---
name: al-680-keep-chatting-with-your-main-agent-while-a-long-research
description: "LangChain's Oct 29, 2026 Managed Deep Agents v0.10 post introduced asynchronous subagents: add async: True on a subagent definition so the orchestrator starts that helper on its own thread and keeps talking with you while the work runs. The agent can check, update or cancel the background task; when the subagent finishes, results arrive mid-run if the orchestrator is busy, or wake an idle agent with a new run, without interrupting a pending human approval. The same release adds browser use with browser_handoff so the agent can work on sites with no API and hand you the window at a login wall so passwords never enter model messages. Product lead Sydney Runkle compared the pattern to a chief of staff who delegates without disappearing. Useful for Slack-based agents that must answer follow-ups while research or multi-step browser work continues. Use when the user wants help with async background subagents (coding) for a small business."
---

# Keep chatting with your main agent while a long research or browser job runs in the background: mark that subagent async so it reports back when finished instead of freezing the conversation

LangChain's Oct 29, 2026 Managed Deep Agents v0.10 post introduced asynchronous subagents: add async: True on a subagent definition so the orchestrator starts that helper on its own thread and keeps talking with you while the work runs. The agent can check, update or cancel the background task; when the subagent finishes, results arrive mid-run if the orchestrator is busy, or wake an idle agent with a new run, without interrupting a pending human approval. The same release adds browser use with browser_handoff so the agent can work on sites with no API and hand you the window at a login wall so passwords never enter model messages. Product lead Sydney Runkle compared the pattern to a chief of staff who delegates without disappearing. Useful for Slack-based agents that must answer follow-ups while research or multi-step browser work continues.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- My product / Slack bot
- Research, multi-page browser task, report build

## Instructions

Do the task below with the user's inputs in place of each [bracket].

Design an orchestrator agent for [my product / Slack bot] that stays responsive while long jobs run. Jobs that should be async: [research, multi-page browser task, report build]. Rules: never block the main chat on those jobs; never put passwords in model context—hand the browser to me at login; escalate if a background job fails twice. 1) List which subagents are sync vs async and why. 2) Draft the subagent definitions (name, description, system prompt, async flag) in plain language I can paste into Managed Deep Agents or recreate in my stack. 3) Write what the main agent says when it starts, checks on, and receives a finished background job. 4) Give a 5-case test plan (user asks a follow-up mid-research; login wall; cancel; approval pending; double failure). Do not deploy anything in this chat.

## Safety checks (share these with the user)

- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: LangChain Managed Deep Agents, ChatGPT, Claude, Slack
- Based on this real-world example: https://www.langchain.com/blog/managed-deep-agents-browser-use-and-asynchronous-subagents
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-680-keep-chatting-with-your-main-agent-while-a-long-research-or/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/