Employed AI

How people use AI and what happens when they do.

AI Agents

How AI agents use tools, carry out tasks, and report their work. Follow the steps between a request, an action, and an outcome you can verify.

Browse all articles

How do you tell if an agent finished the job?

Check the final state, such as a merged change or a completed task. Compare it with what the agent reported and account for any review or rework.

AI coding agents ship 30% more code, but not measurably more software

A Harvard job market paper built on Jellyfish data from 718 firms finds coding agents raise lines of code by 30%, commits by 20% and pull requests by 23%, while issues and epics resolved show no statistically significant change. Pull request review time rises by 49% and the change-request share nearly doubles.

PostgreSQL 19's reverts: LLM-assisted review surfaced more defect reports than volunteers could fix

PostgreSQL 19 shed several planned features during its beta cycle. Peter Eisentraut counts about 8 to 10 significant reverts, depending on how you count, and describes 'a list of like forty defect reports' where each one carries a fixed overhead until 'you run out of time'. His explanation for the pattern is his own opinion: LLM-assisted code review surfaces defects faster than volunteer reviewers can fix them, and the effective quality bar rose after the features were written. The project gives its own reasons for the removals, citing reliability, a predictable schedule and unresolved design questions, and it does not attribute them to AI review. No independent defect count exists. PostgreSQL 19 is due on 19 November 2026 after a second release candidate on 12 November, and the reverted features are expected to return in PostgreSQL 20.

What should an agent be allowed to do?

Follow the permissions from sign-in through tool use. Look for approval before sensitive actions and an audit trail that records what happened.

One AI agent can hand malicious instructions to the next: inside MCP's trust gap

An independent researcher showed that instructions planted in content one AI agent reads can pass through ordinary delegation into a second agent that trusts the first, and that five organisations separately confirmed and fixed SSRF bugs in their MCP servers. There is no evidence of exploitation in the wild and the acknowledged issues are fixed, while researchers disagree about whether the pattern is a new attack class or plain indirect prompt injection. If your assistants are wired into internal tools, the trust between them is part of your attack surface.

Microsoft says your agents are insiders: the doctrine, the licence boundary and what to adopt

Microsoft's security leadership published a doctrine on 19 October 2026: agents should not inherit a person's standing access, and the model cannot be its own security boundary. The principle is sound and portable. The monitoring is partly in preview, extending Entra's agent security needs a Microsoft Agent 365 licence, and the company selling it holds stakes on both sides.

Anthropic hands Agent Skills to the Agentic AI Foundation: skills security guidance is still a proposal

Anthropic donated the Agent Skills standard to the Linux Foundation's Agentic AI Foundation on 22 October 2026, transferring the name and logo, the GitHub organisation and the agentskills.io domain. The foundation has published governance and ten projects, but the security guidance Anthropic has proposed for people who write and install skills remains unpublished, and the format specification defines no trust, permission, signing or review model for a skill an agent will run.

How do agents act on a customer’s behalf?

A shopping or banking workflow can involve separate decisions about who can sign in, what they may buy, and who approves payment.

Amex wants a proof of intent before an AI agent can buy anything

American Express published an Intent Intelligence Framework on 13 October 2026 that asks a cardholder to approve an agent's shopping instructions before a payment credential is issued. The control sits in the network and the credential, unlike the agent-side budget cap in our earlier piece on Google's enterprise agent. No live deployment was found, and the Create Intent API's public status is unconfirmed.

JPMorgan Blocks Outside AI Agents at the Login, Not the Transaction

Jamie Dimon said JPMorgan will not let 'just any outside agent' in, and a spokeswoman confirmed the bank blocks third-party AI agents from acting for retail customers. What has surfaced is an on-record posture rather than a written policy, and liability, enforcement and open banking stay unresolved.

Spotify says agents are a tailwind. It has published no agent revenue figure.

Spotify's Q3 2026 deck documents 788 million monthly active users, 306 million Premium subscribers and EUR 4,969 million in revenue, and Spotify has announced agent integrations with Meta's Muse, ChatGPT and Claude. It discloses no agent-attributable revenue, retention or listening share, and the company's published developer terms let it limit or withdraw third-party access.