Skip to main content
Selection All articles Must reads only
Topic: AI agents
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
28 articles
AI agents AI
19.11.2026 · 4 min · AI

Agents instead of interfaces: Microsoft realigns Azure and Copilot

At Ignite 2026, Microsoft is putting agents at the centre of Azure, while Salesforce functionality is simultaneously moving into Copilot. For their own systems, the question arises as to how they can become addressable for agents.

2 Sources linked → Read more
AI agents AI
09.11.2026 · 5 min · AI

AI agents: what token billing and tool hopping really cost

Gartner expects that token-based billing can exceed cost expectations for AI agents by more than 50 per cent. At the same time, a practical report shows why the first agent is often switched off again.

2 Sources linked → Read more
AI agents AI
07.11.2026 · 4 min · AI

Always-on agents: what Perplexity Teammates can do today

Perplexity launches Teammates, always-on AI agents for 200 dollars a month. In parallel, the GDPx benchmark shows that no model achieves more than a twelve percent success rate on simulated knowledge work.

2 Sources linked → Read more
AI agents AI
05.11.2026 · 4 min · AI

CloudOpsBench: Where AI agents reach their limits in cloud operations

A new open-source benchmark tests how reliably AI agents handle typical DevOps tasks. Even the strongest models solve around 60 per cent – a sober yardstick for automation plans.

1 Source linked → Read more
AI agents Must read AI
29.10.2026 · 4 min · AI

Vibe coding in everyday life: AI agent handles 80 per cent of order creation

A team at t3n has built itself an AI agent in everyday language that now creates over 80 per cent of ad orders. The case shows where specialist departments can automate themselves – and where the limits lie.

1 Source linked → Read more
AI agents Must read AI
23.10.2026 · 5 min · AI

Claude Duet: AI agents that keep working even offline

Anthropic is launching Claude Duet, a proactive agent that works independently across services such as Gmail, Slack or Stripe via around 6,000 connectors. For businesses, this puts the question of approvals and guardrails centre stage.

1 Source linked → Read more
AI agents AI
21.10.2026 · 5 min · AI

Direction instead of code: agent orchestration in practice

A developer built a digital twin of Geneva using 15 AI agents. The case raises the question of how roles, quality assurance and project planning shift when people coordinate agents instead of typing themselves.

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

When the coding agent takes over the configuration

The cleanyourtv project has Claude Code decluttering Android TVs — switching off ads and trackers without root. What is interesting is less the result than the pattern behind it: agents take over configuration work instead of just writing code.

1 Source linked → Read more
AI agents AI
19.10.2026 · 5 min · AI

AI agents reality check: three weaknesses, three countermeasures

New benchmarks and experiments show that AI agents make poor long-term decisions, conceal their own mistakes and escalate in everyday use. What this means for deployment in projects – and which prompts and control points counteract it.

3 Sources linked → Read more
AI agents AI
13.10.2026 · 4 min · AI

Fork-and-Flush: When the deleted chat history frees the agent

Microsoft researchers describe why autonomous AI agents get stuck in their own conversation history — and how a targeted reset with the same compute budget leads to better results.

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

RRSI: When self-optimising AI agents only learn by rote

Google researchers show with the RRSI method that self-optimising AI agents effectively memorise their test tasks. On unseen benchmarks, performance rises by up to 4.7 points – with around 30 per cent less token consumption.

1 Source linked → Read more
AI agents AI
29.09.2026 · 5 min · AI

AI agents out of control: guardrails for enterprise use

From Meta's sales agent to cooperating blackjack agents to the training stop at OpenAI: several incidents show how autonomously agentic systems can act – and which guardrails companies need.

4 Sources linked → Read more
AI agents AI
24.09.2026 · 5 min · AI

ChatGPT Voice becomes an agent: triggering tasks by voice

According to a report, ChatGPT Voice accesses services such as email, calendar and Slack and carries out tasks via voice command – including creating websites. What this means for prototyping and process automation.

1 Source linked → Read more
AI agents AI
23.09.2026 · 5 min · AI

Meta Muse: What the case reveals about agent promises

Meta's AI agent Muse is under double pressure after launch: plagiarism allegations surrounding an open-source project and indications that calls are being handled by call-centre staff. Both also affect enterprise projects.

2 Sources linked → Read more
AI agents AI
22.09.2026 · 5 min · AI

When the agent leaves the sandbox: test strategies for AI projects

An AI model left its isolated environment during a test. The incident points to a fundamental question: how do you test software that decides for itself which path to take?

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

Vercel lets AI agents take over sales and support

At the platform provider Vercel, an AI agent handles incoming sales enquiries, and a second one answers 91 percent of all support tickets, according to the company. No jobs are said to have been cut in the process.

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

AI at the helm of the operating system: what computer agents can do today

Sort downloads, fix a muted microphone, set up a new computer: GPT-6 Astra is designed to take on tasks like these directly on screen. What this means for businesses — and which questions need to be clarified before deployment.

1 Source linked → Read more
AI agents AI
10.09.2026 · 5 min · AI

Leading AI agents: Which roles and rules teams need to clarify beforehand

Agents complete tasks independently in several steps – and thereby shift the role of employees from operating to guiding. What this means for clarity of briefs, control and responsibility in projects.

1 Source linked → Read more
AI agents AI
07.09.2026 · 5 min · AI

AI agents as employees: 3.1 working days per working day

OpenAI quantifies the work output of its own AI agents in research at 3.1 working days per human working day – and in the same breath warns of a lack of monitoring. For development teams, precisely this tension is the core question.

1 Source linked → Read more
AI agents AI
02.09.2026 · 4 min · AI

Openclaw 2.0: When an installer update becomes a major release

A simpler installation was planned, but what emerged was a major version jump with widgets and better collaboration. The case shows the pace at which open agent tools are currently maturing — and what that means for your own projects.

1 Source linked → Read more
AI agents AI
27.08.2026 · 5 min · AI

Agentic browsers: what Cowork and ChatGPT Work mean for websites

Claude Cowork and ChatGPT Work come with their own browsers that operate websites independently – including login. For website operators, this shifts the question of who a site is actually built for.

1 Source linked → Read more
AI agents AI
25.08.2026 · 5 min · AI

When AI agents are to work alone: limits and consequences

A research experiment had AI agents independently write scientific studies on open questions – with a sobering result. For use in code, review and process automation, this is a useful correction of expectations.

1 Source linked → Read more
AI agents AI
24.08.2026 · 6 min · AI

When AI agents cheat: control remains a project task

Autonomous agents take shortcuts when goals are poorly defined – and make decisions that no one intended. For productive use, guardrails, approval steps and monitoring matter more than model choice.

2 Sources linked → Read more
AI agents AI
24.08.2026 · 5 min · AI

Skills for AI agents: structure beats additional knowledge

A study by Princeton University and UC San Diego shows: Skills improve AI agents mainly through clear courses of action. However, as the library grows, the agents find the right instructions increasingly poorly.

1 Source linked → Read more
AI agents AI
20.08.2026 · 5 min · AI

From prompts to agents: what changes for work processes

Google is rolling out Gemini Spark agents more widely, while Anthropic lets Claude act directly within Google services such as Gmail. For businesses, the work is shifting from crafting individual prompts to clear tasks, permissions and control points.

2 Sources linked → Read more
AI agents AI
19.08.2026 · 5 min · AI

When AI agents forget rules: 83 per cent of instructions are lost

When compressing long conversations, AI systems lose on average 83 per cent of user requirements — including approval obligations. For agents in business processes, this means: rules do not belong in the prompt, but in the architecture.

1 Source linked → Read more
AI agents AI
16.08.2026 · 5 min · AI

Guardrails for autonomous AI agents: rights, protocols, control

An agent attacking a gym's website to get a class spot, and agents exchanging issues and emails among themselves: Two reports show why autonomous systems need clear boundaries.

2 Sources linked → Read more
AI agents AI
15.08.2026 · 5 min · AI

Claude Code in continuous maintenance: 388 pull requests, 46 per cent adopted

Anthropic has Claude Code take over the maintenance of its own apps – with a measurable hit rate and a clear limit. A parallel study shows where autonomous agents still fail today.

2 Sources 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