AskCodi

The inbox model for agent blockers is a smart way to cut the noise compared to watching a chat thread spiral. Curious how AskCodi scopes context between projects — does each project get its own isolated context window, or do the agents share ambient workspace state across the whole account? Also wondering if there is a mode where sensitive code stays local and only higher-level summaries go to the cloud.

@shreyans_assistiv Congratulations for your launch. Does Codi work across multiple projects simultaneously, or is it limited to one repo at a time like other AI coding tools? The description mentions "parallel across all your projects", just wanting to confirm if that means true multi-project orchestration from a single inbox.

the overnight autonomy part is what I keep coming back to. if Codi picks a wrong approach at 2am and just keeps going since nothing hit the "needs a decision" bar, do you find out in the morning after it burned hours down a bad path, or is there some checkpoint that catches a run going sideways before it eats your whole night's budget on the wrong thing

@shreyans_assistiv congrats on the launch. Which models do you find are being used most often?

congratulations on the launch! What is the differentiation here between AskCodi and me instructing my agents to run in parallel while using the most optimized models for a given task in Cursor or Conductor? In my mind I just create a skill about this but I could be missing something.

Congrats on the launch. The routing question is already well covered above, so a different one.The part I would poke is memory over long unattended runs. "Remembers your whole codebase" plus "keeps working in your off-hours" is the exact case where drift bites. On a long run the working context gets summarised to stay affordable, and a summary of the codebase slowly stops matching the codebase. Nobody is watching, so the agent keeps building confidently against a picture that has gone stale.So my question, does Codi re-read the actual files as ground truth during a run, or does it work from its remembered version of them? Because for a supervisor running for hours with no human in the loop, what it remembers about the code and what the code actually says drift apart, and that gap is invisible until the mroning.Not a gotcha, it is the thing I get wrong most on long agent runs myself.

This is a great product, I was skeptical at first. I use co-work right now, but this really work done

@shreyans_assistiv I tried new version, What happens if I update the feature board while the agent is running on the task?

Congrats on the launch. The “AI CTO on your Mac” angle is strong, especially the inbox as the main interface instead of another control room.The part I’d want to try is how it handles an existing messy codebase, not a clean greenfield project. Can Codi build a useful feature map from a repo with older decisions, inconsistent patterns, and half-finished work, or does it need the project to be fairly well-structured first?

Congrats on launching a neat product! QQ: the cost story depends on Codi correctly calling a task 'boring' and handing it to a cheap model, and the tasks that look boring but aren't are exactly where cheap models produce plausible-wrong output. How are solving this conundrum if I didn't invent it at all and it exists?

Congrats on the launch guys 🥳! Quick question though I'd usually want to run 2-3 branches on the same repo at once (say a feature, a bugfix, and a refactor in parallel). Does AskCodi isolate that at the branch/worktree level within a single project so they don't conflict, or is the parallelism mainly across separate projects?

Even if we clearly explain the full product vision and guidelines to Codi upfront, how do we ensure the AI agents it runs don't drift off course during execution, especially on longer, multi-step tasks? What mechanisms are in place to keep them aligned with the original intent throughout, not just at the start?

Hey PH 👋 Sachin here, One more thing for anyone coming over from Product Hunt today.The app is free to try for 7 days, no strings. After that it's $60 for the year. Most people spend more than that on AI in a couple of months, and Codi is built to send the cheap work to cheap models, so it usually saves you more than it costs.Two ways you'd genuinely help us:1. Tell us the first moment Codi lost your trust. That's the thing we most want to fix.2. If you juggle more than one project, tell us whether having Codi run them in parallel actually saves you time.We're around all day and will answer every comment. If something breaks, reply here or reach out to us via the web app support and we'll jump on it.

How do balance cost savings without sacrificing output quality?

How did GPT-5.6 change the ambition or scope of what you shipped?