本地 AI,白紙黑字。

業務效益 2026-08-04 · 5 分鐘閱讀

EU AI Act 高風險期限押後至 2027 年 12 月 — 對採購方有何影響

AI Omnibus 於 2026 年 7 月 27 日生效,將高風險義務押後至 2027 年 12 月 2 日。義務沒有改變,改變的只是日期 — 而 16 個月夠做一次架構變更,並非兩次。

產品 2026-07-22 · 3 min read

Sticky caller affinity: each user keeps their own warm worker

The sticky routing strategy maps each caller to a preferred worker by an identity hash, so multi-turn chats keep landing on the box where the model is loaded and the prompt cache is hot — a deterministic mapping with no session table to replicate.

產品 2026-07-22 · 4 min read

Canary rollouts: trial a new model on a slice of real traffic

Mark a worker canary and give the pool a percentage: that share of callers, assigned consistently by identity hash rather than per-request coin flips, prefer the canary while everyone else stays on stable — and the two groups remain each other's failover.

產品 2026-07-22 · 4 min read

Capacity caps and honest backpressure: protecting small GPU boxes

Per-worker concurrency limits keep each GPU box in its sweet spot. A saturated worker is skipped; a fully saturated pool returns 503 with Retry-After immediately — honest backpressure instead of a silently growing queue that ends in a thrash or an OOM.

產品 2026-07-22 · 5 min read

The AI Server security model: what fails closed and where each key lives

A served AI Server deployment's security posture in plain statements: fail-closed serving, keys hashed at rest, two credential tiers in a farm, forwarded pseudonymous identity, fingerprint pinning, and private TLS to workers — the default behavior a security review reads.

產品 2026-07-22 · 4 min read

Watching a private AI fleet: dashboards, Prometheus, and per-app chargeback

Every AI Server hosts a live dashboard and native Prometheus metrics, and its content-free audit attributes each request to app, install, and serving worker — so per-team, per-app chargeback is native data, no metering sidecar required.

產品 2026-07-22 · 3 min read

Branch-office AI: workers that join the farm by being switched on

A gateway that discovers its workers over mDNS on the local network, so scaling a small site is plugging in a prepared box — it advertises itself, the gateway probes it, and within a health-check cycle it is serving. Static core and dynamic discovery compose.

產品 2026-07-22 · 4 min read

Legacy coexistence: old and new AI clients on one box during migration

Serve both generations at once during a migration: modern OpenAI-compatible clients on the governed primary port, and pre-v2 clients on a scoped compatibility listener that carries a compiled sunset date — no flag-day, no broken scripts.

產品 2026-07-22 · 5 min read

Regulated enterprise AI: region policy, mandatory moderation, and signed audit

The compliance-hardened deployment: region-aware governance that fails closed where content scanning is mandated, on-device moderation, per-key quotas and budgets, and a content-free, signed audit an external auditor can verify offline, independently.

產品 2026-07-22 · 4 min read

Zero-downtime upgrades: patching a private AI endpoint without a maintenance window

Upgrade workers and the gateway while traffic keeps flowing. A draining /readyz probe, a configurable drain hold, and gateway failover cover the requests racing the drain — no maintenance window.

產品 2026-07-22 · 4 min read

One office, one AI box: serving every workstation from a shared server

Run one AI Server on the office GPU box and serve every workstation on the LAN over an API-key-authenticated endpoint. The model loads once, the data never leaves the building, and there are no per-token bills.

產品 2026-07-22 · 4 min read

Self-hosting AI in your own VPC: one container, env-configured, probe-ready

Run AI Server as one container on a cloud VM or any Docker host: configured entirely by environment variables, with /livez and /readyz probes and JSON logs so orchestrators manage it correctly. The image is the artifact; the volume is the state.

產品 2026-07-22 · 3 min read

The zero-exposure default: one local AI server for everything on your machine

Every AI Suite app creates one loopback AI Server on your machine. It binds 127.0.0.1 only, needs no keys or licence, and shares one model in memory across every app on the box — the zero-exposure default worth understanding before anything is networked.

產品 2026-07-22 · 4 min read

Model-aware routing: different models on different boxes, one catalog to callers

A farm whose workers carry different model sets. The gateway routes each request to a box that already has the model warm, and advertises the union of every worker's models as one catalog — so callers see one model list and placement is the gateway's problem.

產品 2026-07-22 · 5 min read

AI Gateway: one endpoint in front of a farm of private AI Servers

One URL and one key in front of a pool of worker AI Servers: health-checked load balancing, transparent failover, model-aware routing, and Kubernetes auto-discovery — with no vendor cloud in the request path.

產品 2026-07-22 · 4 min read

AI Server v2 is here: one shared, private AI runtime for your whole PC

A ground-up rebuild of the shared engine behind AI Suite: host, download and run the AI models every app uses — one download, one library, one set of keys, used everywhere. Free serves this machine; Pro serves your whole network with governance. Free on Windows from the Microsoft Store.

產品 2026-07-05 · 4 min read

AI Suite is here: every local AI app in one window

Every Software Tailor AI app — Chatbot, Translate, Rewrite, Notepad, PDF Reader, Image Generation and more — in one window, with the local AI engine built in. Each app keeps its own model and history; your work stays on your device, saved encrypted. Free on Windows from the Microsoft Store; one Pro subscription unlocks the whole suite.

產品 2026-07-03 · 5 min read

Local AI Chatbot v2 is here: the full private AI chat, on your own device

The full private AI chat for Windows: multi-session chats, folders, a prompt library, conversation branching, document chat and durable memory — all free on a local model that works offline, with encrypted on-device history. Pro adds tool use, Agent mode and larger or cloud models. Your existing chats and prompts upgrade in place. Free from the Microsoft Store.

產品 2026-07-03 · 4 min read

AI Image Generation is here: make pictures from words, privately on your own PC

Type a prompt and an original picture appears on your own PC — a built-in FLUX.2 [klein] model, negative prompts, seeds, batch generation and a private encrypted gallery. Free at 512×512; Pro unlocks larger sizes, custom steps and optional bring-your-own-key cloud. Free on Windows from the Microsoft Store.

產品 2026-07-02 · 4 min read

AI Image Tool v2 is here: understand and search your photos, privately on your device

A photo assistant that turns a folder of pictures into a searchable collection — AI captions, object detection, OCR, opt-in face grouping and semantic search, all on your device. Organise, annotate and remove backgrounds. Free on Windows from the Microsoft Store.

產品 2026-06-27 · 3 min read

Local AI Assistant v2 is here: a private AI chat that never leaves your machine

A ground-up rebuild: pick a model, type, and a local AI model streams the reply back on your own device — with an encrypted local history, find and search, and two simple context controls. Deliberately slim. Free on Windows from the Microsoft Store.

產品 2026-06-27 · 4 min read

AI Reasoning v2 is here: a private AI that thinks it through, on your device

A ground-up rebuild built for reasoning models that think step by step — maths, logic, code — with a collapsible Thinking panel showing the chain-of-thought and a larger reply budget so answers aren't cut off. Free DeepSeek R1 model. Free on Windows from the Microsoft Store.

產品 2026-06-24 · 3 min read

AI Voice Generation v2 is here: natural speech and your own cloned voice, on your device

Type any text and hear it spoken in a natural voice — and clone a voice of your own from a short clip — right on your device. Offline by default, encrypted at rest, with a seekable player and WAV/MP3 export. Free on Windows from the Microsoft Store.

產品 2026-06-23 · 4 min read

AI Notepad is here: a private, offline AI notepad that formats itself

A simple notepad that formats itself as you write — plain text to Word, automatically — with on-device AI writing help, ask-your-document Q&A with citations, ask-across-all-open-documents, annotations and a readable dark editor. Free on Windows from the Microsoft Store.

產品 2026-06-22 · 3 min read

AI Dictation v2 is here: turn speech into text privately, on your own device

Turn speech into text on your device — from your microphone, your computer's audio, or an audio file. Export subtitles, replay and re-transcribe recordings, keep an encrypted local history. Free on Windows from the Microsoft Store.

產品 2026-06-19 · 3 min read

AI Rewrite v2 is here: polish any text privately, on your own device

A ground-up rebuild: paste or import text, choose an action, tone and length, and a local AI model rewrites it on your device — with match-my-style, document import and an encrypted local history. Free on Windows from the Microsoft Store.

產品 2026-06-16 · 4 min read

AI PDF Reader v2 is here: ask any PDF, answered privately on your device

A ground-up, cross-platform rebuild: open a PDF and ask questions answered on-device, with clickable page-exact citations — in a full reader with annotations and bookmarks that travel in the file. Windows, macOS, Linux, plus a headless CLI/MCP server.

AI 趨勢 2026-07-22 · 7 分鐘閱讀

從雲端優先轉向資料駐留優先的企業 AI 採購

企業 AI 架構於 24 個月內已轉換預設。EU AI Act 部署者義務、NIST AI RMF 對關鍵基礎設施的方向,以及 a16z 的交易週期數據,全部指向同一方向:駐留優先是新的雲端優先。

公司 2026-07-15 · 4 分鐘閱讀

自 2007 年以來零項目失敗 —— 背後的工程紀律

Software Tailor 在 19 年間交付定制軟件,沒有任何項目失敗。四條工程紀律支撐着這份紀錄。創辦人親述背後的紀律。

AI 趨勢 2026-07-08 · 7 分鐘閱讀

OECD AI Policy Observatory:過去 12 個月有何變化

OECD AI Policy Observatory 追蹤逾 80 個司法管轄區的 AI 政策。2026 年 6 月的 AI Policy Toolkit、GPAI 與 OECD 的合併,以及 EU AI Act 綜合協議,是企業採購團隊應一併解讀的三個訊號。

產品 2026-07-01 · 5 分鐘閱讀

AI Admin Console:六項能力各自實際做甚麼

AI Admin Console 提供六項能力 —— 成員、授權、AI Server 註冊、政策、審計、按組織用量。每一項都對應採購與合規團隊於 EU AI Act 與 NIST AI RMF 部署者義務之下會提出的特定問題。

產品 2026-06-05 · 6 分鐘閱讀

不含內容的審計日誌:我們如何在不保留提示詞的情況下證明模型做了甚麼

AI Suite 的每一項管理動作都會落入一條 JSONL 審計列,包含時間戳、操作者及動作 —— 並且不含任何提示詞或回應內容。內容由部署者保存;我們則保留動作曾經發生的證明。

業務效益 2026-06-03 · 6 分鐘閱讀

為何本地 AI 部署於採購階段卡關(以及打破僵局的論述框架)

企業 AI 採購卡關的是部署者義務,而非技術本身。2026 年化解僵局的部署架構特性,以及為何「我們有 SOC 2」並非合規團隊現時所提問題的正確答案。

AI 趨勢 2026-06-15 · 7 分鐘閱讀

2026 年的 EU AI Act:本地部署改變了哪些合規面向

本法案的高風險部署者義務正於 2026 年逐步生效。本地部署並非規避法規 —— 但會改變哪些義務在實務上可達成,以及哪些是雲端 SaaS 根本無法滿足的。

公司 2026-06-15 · 5 分鐘閱讀

為何我們以可安裝二進制檔交付 AI,而非雲端 SaaS

本地推理、客戶掌控的審計,以及一套早已存在的採購流程。Software Tailor 的 AI 產品之所以是桌面安裝程式而非我們雲端中的一個租戶,有三個結構性原因。