Every launches Frontier log: storyboard-first video editor, fake Slack for agent testing
every · x · 2026-10-29
Every's team launched the Frontier log, a weekly record of experiments with new models, agents, and workflows. Recent entries include:
- Storyboard-first video editor: redo a sketch or story beat before paying for video generation (shelved)
- Heisentool: a fake Slack an agent writes as plain code by watching real tool calls, enabling testing without the real service
- Agent-interviewed documentary: an agent interviews you about an experiment, then cuts a short film
- Everytype: one-place writing, editing, sign-off and preview for the editorial team
- Hill-climbing a skill: author corrections turned into checks, with an agent rewriting the skill until all pass
- Hiring automations kit: four reusable Codex skills for screening, emails, safeguards, phone-screen prep
- Tier-list grades for checks: same 200 outputs judged with yes/no checks vs S-to-F grades
- Clipshot: Mac screenshot/recording app that pipes spoken feedback to your AI assistant
More from coding & agent
- Anthropic says no regression behind Claude Code usage complaints, blames heavy sessions — bcherny · 2026-10-29
- LlamaIndex launches Document Parsing Protocol: 140 rules to standardize OCR output for agents — llama_index · 2026-10-29
- exe.dev Ships WIF Support: Agents Make OAuth Token Exchange Finally Usable for All — davidcrawshaw · 2026-10-29
- Protecting action-taking agents from prompt injection: move defense out of the model layer — Informal-Dust4499 · 2026-10-29
- Designing agent approval screens: show the effect, not the narrative — ClickOk5811 · 2026-10-29
- "Babysit this for me" is now the number one request people make to AI agents — RichardsonDx · 2026-10-29