The Full Agentic Stack: What are you actually deploying? 🏗️

Curious to see what everyone's end-to-end architecture looks like right now when deploying true agentic agents for clients. We’ve moved way past basic chatbots, and the infrastructure to build a fully managed AI employee has gotten deep.

I’d love to know what your non-negotiables are across the entire stack. What are you using for:

The Brain & Logic: Are you relying primarily on Claude’s native computer use, testing Grok 4.5, or routing between multiple open-source models depending on the sub-task?
Compute & Harnesses: What is your core operating environment? (Orgo cloud setups, Hermes, OpenClaw, or custom desktop controls?)
Comms & Identity: How is your agent talking to the world? Are you hooking up AgentPhone for native voice/SMS/iMessage, using AgentMail, or building custom integration layers?
Security & Memory: How are you handling the tricky stuff? Where are you storing the agent's passwords and API keys securely (1Password, Doppler, custom vaults?), and what are you using to manage its memory and state without the stack turning into a debugging nightmare?

The Client Reality: Tech aside, what specific workflow are you actually wrapping this stack around to charge that $5K/mo retainer? (e.g., outbound sales, automated data entry, full customer support reps?)

Drop your full stack and your primary use case below. Let's compare notes!

1 comment

The Full Agentic Stack: What are you actually deploying? 🏗️