Changelog ChatAcademia

Stay up to date with all the latest updates, improvements, and new features we ship to help you do better research. We’re constantly improving ChatAcademia for academics and researchers.

© 2026 ChatAcademia

Send Feedback Instantly & Track Every Chat's Credit Usage

Send Feedback Instantly & Track Every Chat's Credit Usage

A new Feedback button in the page header lets you send feature ideas, bug reports, or questions in seconds — and every chat now tells you exactly how many credits it has consumed, with a friendly warning when a conversation is getting expensive.

Improvements

  • Click the Feedback button next to What's new on any page to open a quick form
  • Pick a category — Feature, Bug, Improve, Question, or Other — so the team can route your note to the right person
  • Optionally attach a PNG, JPEG, WEBP, or GIF screenshot up to 5 MB to give visual context
  • Live character counter and minimum-length helper make sure your message is detailed enough to act on
  • Confirmation toast tells you we received it, and the team is notified by email right away
  • See how many credits each chat has consumed right in the context window popover in the chat header
  • A friendly warning appears when a chat crosses 2,000 credits, explaining that long conversations cost more per message
  • One-click Create new chat button in the warning opens a fresh conversation in the same agent, so you can keep working without losing pace
  • Fixed AI chat tools that search academic databases (Semantic Scholar, ArXiv, PubMed, Google Scholar, ERIC, Europe PMC, OpenAlex, Crossref) failing with an internal error

More Reliable Reading Assistant & Friendlier Chat Navigation

More Reliable Reading Assistant & Friendlier Chat Navigation

Reading Assistant now handles a wider range of PDFs that previously failed during upload, and opening a missing or deleted chat takes you home with a helpful message instead of a broken error screen.

Improvements

  • Reading Assistant accepts PDFs with unusually dense or unsplittable sections that previously caused creation to fail
  • Opening a deleted or unavailable /chat/:id link now redirects home with a clear toast instead of showing an error retry prompt
  • Microphone speech-to-text no longer surfaces noisy error popups for transient network or no-speech events

Conversational Onboarding, Quick Form, & Memory Agent

Conversational Onboarding, Quick Form, & Memory Agent

Onboarding now supports two modes — a friendly guided chat or a quick 3-step form — and a brand-new Memory agent lets you search, add, update, or forget anything ChatAcademia remembers about you across every chat and every other agent.

Improvements

  • Prefer a form? A new Quick form option on /onboarding/form lets you finish setup in three short steps — About You, Institution, Interests — and drop straight into your workspace
  • One-click switch between chat and form from either side, so you can pick whichever style fits you best
  • Tell ChatAcademia about yourself in your own words — or drop in a CV, bio, or research statement and the agent will pull out the key facts for you to confirm
  • New Memory agent at /memory-agent for searching what's saved, adding new facts, updating your role or institution, or forgetting old projects
  • Memory side panel shows a profile snapshot, grouped facts (about you, research focus, projects, preferences), and a list of your saved notes
  • Every agent can now save something to your memory when you ask — "remember that I prefer Vancouver citations" works in any chat
  • Onboarding is free of charge — no credits are spent on the setup conversation
  • Old /memory dashboard is replaced by the richer Memory chat experience
  • Your memory now knows your name and email from the moment you sign up, so every agent can personalise replies from your first chat
  • Branded maintenance page appears across the app during planned downtime, with a 30-second auto-refresh that brings you back online as soon as we're done
  • Mock Peer Review graduates from beta — the agent is now considered stable for everyday use, and the Beta badge has been removed from the sidebar, landing page, and chat header

Branded App Loading Screen

Branded App Loading Screen

A polished loading screen now greets you while ChatAcademia boots up, with a shimmering wordmark, a quiet starfield, and rotating status messages so you always know what's happening.

Improvements

  • ChatAcademia wordmark shimmers as the app hydrates, giving the loader a branded focal point
  • Status messages cycle through what's loading — preparing your workspace, connecting to academic databases, warming up AI agents, syncing your projects
  • Soft static starfield fills the background for a calm, premium feel during cold loads

Clearer File Errors & Better Reading Assistant Retrieval

Clearer File Errors & Better Reading Assistant Retrieval

When a Mendeley, Zotero, Google Drive, or Notes file can't load in your chat, you'll now see a clear notification pointing to the exact source to reconnect. Reading Assistant also pulls more relevant passages from uploaded papers thanks to smarter document structure handling.

Improvements

  • Toast notification appears when an attached file fails to load in a chat
  • Error messages now name the correct source (Mendeley, Zotero, Google Drive, or Notes) instead of always pointing to Google Drive
  • Reading Assistant retrieves more relevant passages from uploaded papers by respecting document structure — sections, lists, tables, and citations stay intact