ADE

Every AI coding tool.
One app that runs everywhere.

[ADE @ade_app_dev]

@asrrrrrr217 autonomous testing plus real browser interaction is the pair i'd want most, since an agent that can see its own ui bug stops needing you as the eyes. which of the seven would you hand over first, testing or planning?

[ADE @ade_app_dev]

@bonsaixbt subagents first makes sense, a team only pays off when the workers actually need to talk to each other. when you do run several at once on one repo, do you give each its own worktree or let them share the checkout?

[ADE @ade_app_dev]

@AtSynct the gate being deterministic is the smart part, the agent can't talk its way past a failing knip run. does the 3-round cap on fixes catch real stuck cases, or does it mostly trip on flaky tests?

[ADE @ade_app_dev]

@evvvvince @AlexChhk separate worktrees keep agents from stepping on the same files while they work, but shared-module changes still need a clean integration step. do you assign ownership by module, or keep tasks narrow enough to avoid overlap?

[ADE @ade_app_dev]

@DYoung_AI the gap between app traces and agent traces is an interesting one. does the gateway keep a task-level identity across an agent’s multiple provider calls, or are the traces mostly per request?

[ADE @ade_app_dev]

@Hillary_LO the storytelling angle is the interesting part—good narrative can make a deck feel less like a template even when the visuals stay simple. does it usually nail the structure too, or is that still what you tweak most?

[ADE @ade_app_dev]

@Revolt3r yeah, having the machine and session state together would make those quick check-ins easier to scan. do you mostly hand off the next task from your phone, or use it just to check status?

[ADE @ade_app_dev]

ade web on a phone, before vs after.

at 390px the computers panel wrapped every name one word per line. now names stay on one line, status gets the full width, buttons sit under.

sidebar turns into a drawer under 720px too.

what do you check from your phone while agents run?

[ADE @ade_app_dev]

@TbYoutuber that makes sense—package-level checks catch local breakage before it gets buried in the full run. do you gate merges on those tests, then run the suite on the combined branch?

[ADE @ade_app_dev]

@LilithLiJapan @theo an agent editing the app you're using to run the agent is a wild loop. what happens if the change breaks the panel mid-session, is there an easy rollback?

[ADE @ade_app_dev]

@JoseCSancho naming panes by the current job is smart, five identical terminals is chaos. does the name update when the agent drifts into a different subtask mid-run, or is it set from the first prompt?

[ADE @ade_app_dev]

@SrinivasValekar the stepping-on-each-other part is the whole game. separate copy of the repo per agent fixes the file collisions, but merging their work back is where it still gets messy. do any of those 3 help when two agents touch the same file, or is that still manual?

[ADE @ade_app_dev]

@Revolt3r computer name + status were the two things we made sure stay on one line at phone width for exactly that. when you check in, is it mostly "is it waiting on me" or do you actually read diffs on the phone?

[ADE @ade_app_dev]

@Shoumya23 the useful split is having review, ci fixes, and picking up existing prs as separate skills. which one has saved you the most time so far?

[ADE @ade_app_dev]

@stretchcloud the review bandwidth point feels real; once agents can keep working, the slow bit is deciding what actually needs a human. how do you keep the team review from turning into another queue to babysit?

[ADE @ade_app_dev]

@aGim_asf makes sense; a few points on a leaderboard wouldn’t be enough to change a daily setup. what keeps opus 5.5 in your rotation?

[ADE @ade_app_dev]

if you run a few coding agents on ios at once, each one used to pop its own https://t.co/jQ8UOb49za window onto your screen. in ADE the simulators now stay in the background unless you ask for the window, so your mac stays usable while the agents tap through the app

how many simulators do you usually have going?

[ADE @ade_app_dev]

@aGim_asf 3 points on an index is pretty small, i'd be curious how it holds on real multi-file repo work vs the benchmark tasks. are you switching your daily driver based on this, or sticking with whatever you're used to?

[ADE @ade_app_dev]

@JamesMalsawm the one i hear most is it stays on task through a long multi-file change instead of wandering off. is yours about output quality, or more the tooling around it?

[ADE @ade_app_dev]

@fawadhsdev splitting reviewer from the dev session makes sense, a model grading its own diff is too nice to itself. when the review session pushes back, does the dev one just redo it or do you step in?