tade — blog

tade / blog

Writing

What we have learned running a team of coding agents. Every screen in a post is drawn by Tade itself.

  1. Tade on a server of yours, and one window over all of it3 min

    A VPS of yours runs Tade with the laptop shut, and the Mac's window shows and drives every machine's projects over SSH. One Tade per machine, nothing merged.

    remotevpsagentssafety

  2. Run as many coding agents as you can land4 min

    Running agents in parallel is the easy half. Landing their work is the queue, and you are it — so that is the half Tade now leads with.

    landingagentsjevreview

  3. Four doors in, and one rule behind all of them13 min

    A file written here, a labelled GitHub or Linear issue, an @-mention in Slack — four polls, one grant, one rule, one queue, and a person who approves.

    intakeawaysafety

  4. Tade Away: the control room, on a phone you paired9 min

    Agents run for hours, and nobody should have to sit with them. Tade Away puts the control room on a phone you paired, served by the Tade window itself.

    awayagentssafety

  5. The away view, and the switches in front of it10 min

    One page your own machine serves to a phone you paired at it, what it took to make acting safe, and every setting you have to find to turn any of it on.

    awaysafetysetup

  6. When somebody else files the ticket8 min

    Four doors into one machine, every one of them a poll rather than a webhook, and a task that stays parked until somebody at the keyboard approves it.

    intakeworkflowssafety

  7. A check nobody ran is not one that passed5 min

    An agent runs the checks and then commits, so HEAD moves under the run. Carrying it forward honestly means comparing trees rather than commit ids.

    checksci

  8. A queue that holds, and says why it did4 min

    Three agents built this blog in order. Six times in September a fourth was held because another was already mid-edit in the files it planned to change.

    queueagentsdesign

  9. From a red main to green in thirty-six minutes5 min

    On 28 September ubuntu-latest went red on Tade's own main at 08:15. A watch found it at 08:20, an agent removed the race, and CI was green again by 08:51.

    ciwatcheschecksagents

  10. A watch may only ever add work6 min

    Nine watch schedules looked 1,447 times in four days here. Four findings started an agent, 425 looks could not look at all, and none of them may push or merge.

    watchessafetysentrydependencies

  11. Every picture on this site is drawn by the program2 min

    A screenshot starts going out of date the day after it is taken. Every screen in a post here is rendered by Tade itself, from the scenarios its own tests protect.

    screenshow-this-is-built

  12. Forty-eight findings, nine of them real6 min

    A judge that flags things is easy. This is the table saying how often ours was right, which question turned out to be noise, and what was done about it.

    jevreviewcalibration

  13. Three kinds of dollar, each one marked5 min

    In seven days this machine spent $200.77 that a harness priced exactly, plus 3,177 million tokens no dollar figure covers. Tade never adds those together.

    spendcost

  14. What Tade will not do, and why not7 min

    Ten refusals that are the design rather than a backlog, including the three that will cost somebody something and the one that is only true if they choose tmux.

    designsafetyrefusals

  15. Why a task never spans two repositories4 min

    One orchestrator runs agents in every repository at once. What it refuses to do is let a single task span two of them, and the reason is git rather than tidiness.

    multi-repodesignagents

the windowrss15 posts│latest 2026-10-18