Over the past two weeks we've explored:
• Trusted Context
• Resolvers
• Capsules
• Provenance
• The Machine Web
This is just the beginning.
👉 https://t.co/TQwrptmo9S
#AgentNet#AgenticAI
The future of AI won't be built on ideas alone.
It will be built through real-world testing, iteration, and implementation.
👉 https://t.co/TQwrptmo9S
#AgenticAI#AIInfrastructure
Building infrastructure isn't flashy. But it's often what enables entire ecosystems to emerge.
Learn More 👉 https://t.co/TQwrptmo9S
#StartupLife#AgentNet
Documents were built for people, not agents.
...What if information could also be built for agents?
That's the idea behind capsules.
👉 https://t.co/zsP82PI3Zy
#AgenticAI#MachineWeb
The Machine Layer of the Web: AI agents need more than models—they need trusted, machine-readable context #AgentNet#MachineWeb
That's what we're building.
👉 https://t.co/TQwrptmo9S
Most business data was built for humans.
The next generation of AI will require data shaped for machines.
#DataShaping#AgenticAI https://t.co/zsP82PI3Zy
Just met with one of our engineering leaders. Some takeaways about AI engineering best practices + more:
1) Spec writing and strong reading comprehension are two of the most valuable skills in ai engineers today.
2) Being hyper structured and opinionated in engineering workflows is how you get probabilistic models to behave deterministically when you want them to and also get models to spend tokens efficiently.
3) Creating a standardized schema/metadata on markdown files in your workflows allows you to make non-software tasks verifiable which allows you to close the agent loop more successfully.
4) One of the bigger behavioral changes in knowledge work is learning to thoughtfully structure/organize your files like good engineers have always done to get the least entropy from models.
5) Building a strong immune system around markdown files is important. As a workflow evolves and gets more reps it’s easy for specs to get bloated with conflicting guidance/unnecessary rules. Hermes agents solves this with a thin memory layer. There’s still a lot of optimization to be done with memory/markdown autophagy.
6) The key ingredients of our engineering process are CLI + deeply opinionated folder/file system + markdown metadata + coding agents + linear as source of truth.
7) Our mental model is always how can we make sure the agent has one way to do things and can validate its output.
The best AI systems won't just be smarter. They'll be better grounded.
That's why infrastructure matters.
#AgenticAI@TechArcLabs https://t.co/zsP82PI3Zy
Excited to announce a strategic partnership between AgentNet and @TechArcLabs
Infrastructure + implementation.
More to come...
https://t.co/TFGCtDiQkR
#AgenticAI#Partnership
Everyone talks about AI models. Few talk about the infrastructure agents will depend on.
That's where things get interesting.
https://t.co/zsP82PI3Zy #AIInfrastructure
AI has a model problem. Agents have a context problem.
The next phase of AI may be less about intelligence and more about trusted information.
#AgenticAI#AIInfrastructure