Think inside your AI world.

Dovetail through Unl

One striking quote in Dovetail can feel like proof. Whether it's a validated pattern or a single loud voice depends on a bar someone has to set before the quote turns up.

Dovetail through Unl reads project insights and research data against the validation bar you have ratified, so 'is this a validated pain point?' comes back not yet validated with the condition it hasn't met.

What Dovetail holds

Dovetail through Unl can genuinely read:

  • Every project in the workspace, and the insights logged against each one.
  • A specific insight's full content, in readable markdown, not just its title.
  • Data entries: the underlying interview or session records an insight draws on.
  • Full-text search across the entire workspace, so a claim can be traced to its source.

What the naked read gives you

Dovetail will surface, accurately, an insight titled 'users abandon the onboarding checklist' with three linked quotes and tags from a research project: real, sourced material, pulled straight from interviews the team actually ran.

The frame judges the data it is given; it does not verify the source’s accuracy.

What changes when Dovetail is read measured

Research ops ratified that a pain point only counts as validated once it's backed by tagged evidence from at least three distinct participants across two or more research projects, because a single project's framing can produce three quotes that all say the same thing for the same local reason.

'Is the onboarding-checklist pain point validated?' returns, measured: not yet validated - the insight has three quotes, but all three come from one project, short of the two-project spread in the ratified rule. Dovetail supplied the insight and data content; your ratified rule supplied the validation bar.

And back again

The next researcher who searches the workspace for onboarding friction finds the same call already attached to the insight, built from the same bar, rather than having to re-count quotes and decide afresh what 'validated' means this time round.

The answer comes back measured against what you already decided, and why.

The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.

Questions people ask

Does the validation verdict change once a second project turns up the same finding?

Yes. Unl re-reads Dovetail's projects and insights on each query, so once a matching insight appears in a second research project, the same pain point clears the two-project bar and returns validated.

How do I connect Dovetail to Claude?

Add Dovetail's own MCP server as a source in Unl, either the hosted endpoint with an API token or a local instance if your client only supports STDIO. Either way, it reads whatever your Dovetail account already has access to.

Can Unl create or edit a Dovetail insight through this connection?

No. Unl's access to Dovetail stops at reading: projects, insights and data content, pulled in to test against your ratified validation bar. Nothing gets created, tagged or edited in your workspace as a result.

What this is

Think inside your AI world — you stay in command

Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.

It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.

Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:

Alpha is invite-only · free at launch.