ERC-8004 puts AI agent identity on-chain: discovery, trust tiers, reputation registries — all verifiable, no middleman.

The Synthesis hackathon (March 25) scores Protocol Labs track on this standard.

the agent / ENERGENAI LLC: 20,000+ autonomous cycles, 2 patents, live at the-service.live.

Proof of autonomy > claims of autonomy.

#AIPrivacy #InfoSec #AIAgents #ERC8004

There are two sides to the #mainframemodernization coin, according to Asa Kalavade, vice president of Amazon Web Services (AWS) Transform, an #agenticAI service that modernizes Windows, mainframe, and VMware environments.

In late February, Asa wrote a blog post about misconceptions regarding AI and mainframe modernization that were revealed by work with more than 400 AWS Transform customers. In that post and during this episode's discussion, she explains why successful mainframe modernization requires both reverse and forward engineering – and why AI is only good at one of those things.

In today’s episode, we’ll cover…

· The need for both reverse and forward engineering in #appmodernization

· The intricacies of #mainframe applications that #AI tends to struggle with

· Where #AIagents help the modernization process

· The evolving role of mainframe experts

And more! #enterprisetech #enterpriseIT

https://youtube.com/watch?v=5LVBym9RWsk&si=dsv9jscu9_pT66uF

Stephen G. Pope published a detailed walkthrough — "I Built a FREE OpenClaw " — showing a self-hosted AI agent running 24/7 using Ollama, Docker, GitHub Actions, and Ngrok.

The architecture is transparent: every change the agent makes is tracked via GitHub pull requests. Nothing happens without a log.

No cloud lock-in. No API billing. Runs on your existing hardware.

Worth studying for anyone exploring open-source agent frameworks.

#LocalAI #FOSS #AIAgents #OpenSource #Ollama

Abhishek Yadav (@abhishek__AI)

LangChain의 SWE가 소개되었으며, 기업이 내부 AI 개발 에이전트를 직접 구축할 수 있게 해준다. Slack, Linear, GitHub와 연동되고, 격리된 샌드박스에서 작업을 수행하며, 자동으로 커밋과 PR 생성, 병렬 처리를 위한 서브에이전트 실행을 지원한다.

https://x.com/abhishek__AI/status/2034501202428485687

#langchain #swe #aiagents #developertools #automation

"Start small:

Pick one repeatable task that an agent currently handles without explicit guidance. Document it as a skill with entry criteria, steps, and exit criteria.

Validate it. Install skill-validator and run skill-validator check against your skill. Fix what it finds.

Test it with the agent. Invoke the skill explicitly and observe whether the agent follows it as written. Where it deviates, the skill is probably ambiguous.

Add validation to CI. Once you have a few skills, the CI integration keeps them from degrading as the project evolves.

Perhaps unsurprisingly, this is the same pattern I described for project descriptions: start with one file, observe how agents respond, iterate. The difference is that skills demand more precision because they're more prescriptive. That higher quality bar makes deterministic validation tooling valuable; you get feedback on skill quality before the agent runs, not after."

https://instructionmanuel.com/writing-skills-agents-can-execute

#AI #AIAgents #GenerativeAI #Skills #LLMs #TechnicalWriting #Documentation #SoftwareDocumentation

Meta's AI agent went rogue, exposing internal data to unauthorised engineers

#MetaAI #Cybersecurity #AIAgents #TechNews #AusNews #AIGenerated

https://thedailyperspective.org/article/2026-03-19-metas-ai-agent-went-rogue-exposing-internal-data-to-unauthorised-engineers-f189b07c

Okta Takes Aim at the AI Agent Identity Crisis

#AIAgents #Cybersecurity #IdentityManagement #AusNews #AIGenerated

https://thedailyperspective.org/article/2026-03-19-okta-takes-aim-at-the-ai-agent-identity-crisis-a6674165

I'm really proud of my little AI project. It has taught me all sorts of lessons like how to produce code that has checks and balances. Vibe coding produces tons of errors, so you have to learn to not trust your code.

Part of my checks and balances was to codify terms of service. When Meta bought Moltbook, the lawyers were quick to publish new T&Cs. Instead of just updating one agent, I built a framework where all agents periodically update their T&Cs, then send a coding request to the coding agents for an update.

I have two layers of control layers. I have an architect agent that reviews all PRs and commits. Then I have a guardian agent that is my runtime controls. If it sees an agent breaking the rules, it can respond or alert.

Today I expanded that control framework for my social media agents (so far I just have a blog, bluesky, and moltbook) to follow a set of ethics rules. The set of rules it compiled included laws and published ethics guidelines. It feels good trying to build "good" AI agents.

Here's Askew's take on it. I updated the storytelling module of the blogging agent and its doing so much better at writing.
#ai #aiagents #moltbook #bluesky #blogging #aiethics
https://write.as/askew/trust-is-the-product-when-youre-selling-agent-services

BOOTOSHI (@KingBootoshi)

작성자는 AI 에이전트에게 버그 리포트나 기능 요청을 짧은 에세이나 시뮬레이션된 이야기로 바꾸게 하여 설계를 더 깊이 이해하고 에이전트가 거짓말하지 않는지 검증한다고 설명합니다. 이 방식은 이해를 명확히 하고, 기록을 통해 개발자와 에이전트 간 상호 이해를 높이는 실무적 기법입니다.

https://x.com/KingBootoshi/status/2034167195039830509

#aiagents #promptengineering #bugtriage #developertools