Agents & Automation tag

48 Articles

Agents & Automation ×

Latest AI news — September 17, 2026

Eight items: Anthropic Life Sciences Verification Program; OpenAI misalignment reporting framework; King Charles at Dumfries House; Claude chat+Cowork in one interface; Novo×Anthropic; Google Home MCP; OpenAI funding talks; TypeSafe Jev.

News OpenAI Anthropic Google Safety & Risk Business & Deals Models & Market Agents & Automation

Sep 17, 2026 Latest AI news

Krisztian Eyssen

Latest AI news — September 16, 2026

Six items from Wednesday: Mistral×Mozilla Firefox Smart Window on Mistral Small 4 with zero data retention; Cohere–Aleph Alpha ~$20B merger; xAI Grok Build Memory; OpenAI ChatGPT Ads with Sponsored Agents, HubSpot and Shopify; Zuckerberg rejecting coordinated slowdown; EU Ribera open to AI-safety antitrust treatment.

News OpenAI xAI (Grok) Meta Mistral Safety & Risk Regulation & Policy Business & Deals Agents & Automation

Sep 16, 2026 Latest AI news

Krisztian Eyssen

Latest AI news — September 14, 2026

Five items from Monday's AI news: Trump's Truth Social post against guardrails, Altman's Monday clarification on pacing, Musk's Grok 4.8 roadmap, OpenAI's Perplexity–Astra customer story, and Obama's call for a clear AI plan.

News OpenAI xAI (Grok) Safety & Risk Regulation & Policy Models & Market Agents & Automation

Sep 14, 2026 Latest AI news

Krisztian Eyssen

Case Study: How We Built Our Own Agent

Close to twenty AI tools running side by side, and whatever one of them learned, the next had never heard of. That is where EYAS came from. This post is not a feature list: it shows the decisions, the trade-offs we said out loud, and the one measurement that threw a finished-looking solution out of the window.

Advanced Business owner Case study EYAS Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

human in the loop (HITL)

The point in a process where a person has to approve before the system moves on.

Beginner Everyone Glossary Agents & Automation

Sep 13, 2026 Glossary

Krisztian Eyssen

least privilege

The principle that a system should get exactly as many rights as its job needs — and not one more.

Beginner Everyone Glossary Agents & Automation

Sep 13, 2026 Glossary

Krisztian Eyssen

MCP (Model Context Protocol)

An open standard for AI tools to connect to your systems in a uniform way — to a database, to files, to company applications.

Beginner Everyone Glossary Agents & Automation

Sep 13, 2026 Glossary

Krisztian Eyssen

tool use

The ability of a model to request outside operations — a search, a calculation, a database query — instead of making the answer up.

Beginner Everyone Glossary Agents & Automation

Sep 13, 2026 Glossary

Krisztian Eyssen

AI agent

An AI system that does not only answer but acts: it calls tools, checks, retries, until it reaches the goal.

Beginner Everyone Glossary Agents & Automation

Sep 13, 2026 Glossary

Krisztian Eyssen

Self-Hosted Personal Agents and Their Risks

The security policy of the most widely used open personal agent lists what does **not** count as a vulnerability. This is on that list: **"prompt injection, if it does not bypass policy, authentication, approval, the sandbox or a tool boundary."** And this: **"anyone who can operate an agent can make it do anything that agent is able to do."** This is not a flaw in the system — this is the system. This article is about what you need to know about that before you start it up.

Intermediate Everyone Explainer Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Testing and Monitoring Your Agents

In a survey of 1,300 practitioners, **39.8%** of respondents ran offline evaluation and **32.5%** ran it online — while everyone named **quality** as the main obstacle to getting into production, more than twice as often as cost or security. Everybody logs. Measuring whether the agent is doing a good job is something most people cannot do. This article is about how you can.

Advanced Developer How-To Agents & Automation

Sep 13, 2026 Bite-Sized AI

Krisztian Eyssen

Multi-Agent Systems: When More Agents Help

Five real multi-agent systems were measured in the same study. The best one scored **84.8%**, the worst **13.3%** — and in the middle of the field sit two systems that got **three quarters of the tasks wrong**. The difference did not come from the model. It came from the pattern. This article is about **which four patterns pay back the cost of coordination, and which two do not.**

Advanced Developer Explainer Agents & Automation

Sep 13, 2026 Bite-Sized AI

Tags

Audience

Everyone Office worker Marketer Creative Business owner Developer

Follow Us

Archives

Tags