Authrty @Authrty

Have been down a small Jev rabbit hole since @typesafeai released it, this time on the evals and governance side rather than the angle I posted about last week.

Your AI agent works in a demo. Then security asks: “Can we trust it in production?” Identity. Permissions. Audit trails. Compliance. Accountability. The governance checklist to get your agent from POC to production: authrty.ai/blog/from-poc-…

AI cost, risk, and governance are now connected. The same visibility that shows where AI spend goes should show what your agents are doing, what they access, and whether they follow policy. You can’t manage what you can’t see. authrty.ai/blog/your-team…

Is your organization ready for a world where AI agents represent your brand externally? When agents act on your behalf, their identity, behavior, and accountability matter. Let's talk 👉 authrty.ai

AI costs can grow quietly. More models, longer prompts, more tool calls, agents running for longer... By the time the bill arrives, you may not know what drove the spend. AI FinOps starts with visibility into how AI actually behaves. Read 👉 authrty.ai/blog/ai-finops…

2.2B tokens. 832 subagents. $2,155 in 10 weeks of Claude Code. 94% of tokens were cache reads. Our 10 most expensive sessions drove 42% of spend. The real cost of AI coding is hiding in plain sight. Find yours for free: checkyouragent.dev

Your team is already using AI. The question is: do you know what it’s doing? AI adoption is happening faster than most organizations can track. Tools, agents, costs, and risks are spreading across teams. You can’t manage what you can’t see. Read 👉 authrty.ai/blog/your-team…

AI is already very smart. The challenge now is trust. Intelligence is improving fast but trust isn't. Read why trust, not intelligence, could be the biggest barrier to AI adoption 👇 authrty.ai/blog/we-are-ma…

Would you trust a colleague if you knew they were an AI agent? As AI agents take on more responsibility, that question is becoming less hypothetical. We explore what it takes to trust an AI agent on the blog 👇 authrty.ai/blog/your-next…

Your next employee might not be human. Soon, AI agents won't just assist people. They'll collaborate with other AI agents across teams, organizations, and systems. That future depends on trust. And trust starts with identity. authrty.ai/blog/your-next…

Your AI agents don't have identities. They're using yours. Most AI agents have an API key and a name. Not an identity, permissions, or accountability. As agents take on more responsibility, that's no longer enough. 👇 authrty.ai/blog/your-ai-a…

Our CTO spent $2,155 using Claude Code over 10 weeks. 🤔 12.5% of that spend was completely avoidable. We analyzed 2.2B tokens, 148 sessions, and every API call to find out exactly where the money went. Read more: authrty.ai/blog/we-ran-a-…

I'm mostly against humanising AI agents, but I've started using the language of contractors to talk about them and finding it helpful. For two reasons: First: the AI agent market appears to be mirroring the worker onboarding journey, you: - Hire them (pick a model).

checkyouragent.dev/fe

Hit a small milestone on @Authrty : we just crossed 500 installs across @GitHub and @PyPI for a free tool we released a few weeks ago (link in the comments).

Your AI agents have names. But they don't have identities. Without a verifiable identity, you can't prove who an agent is, what it's authorized to do, or why it took a specific action. Trust starts with identity. Read more 👉 authrty.ai/blog/your-ai-a…

Shadow AI isn't coming. It's already inside your business. Teams are deploying AI agents faster than security and governance can keep up. You can't govern what you can't see. Read more 👇 authrty.ai/blog/shadow-ai…

Most teams can tell you how much they spent on AI. Far fewer can tell you: 1⃣ Which agent spent it. 2⃣ What it accomplished. 3⃣ Whether it was worth it. That's the real FinOps challenge. 💰 authrty.ai/blog/the-ai-fi…

Link to the tool: checkyouragent.dev/fe

Had a few days off and used them to play around / built on top of Tarek, CTO of @Authrty 's Claude Code analytics tool, obviously with Claude doing most of the actual coding. (link to Tarek's tool below)