Skip to main content
Selection All articles Must reads only
Topic: AI tooling
3D assets 1 Agent security 5 Agent traffic 1 Agentic Commerce 2 Agentic development 1 Agentic coding 1 Agentic shopping 1 API economy 1 Architecture 4 Image generation 1 Bot detection 1 CI/CD 1 Cloud budgets 1 Cloud Native 1 Code governance 1 Code security 1 Code quality 2 Container security 1 Content quality 3 Content protection 1 Content structure 1 Databases 1 Design workflows 1 Digital sovereignty 1 Documentation 1 E-Commerce 1 Developer tooling 1 Development platforms 1 Development process 1 Frontend 1 Frontend AI 1 Frontend tooling 1 Generative Interfaces 1 IT security 1 AI & Architecture 2 AI & Teams 1 AI agents 28 AI architecture 6 AI assets 1 AI assistants 1 AI selection 1 AI automation 3 AI benchmark 1 AI operations 2 AI images 1 AI image generation 1 AI image models 3 AI coding 2 AI Commerce 1 AI compliance 1 AI adoption 1 AI development 18 AI governance 14 AI infrastructure 5 AI content 1 AI interfaces 2 AI costs 5 AI market 2 AI models 36 AI modernisation 1 AI platforms 3 AI in practice 10 AI projects 1 AI prototyping 1 AI processes 1 AI quality assurance 1 AI editing 1 AI safety 20 AI visibility 3 AI sovereignty 1 AI strategy 2 AI search 1 AI tooling 71 AI Visuals 1 AI knowledge management 1 AI workflows 3 AI collaboration 1 AI in operations 1 AI in e-commerce 1 AI in everyday development 1 AI in software design 1 AI in development 1 AI and SMEs 1 Classification 1 Legacy migration 1 Legacy modernisation 2 Local AI 1 Brand management 1 Model access 1 Observability 2 Open models 2 Open-weight AI 1 Open-weight models 2 Open Source 4 Project costs 1 Project organisation 1 Process 1 Quality assurance 4 Release processes 1 Reverse engineering 1 Security 4 Visibility 1 Software supply chain 1 Software security 1 Software architecture 1 Software development 1 Software quality 1 Search and content 1 Search visibility 1 Search strategy 1 Supply chain security 3 Team building 1 Vibe Coding 3 Voice interfaces 1 Voice AI 1 Web security 1 Web standards 1 Web strategy 1 Web security 1 Web standards 2
✕ Topic
71 articles
AI tooling AI
19.11.2026 · 5 min · AI

Coding agents at OpenAI: high usage, clear limits

OpenAI cites figures for the internal use of coding agents for the first time: high token consumption per researcher, large subjective benefit – and clear weaknesses in complex infrastructure and genuinely new ideas.

1 Source linked → Read more
AI tooling AI
18.11.2026 · 5 min · AI

AutoCraft: When AI agents take over the GitHub backlog

The open-source tool AutoCraft is intended to process issues and pull requests in GitHub repositories using AI. What this means in practice for development teams – and where the limits lie.

1 Source linked → Read more
AI tooling AI
17.11.2026 · 5 min · AI

Gemini Notebooks: From notes to interactive web pages

Google is expanding its research tool Gemini Notebook with a feature that turns project content into a web page. What this means for prototypes - and where professional CMSs remain indispensable.

1 Source linked → Read more
AI tooling AI
17.11.2026 · 4 min · AI

Claude Artifacts: AI interfaces with a design standard

Claude can now embellish texts, buttons and other website components with elaborate graphics and 3D effects. This shifts expectations for AI-generated prototypes – and at the same time shows where human work remains.

1 Source linked → Read more
AI tooling AI
16.11.2026 · 4 min · AI

AI agents are moving into IDEs and frameworks

A roundup from the developer scene shows the trend: from AWS Kiro to Spring AI, agentic functions are moving directly into development environments and frameworks. What this means for teams and project plans.

1 Source linked → Read more
AI tooling AI
16.11.2026 · 4 min · AI

Claude Opus 5.5: Why Think hard should disappear from prompts

Anthropic makes Claude Opus 5.5 the default model on all paid plans and recommends dropping practised prompt formulas: drop "Think hard", start at medium effort.

1 Source linked → Read more
AI tooling AI
12.11.2026 · 5 min · AI

Gemini Decisions: When AI decides instead of formulates

Google Deepmind is introducing the Gemini Decisions API, an interface that makes up to 1,000 closed decisions per run – in 150 to 250 milliseconds. This is relevant for classification and moderation in web and CMS projects.

1 Source linked → Read more
AI tooling AI
11.11.2026 · 5 min · AI

Agent swarms in practice: Gemini 4 Carbon and development teams

Google makes Gemini 4 Carbon generally available and demonstrates "/swarm" coordinated agent teams. What is already viable for web and TYPO3 projects today – and where human control remains necessary.

1 Source linked → Read more
AI tooling Must read AI
05.11.2026 · 5 min · AI

Artcraft: AI image editing as an alternative to Photoshop

A developer is working with Artcraft on an AI-powered alternative to Adobe Photoshop. The project is still in development – a good opportunity to check your own image production for dependencies.

1 Source linked → Read more
AI tooling AI
05.11.2026 · 4 min · AI

OpenAI acquires Pierre: toolchain around Codex grows

OpenAI buys the developer tool company Pierre, whose libraries Trees and Diffs are already part of the coding agent Codex. Together with the Git backend Pando, a dedicated infrastructure is being created for humans and AI agents working on code.

1 Source linked → Read more
AI tooling AI
04.11.2026 · 5 min · AI

AI skills in ChatGPT and Claude: making routines reproducible

Skills are intended to simplify recurring tasks in ChatGPT and Claude. When the setup effort pays off and what companies should look out for when getting started.

1 Source linked → Read more
AI tooling Must read AI
04.11.2026 · 5 min · AI

Vibe Coding: From requirements profile to a working prototype

Prompt-driven development shortens the path from idea to clickable prototype. Tool selection, precise requirements and a robust review of what the AI outputs remain decisive.

1 Source linked → Read more
AI tooling AI
03.11.2026 · 5 min · AI

Message Threads: Anthropic accelerates long-running AI agents

Anthropic introduces Message Threads for the Messages API: agents now send only new messages instead of the complete history. For very large requests, the time to first token drops by around 35 per cent.

1 Source linked → Read more
AI tooling AI
03.11.2026 · 4 min · AI

When the system prompt blocks: Claude also rejects legitimate projects

Anthropic has adjusted Claude's system prompt to prevent the recreation of existing games. According to reports, the rule also affects unsuspicious development projects – with consequences for ongoing workflows.

1 Source linked → Read more
AI tooling AI
02.11.2026 · 5 min · AI

Herdr: Desktop app as a control centre for AI coding agents

Herdr has released a desktop application that serves as a central control hub for AI coding agents and runs on Linux, macOS and Windows. For development teams, this brings the question of orchestration to the fore.

1 Source linked → Read more
AI tooling AI
02.11.2026 · 5 min · AI

Shared token budget for ChatGPT and Codex from December

OpenAI merges the Chat and Work modes. From December, Plus, Pro and Business plans will access a shared token-based allowance for ChatGPT and Codex. For development teams, this shifts cost planning.

1 Source linked → Read more
AI tooling AI
30.10.2026 · 5 min · AI

Android Studio Rabbit 2 opens up to third-party AI models

Google is allowing the use of AI models from other providers in Android Studio Rabbit 2 for the first time and expanding the agentic functions. For development teams, freedom of choice when it comes to the model is therefore moving to the forefront.

1 Source linked → Read more
AI tooling AI
30.10.2026 · 4 min · AI

OpenAI doubles Codex and Work limits for paid plans

OpenAI is raising the usage limits for Work and Codex features across several paid plans. For development teams, this shifts the calculation of how much AI support can realistically be planned per project.

1 Source linked → Read more
AI tooling AI
29.10.2026 · 5 min · AI

PipesHub 1.0: Open up company knowledge in a controlled way for AI agents

PipesHub brings together content from Slack, Jira and GitHub for internal search and AI agents. Version 1.0.0 adds code graphs and stricter permissions – precisely the two points on which assistance systems fail or succeed in practice.

1 Source linked → Read more
AI tooling AI
29.10.2026 · 4 min · AI

Coding agents move into the IDE: Android Studio opens up to third-party agents

Android Studio now supports over 40 external coding agents, and at Berlin DevDay OpenAI positioned itself as a platform for developer products. What agent-centric workflows change for speed, token costs and tool choice.

2 Sources linked → Read more
AI tooling AI
29.10.2026 · 5 min · AI

Copilot Access, model routing and 3.5 million merges per day

GitHub simplifies Copilot access for enterprise customers and aims to save tokens through model routing. In parallel, the activity report shows how strongly AI agents are shaping everyday development.

2 Sources linked → Read more
AI tooling AI
28.10.2026 · 5 min · AI

Local AI at home: Anything LLM as an alternative to the cloud

Anything LLM bundles agentic functions, web search and a knowledge store in a locally operable interface. Two current practical reports show what the tool can do and what hardware local models require.

2 Sources linked → Read more
AI tooling AI
27.10.2026 · 4 min · AI

Claude Motion: AI-generated animations in everyday web project work

Anthropic has added a simple animation tool to its AI assistant Claude. For web teams, the effect itself is less interesting than the question of where prompt-based motion design can sensibly fit into the process.

1 Source linked → Read more
AI tooling Must read AI
22.10.2026 · 4 min · AI

OpenCode 2.1: a coding agent for many models

Version 2.1 of the open-source coding agent OpenCode brings new data fields for plug-ins and clients as well as persistent terminals on Windows. For teams, the model independence is particularly interesting.

1 Source linked → Read more
AI tooling AI
20.10.2026 · 5 min · AI

A programming language against AI – and what teams can learn from it

A developer has designed a language that AI models find as difficult as possible to understand. The experiment is more than just a gimmick: it shows what AI-assisted development actually depends on.

1 Source linked → Read more
AI tooling Must read AI
19.10.2026 · 5 min · AI

Deepseek V4.1-Flash: open model as a low-cost option in coding tools

Deepseek has released an open-weight model with V4.1-Flash that responds faster, delivers shorter outputs and brings new search and fetch APIs. For development teams, this shifts the cost calculation of AI-powered workflows.

1 Source linked → Read more
AI tooling AI
15.10.2026 · 4 min · AI

Scion: Anthropic introduces server-based Git alternative for AI agents

Anthropic has introduced Scion, a server-based alternative to Git. The reason: permanently active AI agents generate a load that pushes classic version control to its limits.

1 Source linked → Read more
AI tooling AI
15.10.2026 · 4 min · AI

Three.js in the agent hype: When AI shapes technology selection

Three.js is suddenly recording weekly download figures in the tens of millions. One driver is likely to be AI agents that generate web interfaces – with consequences for architecture, performance and maintenance.

1 Source linked → Read more
AI tooling AI
12.10.2026 · 5 min · AI

Google's MCP Toolbox: Interacting with databases using Java and AI

Google's MCP Toolbox lets you connect databases to AI assistants via the Model Context Protocol – including from Java. For now, however, with limitations.

2 Sources linked → Read more
AI tooling AI
09.10.2026 · 5 min · AI

Claude generates live dashboards and explainer videos via prompt

Anthropic extends Claude with two beta features: dashboards on data sources such as BigQuery or Snowflake, as well as animated explainer videos from text and images. For companies, the question arises as to the boundary between prototype and production system.

1 Source linked → Read more
AI tooling AI
08.10.2026 · 5 min · AI

Google Playground: Create games in the browser using just a prompt

Google is launching Playground, a browser-based platform where games are created via text input – without any programming knowledge. At the same time, Google is announcing Unity Spark, a tool developed with Unity. What this means for prototyping in projects.

1 Source linked → Read more
AI tooling AI
08.10.2026 · 4 min · AI

ReviewBench: GitHub sets a benchmark for AI code reviews

GitHub has introduced ReviewBench, a benchmark designed to make AI-assisted code reviews comparable. GitHub's own product Copilot takes first place — an independent test reaches a different conclusion.

1 Source linked → Read more
AI tooling AI
07.10.2026 · 5 min · AI

When corporations scale back AI coding tools: lessons for practice

Microsoft and Meta want to reduce the use of Claude Code among their developers. The move is less a verdict on a product than an indication of open questions about costs, tool strategy and dependencies.

1 Source linked → Read more
AI tooling AI
06.10.2026 · 5 min · AI

Meta and Microsoft throttle Claude: Consequences for AI coding stacks

Microsoft is drastically cutting the per-capita budget for Claude in its cloud division, Meta is halving the number of Claude Code users. For development teams, this is a reason to make their toolchains more independent.

1 Source linked → Read more
AI tooling AI
05.10.2026 · 5 min · AI

Pi 1.0.0: Coding agent in the terminal with a leaner code mode

With version 1.0.0 of the extensible AI coding agent Pi, an approach that works without an IDE is coming into focus: the agent works directly in the terminal, streamlines code mode and adds image generation.

1 Source linked → Read more
AI tooling AI
05.10.2026 · 4 min · AI

AI coding assistants in your own data centre: Bob and Hermes

IBM now also offers its modernisation assistant Bob as a self-hosted option, and a field report tests the open-source agent Hermes locally. Two signals that AI-assisted development does not necessarily have to take place in the cloud.

2 Sources linked → Read more
AI tooling AI
05.10.2026 · 5 min · AI

Google limits free Gemini access to Flash-Lite

From October 2026, without a subscription, only the smallest Gemini model will remain available free of charge. Anyone running AI functions in websites, CMS or prototypes should review their model choice, budget and architecture now.

1 Source linked → Read more
AI tooling AI
02.10.2026 · 4 min · AI

Local AI models: when processing stays in-house

Language and image models are increasingly running on local hardware instead of in the cloud. Apple ships a local model with Macs using its own chip, and alongside this there is a growing tool landscape for operation in the workplace.

2 Sources linked → Read more
AI tooling AI
01.10.2026 · 5 min · AI

AMD Ross: AI agents take over development workflows

AMD Ross introduces an agentic assistant that accesses tools, documentation and stored engineering workflows. This shifts the role of AI in development — and turns your own documentation into a production factor.

1 Source linked → Read more
AI tooling AI
01.10.2026 · 4 min · AI

From Gems to Skills: Google bets on an open prompt format

Google replaces the Gems in Gemini chat with Skills — reusable prompts that are invoked with a slash. The underlying format comes from an open standard by Anthropic and is becoming established across providers.

1 Source linked → Read more
AI tooling AI
30.09.2026 · 5 min · AI

OpenAI DevDay 2026: Codex becomes a platform for AI development

Reusable cloud environments, security scans for GitHub repos and a dedicated code review view: OpenAI is expanding Codex for DevDay 2026. New APIs are also being added, along with GPT-6.1 Sol, a significantly cheaper model.

3 Sources linked → Read more
AI tooling AI
30.09.2026 · 5 min · AI

AI agents in code review: 24 Android vulnerabilities and new guardrails

An open-source agent from the GitHub Security Lab has discovered 24 vulnerabilities in Android. In parallel, OpenChamber 2.0.4 introduces an enterprise mode that lets teams control model providers and extensions.

2 Sources linked → Read more
AI tooling
30.09.2026 · 5 min · AI

Vibe coding in the product team: from prototype to robust decision

Prompt-driven prototypes styled like your own application can be tested before development time is committed. How product teams use them to validate decisions instead of building features on spec.

1 Source linked → Read more
AI tooling AI
28.09.2026 · 5 min · AI

Docker Cloud Sandboxes: Coding agents leave the laptop

Docker is offering cloud sandboxes for coding agents, meaning longer tasks move from the local machine to an isolated environment. In parallel, VS Code is expanding its agent functions. What this means for project teams.

2 Sources linked → Read more
AI tooling AI
25.09.2026 · 5 min · AI

Meta Horizon Create: games and apps via prompt on your smartphone

With Horizon Create and Horizon Studio, Meta wants to bring AI-prompt-based game creation to the masses — on smartphones and in the browser. What this principle means for professional development projects.

2 Sources linked → Read more
AI tooling AI
25.09.2026 · 5 min · AI

Browser extensions via prompt: vibe coding reaches Safari

On macOS, iOS and iPadOS 27, Safari extensions can be created using an AI prompt. This significantly lowers the barrier for small tools – and shifts the real work towards quality, maintenance and security.

1 Source linked → Read more
AI tooling AI
25.09.2026 · 5 min · AI

Gemini 4 draws closer: what this means for AI-assisted coding

Google DeepMind is already testing the next Gemini generation internally in the Antigravity coding tool. Instead of AGI debates, the focus is on reliable agents – with consequences for teams that have firmly scheduled AI assistants.

1 Source linked → Read more
AI tooling AI
24.09.2026 · 4 min · AI

Strands Harness from AWS: open-source runtime for custom AI agents

AWS has introduced Strands Harness, an open-source runtime environment for self-built AI agents. It is designed to take care of context management, save tokens and run locally – three points that have an immediate impact on operating costs and data protection.

1 Source linked → Read more
AI tooling AI
21.09.2026 · 5 min · AI

Unity provides official plugins for Claude Code and Codex

Unity provides official plugins for Claude Code and OpenAI's Codex. The move shows where AI agents are heading: away from generic code snippets and towards work within the specific project context.

1 Source linked → Read more
AI tooling AI
18.09.2026 · 5 min · AI

Android Bench 2.0: What Google's new benchmark reveals about AI coding

Google's new benchmark measures AI models against realistic Android development tasks. The company's own Gemini, of all things, lags behind Claude and GPT — an indication of how much the choice of model matters in a project.

1 Source linked → Read more
AI tooling AI
18.09.2026 · 4 min · AI

Claude Code distributes tasks itself across parallel threads

Anthropic is turning Projects in Claude Code into a job distributor: a project breaks down tasks and sends them into parallel threads. The beta starts initially for Pro and Max subscriptions.

1 Source linked → Read more
AI tooling AI
18.09.2026 · 4 min · AI

Claude Code distributes tasks to parallel cloud agents

Anthropic has restructured the projects feature in Claude Code: a coordinator distributes tasks across parallel cloud threads that themselves open pull requests and run tests. This shortens implementation cycles and shifts effort into review.

1 Source linked → Read more
AI tooling AI
17.09.2026 · 5 min · AI

When the context is full: Why AI assistants deteriorate over the course of a session

Long chats with coding assistants often end in errors, repetitions and forgotten requirements. The cause is usually a full context window. Anyone who knows the symptoms works much more reliably.

1 Source linked → Read more
AI tooling AI
17.09.2026 · 5 min · AI

Who chooses the model? The provider question in AI coding tools

Providers such as Anthropic and OpenAI face the decision of whether their development tools may also work with third-party models. For project managers, this is not a detail question but a question of cost, data protection and predictability.

1 Source linked → Read more
AI tooling Must read AI
16.09.2026 · 5 min · AI

Agentic development: When AI takes over entire tasks

AI coding moves beyond autocomplete: agentic workflows handle entire tasks within the project. This shortens development cycles – and shifts the effort into review, testing and quality assurance.

1 Source linked → Read more
AI tooling AI
14.09.2026 · 5 min · AI

Herdr: When fleets of coding agents need to be coordinated

Running multiple AI coding agents in parallel is easy. Keeping track of which one is currently waiting for a response is the real work. The open-source project Herdr addresses exactly this.

1 Source linked → Read more
AI tooling AI
14.09.2026 · 5 min · AI

Less is more: when old prompts hold back modern coding agents

OpenAI warns: Bloated skill descriptions and rigid rule sets hold back high-performing models in Codex. For development teams, this means decluttering grown prompt libraries.

1 Source linked → Read more
AI tooling AI
11.09.2026 · 5 min · AI

Choosing an AI model: criteria instead of gut feeling

Even individual providers maintain entire model families. Anyone selecting for a project therefore needs a traceable procedure based on task definition, cost framework and measurable quality.

1 Source linked → Read more
AI tooling AI
09.09.2026 · 5 min · AI

ML Intern: Hugging Face's agent builds ML pipelines for under 50 cents

Hugging Face has introduced ML Intern, an assistant for its chatbot that is designed to let users run through machine-learning experiments without expert knowledge. What this means for companies without their own data-science team.

1 Source linked → Read more
AI tooling AI
31.08.2026 · 6 min · AI

Copilot Business and Enterprise: new sign-ups from 1 September

Since 22 April, new sign-ups for GitHub Copilot Business and Enterprise have been blocked; from 1 September they are possible again. For teams, this is the occasion to approach the introduction of AI coding assistance in a structured way.

2 Sources linked → Read more
AI tooling AI
31.08.2026 · 5 min · AI

If model access is lost: dependencies in the AI toolchain

OpenAI cancels the coding tool Cursor's model access, Anthropic readjusts Claude Code's weekly limits. Two reports, one lesson: anyone developing with AI support needs a plan B for models, limits and costs.

2 Sources linked → Read more
AI tooling AI
31.08.2026 · 5 min · AI

AI coding agents misjudge their abilities – and don't realise it

A study shows: Claude Code and Codex have no sense of time and rate their own work around 20 percentage points too highly. For autonomous agents in customer projects, this means: clear review processes and experienced teams remain essential.

2 Sources linked → Read more
AI tooling AI
28.08.2026 · 4 min · AI

Agents.md under scrutiny: study questions the benefits of context files

Context files such as Agents.md are considered standard practice for AI coding assistants. A study by ETH Zurich reaches a sobering conclusion: higher token costs, no discernible quality gain.

1 Source linked → Read more
AI tooling AI
28.08.2026 · 5 min · AI

Agentic coding tools in everyday team life: what really changes

AI-assisted code generation is changing the way development teams work. The benefit does not come from the tool alone, but from clear rules for review, quality and responsibility.

1 Source linked → Read more
AI tooling AI
21.08.2026 · 5 min · AI

Nvidia acquires Poolsides Model Factory: What this means for your choice of tools

Nvidia pays six billion dollars for Poolside's model development software and takes on 109 employees. The deal shows how quickly the market for AI coding tools is being reshuffled – and why teams should check dependencies.

1 Source linked → Read more
AI tooling AI
19.08.2026 · 5 min · AI

Coding agents in everyday use: Claude Code and Copilot in the lead

According to a JetBrains survey, nine out of ten developers regularly use a coding agent. The actual work is thus shifting into the structure of the repositories.

2 Sources linked → Read more
AI tooling AI
19.08.2026 · 4 min · AI

Claude Code /design: UI drafts directly from the terminal

Anthropic brings a visual design workflow to Claude Code. The new /design command generates drafts as artboards and draws on the UI style of the existing codebase.

1 Source linked → Read more
AI tooling Must read AI
16.08.2026 · 5 min · AI

Vibe Coding with Claude Code: Team tools without programming knowledge

Specialist departments are building their own dashboards and small helper tools with prompt-driven development—in hours instead of weeks. Where this brings real relief and where maintainability, data protection and integration need professional support.

1 Source linked → Read more
AI tooling AI
13.08.2026 · 5 min · AI

Coding agents work independently in the IDE and browser

Claude Code will run in Auto Mode by default going forward, WebStorm agents access Chrome directly for debugging. This speeds up troubleshooting in web projects – and shifts the question from ability to permissions.

3 Sources linked → Read more
AI tooling Must read AI
09.08.2026 · 5 min · AI

Vibe Coding: When the business department builds its own tool

With Claude Code, dashboards and small team tools can be designed, extended and shared via prompt – without any programming knowledge. For companies, this is a quick way to test, but not a substitute for clean architecture.

1 Source linked → Read more
AI tooling AI
08.08.2026 · 5 min · AI

Adobe plugin for ChatGPT: 70 creative tools in the chat window

Adobe is bringing over 70 features from Photoshop, Illustrator, InDesign, Acrobat and Firefly to ChatGPT as a plugin. For web and content teams, this shifts the question from tool selection to quality assurance.

1 Source linked → Read more

Barrierefreiheit

Passen Sie die Darstellung an Ihre Bedürfnisse an. Ihre Auswahl bleibt auf diesem Gerät gespeichert.

Schrift und Text

100 %

Schriftgröße der Seite

Farben und Kontrast

Lesen und Bedienen