LoginSign Up
← Back to all sparks
D

Dovetail

ANALYTICS
Velocity6.3

Customer insights platform for analyzing research, feedback, and user interviews

dovetail.com ↗

Dovetail is turning its research repository into an AI analyst that reads, computes, and cites.

ai-chatresearch-repositorymcpcode-executionagentic
◆Current state
Dovetail has shifted its center of gravity from storing research to answering questions over it. The last month is almost entirely about the chat layer: persistent multi-turn context, code execution with inline charts, admin-curated Docs as context, and a new deep research mode. The MCP server is gaining write tools, making the repository operable by outside agents.
◆Where it's heading
The arc points to an analytical agent that works across both qualitative and quantitative data and can be driven programmatically. Each release widens what chat can pull in and what it can do, from running code to sustaining reasoning across turns. Dovetail is positioning the chat surface, not the project, as the primary way users interact with their research.
◆Prediction
Expect deep research mode to gain agentic follow-through that writes results back to Docs, and the MCP write surface to keep expanding toward full repository control from external tools.

◆Recent moves

  1. 6d ago

    Deep research mode in chat

    ⚡ SPARK

    Deep research mode is the clearest signal yet that Dovetail wants chat to handle sustained, multi-step investigation, not just quick lookups, splitting the surface into a fast path and a deeper analytical one.

    View source ↗
  2. 13d ago

    New MCP tools for comments, folders, and tags

    New MCP write tools for comments, folders, and tags extend the pattern of making the repository operable by external agents, not just readable, alongside the recent channel-themes API work.

    View source ↗
  3. 19d ago

    Chat now carries full context across turns

    Carrying full conversation context across turns is foundational plumbing for the deep research direction: follow-ups now build on prior reasoning and citations instead of starting cold.

    View source ↗
  4. 24d ago

    Run code and generate charts in chat

    Running code to answer quantitative questions and rendering inline charts stretches chat from qualitative summarization into actual analysis, an important widening of what the research surface can do.

    View source ↗
  5. 24d ago

    Workspace Docs can now be used for AI context

    Letting admins inject workspace Docs into the chat context window broadens what answers can draw on beyond raw data points, tightening the link between curated knowledge and AI responses.

    View source ↗
  6. 24d ago

    Customizable home

    Admin-configurable Home sections are a workspace personalization touch with no bearing on the AI direction, useful housekeeping rather than a capability change.

    View source ↗