eve Sanity Copilot

Sanity Copilot eve Template

A Slack-based Sanity copilot built on eve. Team members @mention it in Slack and it manages their Sanity project: querying and editing content with GROQ, inspecting and shaping schemas, creating and editing drafts, managing releases, and drafting content pieces into Notion. Long-form drafts are shared as Notion pages.

• Lives in Slack. Answers @mentions and DMs, replies in threads, and renders approvals as buttons.
• Works on your Sanity project. Each user signs in to Sanity through Vercel Connect, so queries and edits run as the real person with their own permissions, and destructive operations (patching, publishing, deploying schemas) pause for approval before they run.
• Drafts in Notion. Long-form pieces are created as Notion pages through the same user-scoped OAuth flow, with page updates and moves gated on approval.
• Stores files in Vercel Blob. Export drafts, save images and attachments, and read them back, authenticated by the project's OIDC token.

Deploy

Deploying with the button provisions everything the agent needs and wires it up for you:

• a Slack connector (sets SLACK_CONNECTOR, with the event trigger pointed at /eve/v1/slack),
• a Sanity connector (sets SANITY_CONNECTOR),
• a Notion connector (sets NOTION_CONNECTOR),
• a Vercel Blob store for the asset tools.

Once deployed, @mention the bot in your Slack workspace to start working on your Sanity project.

Tech stack

Zero static keys. Authentication runs entirely on Vercel Connect (Slack, Sanity, and Notion) and Vercel OIDC (Vercel Blob and AI Gateway). There are no API keys or client secrets to manage in code or .env files: Sanity and Notion are authorized per user in the browser, and Blob and the model authenticate with the project's OIDC token.

Quick start with an AI coding agent

If you're working with an AI coding agent like Claude Code or Cursor, you can use this prompt to have it help you with building your agent:

1
I want to build a Slack agent with the eve framework, using the Sanity copilot template. Read the setup instructions at https://agent-resources.dev/sanity-copilot-eve-template.md and follow them. They will cover deploying the template, building with eve, how everything works overall, and more.

What's inside

1
agent/
2
  agent.ts                  # model configuration, compaction, session token limits
3
  instructions.md           # the agent's behavior
4
  channels/
5
    slack.ts                # Slack surface (Vercel Connect credentials)
6
    eve.ts                  # dev TUI surface for local development
7
  connections/
8
    sanity.ts               # Sanity MCP, user-scoped OAuth; destructive tools require approval
9
    notion.ts               # Notion MCP, user-scoped OAuth; page updates/moves require approval
10
  sandbox.ts                # Vercel Sandbox backend
11
  subagents/
12
    researcher/             # fresh-context web researcher (own session, web tools only)
13
    reviewer/               # fresh-context draft reviewer (own session)
14
      skills/writing-quality/  # its own copy of the writing-quality rubric
15
      sandbox.ts            # its own sandbox backend
16
  tools/
17
    upload_asset.ts         # Vercel Blob: store text or binary content
18
    list_assets.ts          # Vercel Blob: browse stored assets
19
    get_asset_info.ts       # Vercel Blob: metadata without downloading
20
    download_asset.ts       # Vercel Blob: read a stored file back
21
    delete_asset.ts         # Vercel Blob: delete (requires approval)
22
    get_user_preferences.ts   # load this user's saved preferences
23
    save_user_preferences.ts  # save standing preferences (per-user, principal-scoped)
24
    clear_user_preferences.ts # clear this user's preferences (requires approval)
25
  lib/
26
    user-preferences.ts     # principal-scoped Blob key + reserved-prefix guard
27
  skills/
28
    sanity-best-practices/              # schemas, GROQ, releases, framework integrations
29
    content-modeling-best-practices/    # designing and refactoring content types
30
    portable-text-conversion/           # converting rich text into Portable Text
31
    portable-text-serialization/        # rendering Portable Text out to other formats
32
    seo-aeo-best-practices/             # metadata, structured data, AI-answer readiness
33
    content-experimentation-best-practices/  # A/B tests and variants
34
    writing-quality/                    # prose rules for anything written for humans

All of the skills except writing-quality come from Sanity's Agent Toolkit; the sanity-best-practices references are also the canonical content behind the Sanity MCP server's rules tools.

Pairing with the content agent template

The eve content agent template is a full content assistant: per-surface style skills (blog, LinkedIn, X, release notes, newsletters), a house voice, and a style lint. Instead of merging all of that into this copilot, you can deploy it as its own agent and let the copilot delegate to it through eve's remote agents feature.

1. Deploy the content agent template as its own Vercel project.
2. Add a remote subagent file to this repo. The filename is the tool name, and vercelOidc() handles deployment-to-deployment auth with no shared secret:

1
// agent/subagents/content_writer.ts
2
import { defineRemoteAgent } from "eve";
3
import { vercelOidc } from "eve/agents/auth";
4

5
export default defineRemoteAgent({
6
  url: () => process.env.CONTENT_AGENT_URL ?? "https://your-content-agent.vercel.app",
7
  description:
8
    "Drafts blog posts, LinkedIn and X posts, release notes, and newsletters in the house voice. " +
9
    "Pass the surface, the source material, and any constraints in the message.",
10
  auth: vercelOidc(),
11
});

1. Set CONTENT_AGENT_URL in this project's environment and mention the new subagent in agent/instructions.md so the copilot knows when to hand off.

The remote agent runs in its own deployment with its own skills and connections, and it never sees this copilot's conversation history, so the copilot packs everything the writer needs into the call message. The result comes back as a normal tool result, the same shape as the local researcher and reviewer subagents.

Local development

Link the project you deployed (or a fresh one) and pull its environment:

1
vercel link
2
vercel env pull

Then run the development server and link a model provider with /model in the TUI:

1
pnpm dev

You can chat with the agent directly in the dev TUI to test the Sanity, Notion, and Blob flows. The Slack surface itself only runs against a deployment. Ship changes with:

1
eve deploy

Linting and formatting

This project uses Ultracite (a Biome preset) for linting and formatting:

1
pnpm check      # check formatting and lint rules
2
pnpm fix        # auto-fix what is fixable
3
pnpm validate   # lint + typecheck + eve discovery diagnostics

Setting up the connectors by hand

The Deploy button provisions these for you. To set them up manually (for a project you didn't create with the button), use the Vercel CLI:

1
# Sanity connector (note the printed UID, e.g. sanity/<name> -> SANITY_CONNECTOR)
2
vercel connect create mcp.sanity.io --name sanity
3

4
# Notion connector (note the printed UID, e.g. notion/<name> -> NOTION_CONNECTOR)
5
vercel connect create mcp.notion.com --name notion
6

7
# Slack connector (note the UID, e.g. slack/<name> -> SLACK_CONNECTOR), then point its
8
# event trigger at the route the agent serves
9
vercel connect create slack --name <name> --triggers
10
vercel connect attach slack/<name> --triggers --trigger-path /eve/v1/slack
11

12
# Blob store, connected to the project for all environments
13
vercel blob create-store <name> --access public --yes

Customizing

• Behavior: edit agent/instructions.md. It describes the whole workflow: load the right skill first, ground work in the real project with GROQ and schema reads, work in drafts and publish only on approval, draft long pieces into Notion, and get a fresh-eyes review before proposing a draft.
• Approval gates: edit the APPROVAL_REQUIRED_TOOLS lists in agent/connections/sanity.ts and agent/connections/notion.ts to change which MCP tools pause for a human decision.
• Skills: edit or add skills in agent/skills/. Each folder holds a SKILL.md plus its reference files. The reviewer subagent keeps its own copy of writing-quality under agent/subagents/reviewer/skills/.
• Model: edit agent/agent.ts (or run /model in the dev TUI).
• Tools: add or change tools in agent/tools/. The filename is the tool name.

The agent auto-updates as you edit these files.

Learn more

• eve documentation: the framework powering this agent.
• Vercel Connect: manages the Slack, Sanity, and Notion credentials.
• Sanity documentation: the CMS the copilot manages.
• Sanity Agent Toolkit: the source of every skill here except writing-quality.
• Vercel Blob: object storage for the asset tools.

Related templates

• eve Content Agent
• eve Personal Agent