Urgent.News

What's breaking now, across thousands of outlets.

Tech

One inbox for the comments that come back

A post is the start of a conversation, and the conversation happens in seven different apps. Clienzo's inbox brings the comments back to one place: Facebook, Instagram, Threads, Bluesky, Mastodon, DEV and Tumblr. From there you can reply, hide a comment, or mark it done. Pulled, not pushed The textbook way to get comments is webhooks: the network calls you when something new arrives. Clienzo…

Clienzo’s inbox consolidates comments from seven different social media platforms into a single location. These platforms include Facebook, Instagram, Threads, Bluesky, Mastodon, DEV, and Tumblr. Users can then interact with the comments by replying, hiding them, or marking them as completed. Clienzo achieves this by pulling comments rather than pushing them, unlike the traditional method of using webhooks.

This pulling method involves Clienzo periodically checking the comments on the posts it published within the last 30 days from each network, with a maximum of one check per minute per account owner. While this approach might not be as real-time as webhooks, it is a more straightforward solution that works across all networks without requiring each platform's app to have extra endpoints and undergo additional reviews.

The most significant advantage of pulling is that it allows for permissions setup during the initial integration, regardless of the network. The permissions needed to read and reply to comments involve a second review round, while each reply, hide action, or status change requires two checks to ensure both the comment and the connected account belong to the user making the request.

AI-generated suggestions for replies were initially problematic, often suggesting responses that were irrelevant to the conversation. The issue stemmed from the model’s limitation of only processing the initial 280 characters of the original post, leading to misunderstandings regarding the context of the discussion. To address this, Clienzo improved its AI suggestions by providing the entire post, clearly defining roles within the conversation (Them, You), removing "@mentions" to avoid confusion, and incorporating a short business profile that includes information about what the business does, its tone, trusted facts, and a list of things it should never say.

This additional context helps the AI generate more accurate and relevant suggestions. If no profile is available, Clienzo defaults to using the connected accounts' bios. Users can still override any suggestions by manually pressing the Reply button. Looking ahead, Clienzo plans to develop a public API to further enhance its capabilities, along with implementing additional safety measures or guardrails to ensure responsible use of the platform.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

How Anti-Cheat Systems Detect Unauthorized Software in Online Games

How Anti-Cheat Systems Detect PUBG Cheats: Aimbots, ESP and Game Security Online multiplayer games have become increasingly complex, and so have the security challenges surrounding them.

  • Anti-cheat systems use multiple layers of protection.
  • Client-side monitoring verifies game components.
  • Server-side validation independently validates gameplay aspects.

More from Friday 6 November →