog category

AI and Machine Learning

Applied AI guidance for computer vision, voice, agents, RAG, workflow automation, TinyML, and AI-enabled connected products.

Category articles

AI and Machine Learning articles

AI-generated scene of a wall-mounted control panel in a home, not a product or field test
Nov 11, 2026

Upgrading a Smart Control Panel for AI: Fix the Interaction Before Replacing the Board

A user says “get ready for bed” to a wall panel. It replies “done.” The living-room light may still be on, the wrong bedroom may have been selected.

Read article
Generated edge computing cabinet scene, not a measurement of a specific device
Nov 03, 2026

Can an 8 GB Edge Device Run a 2 GB Model? Budget Memory at Peak Concurrency

Eight gigabytes of RAM minus a 2 GB model file is not 6 GB of usable inference memory. Calculate KV cache, then test the longest request and peak concurrency.

Read article
Generated edge-board development scene, not the target RK3588 device or a measured inference result
Oct 30, 2026

Deploying RKLLM on RK3588: Pin Versions, Convert the Model, and Validate On-Device Inference

Copying Hugging Face weights onto an RK3588 board does not make the model run on its NPU. Rockchip's RKLLM path has two distinct sides.

Read article
Generated edge LLM testing scene, not a measurement of any device
Oct 26, 2026

How to Benchmark an Edge LLM: TTFT, TPOT, Memory, Thermals, and Power

An edge LLM benchmark needs separate TTFT, TPOT, memory, thermal, and whole-system power results under a fixed model and workload.

Read article
Generated edge-computer selection scene, not a performance test of a specific board
Oct 23, 2026

How to Select Edge Hardware for LLM Inference: Memory, Bandwidth, Accelerators, and Power

A supplier's “8 GB RAM, 6 TOPS NPU” line does not establish that a field device can answer questions about a long service manual offline.

Read article
Gateway, embedded board and phone on a realistic workbench illustrating edge runtime targets, not benchmark evidence
Oct 14, 2026

Choosing an Edge LLM Runtime: Start with Devices and Model Artifacts

Compare llama.cpp, RKLLM, ExecuTorch, and MLC LLM by target device, model artifact, acceleration backend, and release responsibility—not an unverified speed ranking.

Read article
Maintenance technician reviewing equipment manuals in an illustrative workshop scene; not a field test
Oct 10, 2026

Offline RAG for Equipment Manuals: Versioned Evidence Before Answers

A technician asks how to reset an E42 alarm. A local model produces a convincing procedure, but cannot identify the machine variant, manual edition, or page it used.

Read article
When an RK3588 Edge AI Box Fits Industrial Vision—and When It Does Not
Sep 05, 2026

When an RK3588 Edge AI Box Fits Industrial Vision—and When It Does Not

A 6-TOPS RK3588 does not automatically deliver a production vision system. Learn how to qualify camera, RKNN, latency, thermal, recovery, and rollback boundaries.

Read article
How to Choose a Local AI Model for Enterprise Deployment
Aug 24, 2026

How to Choose a Local AI Model for Enterprise Deployment

The most expensive mistake in local AI selection is not choosing the second-best model. It is downloading a popular model before defining where data may go.

Read article
FunASR for AI Voice Projects: Offline, Edge, or Cloud ASR?
Aug 16, 2026

FunASR for AI Voice Projects: Offline, Edge, or Cloud ASR?

FunASR belongs on the shortlist when audio must remain in a factory, clinic, meeting room, or private network; transcription must continue during an Internet outage.

Read article
n8n AI Workflow Automation for Business Systems
Aug 13, 2026

n8n AI Workflow Automation for Business Systems

n8n is most useful when it turns hand-offs scattered across webhooks, CRM, email, forms, tickets, and internal APIs into a visible process that can be replayed and.

Read article
YOLO for Vision Inspection: From Acceptance Criteria to Edge Deployment
Aug 11, 2026

YOLO for Vision Inspection: From Acceptance Criteria to Edge Deployment

YOLO is a strong fit for a specific class of vision problem: determine whether a visible object is present, identify its class.

Read article
Technical evaluation

Evaluating a AI and Machine Learning project?

Share the device, data flow, network condition, target users, and business system boundaries. We can help you decide what to build first.