Back to Home11/18/2025, 4:17:35 PM

Real-time interactive words in chat(open source – MIT)

ronitelman
1 points
1 comments

Mood

supportive

Sentiment

positive

Category

tech

Key topics

open-source

javascript

UX

NLP

The author released an open-source JS library for real-time interactive words in chat, which can be used to handle various UX heuristics, and is sharing it with the community.

Snapshot generated from the HN discussion

Discussion Activity

Light discussion

First comment

N/A

Peak period

2

Hour 1

Avg / period

2

Comment distribution2 data points

Based on 2 loaded comments

Key moments

  1. 01Story posted

    11/18/2025, 4:17:35 PM

    5h ago

    Step 01
  2. 02First comment

    11/18/2025, 4:17:35 PM

    0s after posting

    Step 02
  3. 03Peak activity

    2 comments in Hour 1

    Hottest window of the conversation

    Step 03
  4. 04Latest activity

    11/18/2025, 4:45:33 PM

    5h ago

    Step 04

Generating AI Summary...

Analyzing up to 500 comments to identify key contributors and discussion patterns

Discussion (1 comments)
Showing 2 comments
ronitelman
5h ago
Adds a sensor to textareas so that certain phrases get triggered and call events: blocking submission (for PII for example), calling an API (to get a list from a db rather than asking an LLM to do so), or quick lists (for personal preferences).

The goal is disambiguation directly in the query before sending queries to an LLM.

ronitelman
5h ago
Hello, I release an open source (MIT license) js library that auto-detects trigger phrases, and offers a simple JSON programmatic way to handle various UX heuristics. For example, if you need data that's 100% deterministic, you can do that with a trigger word, rather than asking AI to convert your text to SQL. Or, if you want definitions of ambiguous words to be flagged, you can do that and ask clarifying questions.

I have many other open source tools coming up that will work with the front-end library, called trustquery-browser, that are meant to maximize query input quality and flag issues in LLM responses.

Happy to meet anyone 1:1 over video to help them try it out and would love any feedback, thanks!

View full discussion on Hacker News
ID: 45968217Type: storyLast synced: 11/18/2025, 4:20:40 PM

Want the full context?

Jump to the original sources

Read the primary article or dive into the live Hacker News thread when you're ready.

Read ArticleView on HN