⌘ Tech

Beyond Token Maxing: The Path to Profitable AI

When: Wednesday, July 1 · 6:30 PM – 8:30 PM
Where: James Bong Building — Yerba Buena
Listed by: Lu.ma — Gen AI SF

Agentic AI changed the cost equation. Multi-step reasoning, tool calls, and agent fan-out consume tokens with no natural ceiling — and under per-token pricing, your bill grows with every request. Cheaper tokens do not help when your agents consume them faster than prices fall. Teams moving agentic workloads into production keep hitting the same wall: the cost structure breaks right as the product starts working. Token maxing was never a strategy — it is just what unmanaged agentic spend becomes. This evening is about the other path: optimizing tokens instead of maxing them, and what it takes to run agentic AI at a fixed, predictable cost. What we will cover Why agentic consumption outruns falling token pricesThe difference between maxing tokens and optimizing themHow teams protect gross margin while scaling agentic productsPractical approaches to predictable cost: reserved capacity, model routing, open-source models Format A short framing talk, a panel with operators living the agentic-cost problem firsthand, then drinks and conversation. Intentionally small — built for real discussion, not a crowd. Who should attend Engineering and AI leaders running agentic workloads in production, and the finance leaders responsible for the economics. Built for teams scaling from experiment to production. Speakers Panel to be announced. If you are living the agentic-cost problem and want to share your perspective, reach out — we are still shaping the conversation.Note: Capacity is intentionally limited, register early to secure your spot

More tech soon

TBA

Innhouse with E2B & Inngest

The tradeshow floor will still be there. Come eat first. Whether you're in town for AI Engineer World's Fair or just live in SF and want to hang out, you're invited.

⌘ TechLu.ma — Gen AI SFRSVP · Luma

When: Wednesday, July 1
Where: San Francisco

The tradeshow floor will still be there. Come eat first. Whether you're in town for AI Engineer World's Fair or just live in SF and want to hang out, you're invited. Join E2B and Inngest for lunch on Wednesday, July 1st from 12–2pm, just steps away from Moscone West. Grab-and-go lunch from Señor Sisig, matcha & coffee, swag, and a rooftop DJ. Space is limited, request to join!About Inngest Inngest is the durable execution engine that lives in your codebase. Wrap any function in Steps to instantly add retries and control flow. And because Inngest executes each step, you get deep observability your APM tools can't reproduce. No workers, no queues, no added instrumentation. Trusted by ElevenLabs, 11x, Replit, Cohere, and more.About E2BE2B gives AI agents computers with real-world tools. Fast, secure, and built for scale, it powers the infrastructure behind Manus, Genspark, Lindy, and some of the most widely used consumer and enterprise agents in production.

RSVP on Luma

TBA

IPO: Bending Spoons (Nasdaq: BSP)

Its portfolio includes Eventbrite, Evernote, Vimeo, AOL, WeTransfer and Meetup.

⌘ TechTechMeme EventsDetails · techmeme.com

TBA

IPO: Neutron Holdings (Nasdaq: LIME)

Please make sure your browser supports JavaScript and cookies and that you are not blocking them from loading.

⌘ TechTechMeme EventsDetails · techmeme.com

TBA

Keycard Workshop @ AI Engineer World's Fair

111 Minna Gallery and Event Space — Yerba Buena

Your agents are reaching for real tools and real data. The risk isn't the capable agent, it's the standing secret it holds.

⌘ TechLu.ma — Gen AI SFRSVP · Luma

When: Wednesday, July 1
Where: 111 Minna Gallery and Event Space — Yerba Buena

Your agents are reaching for real tools and real data. The risk isn't the capable agent, it's the standing secret it holds. One long-lived API key sitting in an agent's environment is one prompt injection or Shai-Hulud away from being read out. At AI Engineer World's Fair, Keycard is running a hands-on workshop where you build the answer on your own machine. We'll serve lunch and then you'll build a custom support-escalation MCP server in TypeScript (Express, Streamable HTTP), and lock down both the server and everything it touches with Keycard, end to end. You'll leave having built a server with three tools: Read support tickets, where the user's identity is swapped for a read-only credential so no standing key ever sits in your serverEscalate to engineering, where an LLM scrubs the PII before posting a clean issue to Linear using a write-scoped credentialDelete an escalation, which asks for a scope your policy refuses to grant What you'll learn: Why standing secrets are the real risk in agentic systems, and how to build them so your server never holds oneHow to give each tool exactly the access it needs, and nothing moreHow to trace every hop of an agent delegation chain in a complete audit trailHow to set policy that blocks an over-permissioned action Bring a laptop with Node and npm, a GitHub account, and your local coding agent (Claude Code, Cursor, Codex, or Copilot). TypeScript familiarity is strongly preferred. You'll walk out with a governed escalation server you built, and a clear pattern for securing every agent you ship next. Join us if you're building MCP servers or agentic systems and want to learn how to control access to your server and the resources behind it.

RSVP on Luma