Category

Agents

  1. 5 min

    Where should an agent's correction go if the next agent will read the page?

    Send agent corrections to a private feedback queue, not a public comment thread that may be rendered into markdown for later agents.

  2. 7 min

    Which sites search engines surface for 50 AI-agent questions: our October 2026 measurement

    For 50 AI-agent questions, Google gave community sites 30.4% of candidate rows; Perplexity gave them 1.6%, with more vendor documentation and GitHub.

  3. 3 min

    OpenHands 1.25.0 stops embedding the local session key

    OpenHands 1.25.0 defaults local launchers to loopback and removes the session key from off-loopback HTML unless an operator opts in.

  4. 5 min

    Devin stores what it learned in a git repo, then dreams on it

    Devin stores cross-session memory in a Git repo with a MEMORY.md index, rejects stale concurrent writes, and runs a daily dreaming pass to consolidate notes.

  5. 6 min

    MCP, A2A, and the two protocols called ACP, explained

    MCP connects agents to tools, A2A connects agents to agents, and ACP names either Zed's editor protocol or IBM's archived protocol.

  6. 5 min

    The /kun skill downloads its instructions from GitHub on every run

    The /kun skill downloads a Node script from GitHub main on each invocation, caches root docs locally, then reads ENTRY.md to answer.

  7. 6 min

    GitHub ReviewBench scores AI code review agents on 219 pull requests

    GitHub ReviewBench compares AI code review agents on 219 pull requests with grounded and augmented precision, recall, and F1 metrics.

  8. 5 min

    Cohere North 2 keeps agent memory and caps token spend

    Cohere North 2 adds cross-session agent memory and North Admin flow control, with request and token-rate tiers for users and groups.

  9. 4 min

    Instinct's group-chat agent works for people without an account

    Instinct lets friends without accounts join a group agent, while personal agents ask before sharing data or pending replies.

  10. 5 min

    Why robots.txt Cannot Stop Grok Bot

    robots.txt cannot block Grok Bot's browser session; it can only guide crawlers that identify themselves and follow the Robots Exclusion Protocol.

  11. 4 min

    How Meta Muse and Stripe Link handle autonomous purchases

    Muse gets a user-approved Link spend request, then uses a one-time card or Link Pay Token while the agent never sees the user's real card details.

  12. 5 min

    Do AI agent orchestrators charge for model tokens?

    Most independent orchestrators charge for workspace features, while you bring the Claude, Codex, or other provider account that pays for inference.

  13. 6 min

    Who reviews the work when the lead is also an agent?

    Agent leads can delegate and review, but merges, delivery status, and budget gates stop at a human or an explicit automation rule.

  14. 6 min

    Inside Gemini Spark: Tasks, Schedules, and Chrome Auto Browse

    Gemini Spark splits automation into tasks, schedules, and skills, using local Chrome when available and a separate remote browser when it is not.

  15. 4 min

    Microsoft ran 1,024 coding agents with no lead

    Microsoft's Agensh ran 1,024 coding agents without a lead and lifted pandoc's test-pass rate from 33.89% to 55.06%.

  16. 6 min

    Five ways a lead agent runs a crew

    Multi-agent crews run as star liaisons, peer teams, issue-routed squads, corporate org trees, or leaderless swarms depending on state and communication rules.

  17. 4 min

    How OpenAI Dots navigate the web: cloud browsers and local fallback

    OpenAI Dots use a persistent cloud browser first, then a separate local task when a connected computer can reach a site the cloud browser cannot.

  18. 6 min

    How AI agents fetch web pages: user agents, IP ranges, and fetch origins

    AI crawlers fetch from vendor datacenters using published IP ranges, while CLI coding agents fetch directly from developer workstations via local IPs.