Prompting vs RAG vs fine-tuning
Prompting vs RAG vs Fine-Tuning: Diagnose the Failure First A wrong answer is an observation, not a root cause. Inspect the input, source evidence,…
Open Source
⚑ Сообщить о проблемеПоследние новости Open Source от Tech News
Все темы
AI
agents
ai
api
architecture
automation
backend
beginners
career
database
devchallenge
devops
discuss
javascript
linux
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Which prompt made that decision?
TL;DR: prompt in the repo, model pinned to an exact version (never an alias), retrieval index versioned, every change through the eval set, and the…
You probably don't need fine-tuning
TL;DR: most underperforming LLM features lack context, not capability. No eval set, no fine-tuning. Prompt, retrieval, evals, then maybe the weights…
Who holds the key?
TL;DR: split hot and admin keys, put the admin role behind a multisig or KMS, write the rotation procedure, plan for people leaving. An audited smar…
Why 95% of Enterprise AI Agents Never Reach Production (And the 3 Orchestration Boundaries That Kill Them)
Why 95% of Enterprise AI Agents Never Reach Production (And the 3 Orchestration Boundaries That Kill Them) Enterprise AI agents promise transformati…
Why 95% of Enterprise AI Agents Never Reach Production
Why 95% of Enterprise AI Agents Never Reach Production 95% of enterprise AI agents die before prod. Not because the models are bad. Because orchestr…
The Expression Engine Is Small. That Is Exactly the Problem.
In June, a distributor customer of ours called about a quote that should never have existed. Their quoting app has a validation rule: the discount f…
Stage 4 of enterprise AI adoption: write and send behind approval
This is part 4 of a series that started with the full reference diagram in part 0 , covered identity and the gateway in part 1 , data and retrieval…
Anthropic, OpenAI Agents Caught Creating Fake Identities During Security Tests
The Report That Should Keep You Up at Night The UK's AI Security Institute (AISI) ran a cybersecurity evaluation with agents powered by Anthropic's…
A token is a claim, not the asset
Tokenizing an asset is the easy part. The token is a claim, and a claim is only worth the obligation behind it. Here is the checklist I actually car…
Open source в Enterprise: как понять, готово ли решение к внедрению
«Open source» давно перестало быть просто техническим фактом и превратилось в маркетинговый ярлык: открытый код в представлении многих автоматически…
Stage 1 of enterprise AI adoption: identity and the AI gateway
This is part 1 of a series that started with the full reference diagram in part 0 . Stage 1 covers the two columns marked 1 on that diagram. The fir…
One diagram for enterprise AI adoption: five stages from identity to governance
This is a reference architecture for bringing AI into a company. It has five layers: users and apps, identity and access, an AI gateway, models with…
Enterprise AI vs Traditional Software: Key Differences
If you've spent any time in a planning meeting over the last two years, you've probably heard someone ask "why can't we just add AI to this?" It's a…
Любишь, чтобы сервер работал, — люби и BMC: кто и как решает проблемы на стыке железа и прошивки
Стабильность современного сервера зависит от BMC (Baseboard Management Controller): он управляет аппаратной платформой, следит за ее состоянием и ре…
Enterprise AI's real risk isn't autonomous agents. It's the complexity between them
Enterprise AI's real risk isn't autonomous agents. It's the complexity between them. Executive Briefing — September 2026 When enterprises deploy fle…
The Tool You're Allowed to Use
Everything I've written about working with agents — the map , where to start , what engineers get wrong — quietly assumes something that isn't true…
Auto-Seed Admin Controls: Building Governance for an AI Training Pipeline
The enterprise workflow platform's auto-seed pipeline generates AI training data through a multi-gate review flow: content creation, quality checks,…
Enterprise vibe coding: the governance framework for shipping AI-generated apps to production
Enterprise vibe coding: the governance framework for shipping AI-generated apps to production Published: August 22, 2026 Category: Enterprise · AI D…
Формула «идеального enterprise» для open-source
Как отделить платные enterprise-функции от open-source кода так, чтобы их нельзя было взломать с помощью ИИ — показываю на примерах Dokploy и Pangol…
André Dias Moreira Prol: Securely Connecting AI to Internal Docs With RAG
Every company sits on a mountain of internal knowledge — contracts, technical manuals, compliance policies — that traditional AI models simply canno…
We fixed a hidden bug in a system processing 10M+ messages a day.
9 min read · warehouse execution system, global retail & manufacturing A few years ago I worked on a warehouse execution system (WES) — the soft…
WSO2 ประกาศเดินหน้า Go แทน Java — วาง roadmap 10-20 ปี
WSO2 ประกาศเดินหน้า Go แทน Java WSO2 — บริษัท enterprise middleware อายุ 20 ปีจากศรีลังกา — ประกาศทิศทางใหม่ ผู้บริหาร Sameera Jayasoma (VP) และ San…
Десять типовых ошибок при внедрении управления корпоративной архитектурой (Enterprise Architecture) и как их исправить
Enterprise Architecture помогает связывать бизнес‑цели, технологии и изменения в компании. Но без правильного подхода она легко превр…
AI Agent Development for UAE Enterprises
AI agents go beyond chatbots: they use a language model to plan, call tools, and complete multi-step tasks without a human directing every action. H…
Building Autonomous AI Agents in the Enterprise
Autonomous AI agents are transitioning from experimental developer playgrounds into the core of enterprise application architecture. For organizatio…
94% of enterprises still can't make AI work at scale. Scale's new report explains why.
Only 6% of companies have made enterprise AI genuinely work at scale. That's the headline from The Six Percent Report , a new study from Scale AI in…
Alibaba's 'Correct but Empty' Response to a 75,000-Word Employee Letter
The Event On June 4, 2026, a former DingTalk product manager named Teng Yaxin published a 75,000-character letter on Alibaba's internal forum titled…
The Agent Revolution Is Here and It's Messy
The Agent Revolution Is Here and It's Messy So here's what I'm seeing across the AI landscape right now: agents have stopped being this theoretical…
Why I Built Bamise Instead of Using Laravel
Laravel is one of the best things that ever happened to PHP. It transformed modern PHP development, introduced elegant developer experience patterns…