DeepSeek Harness + Lark
Lark is the conversation entry point; DeepSeek Harness is the agent that runs the work. Test DeepSeek Harness with DeepSeek V4 Pro below, then connect Lark and choose this agent in channel settings.
How the combination works
DeepSeek Harness does the work. Lark carries the conversation.
DeepSeek Harness runs coding work through a persistent shell and repository workspace while the selected model supplies reasoning and generation.
Connect your organization once. Everyone shares the workspace; each conversation can continue a task or start a new one.
DeepSeek Harness
Owns the work loop, model calls, files, cloud computer, enabled tools, and the result returned to the conversation.
Lark
Lets people reach the selected AgentSky agent from Lark. It does not grant access to repositories or other applications mentioned in a message.
AgentSky
Owns the selected responder, channel binding, task state, model and runtime usage, and the separate permissions for tools and connectors.
Setup and first task
Connect DeepSeek Harness to the Lark conversation you intend to use.
The Composer tests the exact agent in the browser. Channel setup remains a separate account or workspace authorization, so neither step can silently stand in for the other.
Test DeepSeek Harness in the Composer
The Composer above selects DeepSeek Harness and its current recommended model, DeepSeek V4 Pro. Use a small task with an answer you can inspect before connecting a shared channel.
Connect Lark and choose DeepSeek Harness
In Channels, choose Lark. Register your organization’s bot and publish it. Send the temporary connection code to your bot, in a direct chat or group.
Verify the real channel path
Send a small task and check the reply in Lark. Use /new for a separate session. Check that the reply arrives in the intended Lark conversation and that the dashboard still names DeepSeek Harness as the responder.
Access, cost and limits
What DeepSeek Harness + Lark establishes
Cost-conscious coding and shell work where DeepSeek-compatible models and explicit verification fit the task.
Configure and verify
- DeepSeek Harness and DeepSeek V4 Pro are preselected for the browser evaluation.
- Lark is connected or paired to the intended account, workspace, server, device or conversation.
- The first real message reaches the selected agent and returns a useful reply through the same channel.
Do not assume
- A browser task does not automatically bind Lark; finish the channel setup separately.
- Lark membership does not authorize repositories, email, documents or other application data.
- Model tokens and active computer time are billed separately from any channel or provider plan.
Common questions
Related resources
DeepSeek Harness
Review DeepSeek Harness's supported models, capabilities and browser Composer.
Lark channel
Review the channel-specific authorization, pairing and troubleshooting guide.
DeepSeek Harness + DeepSeek V4 Pro
Review the current default agent and model combination.
Pricing
Review model, active-computer, tool and connector charges.