We Built 270 Realistic Chats So Agents Don't Freeze While Tools Run
Postedabout 2 months ago
huggingface.coTechstory
calmpositive
Debate
0/100
AI DevelopmentConversational AIDataset Creation
Key topics
AI Development
Conversational AI
Dataset Creation
The creators of AsyncTool developed a dataset of 270 realistic conversations to improve AI's ability to continue interacting while running background tools, addressing a common issue in conversational AI.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
N/A
Peak period
1
Start
Avg / period
1
Key moments
- 01Story posted
Nov 10, 2025 at 4:30 PM EST
about 2 months ago
Step 01 - 02First comment
Nov 10, 2025 at 4:30 PM EST
0s after posting
Step 02 - 03Peak activity
1 comments in Start
Hottest window of the conversation
Step 03 - 04Latest activity
Nov 10, 2025 at 4:30 PM EST
about 2 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45881203Type: storyLast synced: 11/17/2025, 5:59:57 AM
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.
AsyncTool is a Hugging Face dataset of 270 high‑quality, multi‑turn (and I mean up to 60 turns) conversations where the assistant keeps talking while tools work in the background. Each case is different, grounded in real JSON‑Schema tool definitions, and the tool calls/results are consistent and make sense with no fabricated states or magical shortcuts.
What’s inside - 18 scenario templates × 15 renders = 270 conversations. - Conversations run 10–30 “in‑world” minutes with filler chat, retries, status checks, and out‑of‑order returns. - Every row includes messages, tools, and meta so you can replay transcripts, inspect schemas, and trace provenance. - Protocol features: <tool_ack /> placeholders, -FINAL handoffs, mixed sync/async chains, transient failures, and fatal‑error surfacing. - License: Apache‑2.0.
We’re exploring how agents can ack now, answer later - waiting for the right signal (last relevant tool result vs. last user question) while staying natural and helpful. This dataset gives you supervised signals to: - finetune assistants that acknowledge async work without hallucinating tool states, - build guardrails/regression tests for routers juggling retries and reordered responses, - evaluate “answered at the right time” behavior.
We’re also publishing the generator so you can reproduce or extend everything locally. If you’re building tool‑using agents - or just tired of UIs that freeze—this should help you train, test, and iterate faster.
Built with Torque → https://usetorque.dev/