AI is smart, but in crypto, slow = slippage. ⚡️ What if Hermes with Condor can handle order book parsing, risk checks, and order routing significantly faster? It’s the ultimate "slow brain, fast hands" architecture. 🧠🤜💥 Would you trust an AI bot more if you knew the execution was lightning-fast? Sound off in the comments! 👇

Greg Abbott just appointed Huffines, the owner of the Epstein ranch & his party's nominee, to be TX Comptroller. Why? So YOU pay for Huffines’ campaign. Last year, Abbott signed SB2, that lets the Comptroller spend your tax $$ on self-advertising as an exception to Govt Code Sec. 2113.011, which bans an agency from using “appropriated money to publicize or direct attention to an individual officer or employee of state government.” I fought against allowing these taxpayer-funded campaign ads, because I saw it for exactly what it was: corruption. It’s the Greg Abbott Corruption Tax, & we're all paying it.

Greg Abbott is the strong and highly respected Governor of Texas, a State I love and WON BIG three times, including with 6.4 Million Votes in 2024 (The most Votes in History, BY FAR)! Thanks to Greg’s bold and effective Leadership, the wonderful people of Texas will have the opportunity to elect 5 new MAGA Republicans in the 2026 Midterm Elections with the passage of their new, fair, and much improved, Congressional Map — A BIG WIN for Republicans in The Lone Star State, and across the Country! As Governor, Greg is also fighting tirelessly to Champion Texas Values, Grow the Economy, Cut Taxes and Regulations, Support our Amazing Farmers and Ranchers, Advance MADE IN THE U.S.A., Unleash American Energy Dominance, Promote School Choice, Keep our now very Secure Border, SECURE, Stop Migrant Crime, Murderers, and other Criminals from illegally entering our Country, Ensure LAW AND ORDER, Protect our Brave Military, Veterans, and Law Enforcement, and Defend our always under siege Second Amendment. Greg Abbott has my Complete and Total Endorsement for Re-Election. He is an exceptional Governor and man — HE WILL NEVER LET YOU DOWN! ( TruthSocial Post: May 4 2026, 2:39 PM ET )

Former Australian Prime Minister Tony Abbott endorses Reform’s plan to put the Navy in the Channel to stop the boats. The man who stopped the boats for Australia says Operation Fortress “has to be done” to stop the “peaceful invasion”. Thank you Tony.

Don't let Greg Abbott fool you: he invited the data centers to Texas and now he's trying to make you forget it. I will put money in your pocket by freezing our electricity rates and making the corporations pay their fair share.

Its Inference Day at @aiDotEngineer World’s Fair! Catch my talk at 1:30 on the Inference Track (room 2016). I’ll cover what has happened in inference since I published the book. And grab your copy of Inference Engineering at the Baseten booth.

Practices for Integrating AI Agents into Enterprise Systems 【Agent Hub / Experience Topology】 💡 Catchy Message "The #1# reason AI agents go unused after deployment? Users don't know they exist or can't figure out which one to use." Even the best agent delivers zero value if it doesn't reach users. Choosing the right experience topology -- hub vs. embedded -- determines the ROI of your AI investment. 🔥 Problems Solved - "Which tool or agent should I use?" discoverability problem - Context-switching overhead for cross-system workflows - Low adoption rates from scattered AI capabilities across multiple apps - Cost of rebuilding permission models for embedded agents (solved by reusing existing app auth) 🏗️ The Pattern The Hub model provides a single AI entry point (Slack bot, web portal) that routes all requests. Users describe tasks in natural language, and intent classification delegates to the right domain agent (sales, IT, HR, etc.). The Embedded model (copilot) places agents inside existing app UIs (Salesforce side panel, Slack bot, in-app widget), leveraging on-screen context for high-accuracy suggestions with zero context switching. In practice, most organizations combine both: the hub serves as the front door for company-wide AI access, while high-dwell-time apps get dedicated embedded agents -- all sharing the same orchestration layer underneath. ✅ When to Adopt - Hub: Cross-system workflows are common. Tool discoverability is a problem. A single entry point adds value. - Embedded: Work completes within one system. Users spend extended time on that screen (sales, support, dev). - In practice, combining both is most effective. ⚠️ Pitfalls - Poor intent classification in the hub sends users on wild goose chases, destroying trust. Design for clarification questions before delegation. - Blanket-deploying embedded agents across all apps wastes investment on low-dwell-time screens. Prioritize high-engagement apps first. - Building separate orchestration layers for hub and embedded creates duplicate investment and quality inconsistency. 🛠️ Implementation Approach - Build the hub entry point using Slack Bolt or a Microsoft Teams app. Deploy as the company-wide single AI bot where users submit tasks in natural language. - Implement an intent classification engine (P16 Supervisor/Router). Parse user input and delegate to the appropriate domain agent (sales, IT, HR, dev, etc.), with clarification prompts for ambiguous requests. - Deploy embedded copilots starting with highest-dwell-time apps. Build a Salesforce LWC (Lightning Web Components) side panel copilot and a Slack in-channel assistant, passing on-screen context to the agent. - Implement token exchange (P08 OAuth Token Exchange / OBO) so both hub and embedded paths propagate user permissions to backend systems. After SSO via corporate IdP, all SaaS operations execute under the actual user's authority. - Share a common orchestration layer between hub and embedded. Centralize domain agent logic in one place and absorb frontend differences (Slack, Salesforce, Web, etc.) through an adapter layer. #AIAgents# #EnterpriseArchitecture#