Every breaks down how it made its Slack company agent more token-efficient
every · x · 2026-10-08
- Every launched Every Agent, a shared agentic coworker in Slack meant to make a whole company AI-native; token costs are passed through at no markup, so the team is incentivized to cut token usage.
- Engineer Paridhi Agarwal published a deep dive on making the agent more token-efficient, including a reusable four-step workflow for finding token waste in your own software.
- The accompanying podcast covers why Every moved from everyone running personal OpenClaw agents to one shared company agent: Dan Shipper's personality-driven personal agent (R2-D2) died when a power cord got knocked loose and he never revived it — "in a work context, I mostly care: does it do the thing?"
- Also included: the team's current model picks, a fresh batch of Thesis Statements, and Willie Williams on being an AI-first engineering manager.
Related event: Every launches Every Agent on Slack as a company-wide AI coworker(26 posts)→
More from coding & agent
- AI agents made writing code cheap, but reviewing generated code is a different job — alex_verem · 2026-10-08
- CADFather: Autonomous Agentic System Reconstructs Parametric CAD from 3D Meshes — Gennadiy Savrasov · 2026-10-08
- UniSkill: Actor-Aligned Skill Proposals Hit 98.4% Success on ALFWorld — Yifei Lu · 2026-10-08
- Client banned AI from payments data; 15 months later they asked for the AI setup — alex_verem · 2026-10-08
- Open-Source FrameForge Chains Prompts on MiniMax h3 for Long Combat Videos — Super_Range45 · 2026-10-08
- Aseprite MCP Rebuild: Grid Loop + Pixel-Art Knowledge Base Boosts Output Quality — Complex-Log-635 · 2026-10-08