See how it can help you

Ask your agent what it could do with what your team knows.

Connect an agent to your nest and paste one prompt. In a few minutes you have a map of what it can do for you today, what's missing, and which agents to run.
See how it can help you

Here's what that looks like.

Point your agent at a nest and paste one prompt. It proves it can read your knowledge, gets oriented, and maps what it can do for you today, what's missing, and which agents you should run. Then it saves the map as a draft for you to approve.

Claude Code · a fictional support team's nest
Example
  1. 1. Prove it
  2. 2. Get oriented
  3. 3. Map it
  4. 4. Save as a draft
  1. 1

    Connect Claude Code to your nest

    Add the ContextNest plugin for a nest on your machine, or use the Connect button in a hosted nest. Claude Code works best, because the agent can reach the nest directly.

  2. 2

    Paste the prompt

    If the agent can't read real documents, it says so and stops. It never pretends.

  3. 3

    Approve the map

    The map lands in your nest as a draft. Nothing is published until you say so.

In Claude Code
$ /plugin marketplace add promptowl/contextnest
Then
$ /plugin install contextnest
The prompt
You're connected to my ContextNest nest. Before anything else, prove it: search the nest, open two or three documents, and tell me their titles and one line from each. If you can't read real documents, say so and stop. Don't guess what's in the nest.

Use search and single-document reads. If one way of reaching the nest fails, try the other tools you have (the ContextNest MCP tools, the ctx command line or the REST API) before you give up.

If the nest is empty or nearly empty, ask me three questions first: what my team does, which questions people ask us most, and which documents we'd trust an agent to answer from. Then work from my answers.

Then build me an opportunity map:
1. Five things you can do for me today with what's in the nest. For each one, name the documents it relies on.
2. What's missing: the documents or decisions that would let you do three more things, and who on my team probably owns each one.
3. The agents you'd run on this nest: what each one does, and what each one should not be allowed to see.

Save the map back to the nest as a draft titled "How AI can help us: opportunity map". Don't publish it or share it anywhere. Ask me before you publish anything.
Built to be safe to try

The agent proves what it read, and you approve what it wrote.

It proves the connection first

The prompt makes the agent open real documents and quote them before it says anything else. If it can't, it tells you and stops.

An empty nest gets questions

With nothing to read, the agent asks what your team does and what people ask most, and works from your answers.

The map is saved as a draft

The map is saved to your nest as a draft. An owner approves it before anyone, or any agent, treats it as settled.

Start with your team

Each team starts from its own knowledge.

For engineering teams

Every coding agent your team runs, working from the same standards.

Start here →For sales and revenue teams

Every rep's AI quotes the price you approved this quarter.

Start here →For marketing teams

Every content agent writes in your voice, with claims you can stand behind.

Start here →For leadership and operations

Every team's AI works from what leadership actually decided.

Start here →For research and analyst teams

Every analyst's AI follows your method and cites your sources.

Start here →For agencies and consultancies

Run your firm on AI. Then bring it to your clients.

Start here →For one person, to start

Your own governed context, for every AI you use.

Start here →

Start with what your team already knows.

Free to start. Connect the AI tools your team already uses, and see what they could do with approved knowledge.

Get PromptOwl freeGet a demo