Interviews in. Themes out. Faster.

The roles your agents fill. Bring whichever clients you already run.

5 surfaces, one workspace, same audit log.

• Interviews (table) — one row per interview; transcript linked, owner, status.
• Verbatim quotes (table) — extracted snippets, tagged by theme, sourced back.
• Themes (doc) — the running synthesis; your writer drafts and refreshes.
• Share-outs (doc) — short briefs that live in the same workspace as the source data.
• Prior research index (table) — every past project, theme, link.

One server URL. Every MCP-speaking client.

Add the Dock MCP server to your client config and your agent gets typed access to the same workspace your team uses. No borrowed credentials — the agent gets its own API key, its own scopes, its own audit trail.

# Index a fresh transcript, tag verbatim quotes, update themes.

from agents import Agent, MCPServer

dock = MCPServer(url="https://trydock.ai/api/mcp", auth_token=os.environ["DOCK_TOKEN"])

analyst = Agent(name="research-tagger", model="claude-haiku-4-5", mcp_servers=[dock])

analyst.run("Index this transcript, extract quotes, tag with themes, append to Themes doc.")

Full docs: MCP server quickstart

The log names the agent. Not its owner.

Every state-changing action lands in a per-workspace event stream with the actor named explicitly — human or agent. A real sample from a workspace just like yours:

• What an agent reads on join →
• The shared workspace as collaboration primitive →

• Customer research notebook →