Profer

Your agents create. Profer carries it forth. Humans respond.

Shareable artifacts for AI agents. Publish HTML, share a URL, collect structured feedback. Works with any MCP client.

Read the Docs →

Agent-Agnostic

Works with Claude Code, Cursor, Gemini, Copilot and any MCP client. Your pigeon flies to every destination.

Structured Feedback

Approve/reject, multiple choice, checkboxes, free text. Not unstructured prose your agent can't parse.

One URL, Anyone

Share anywhere: Slack, email, WhatsApp. No login required. No repo access needed. Just click and review.

Agent writes. Reviewer responds.

Call publish(), share the URL, collect structured feedback. The agent reads it back and acts on it.

agent
html: specHtml,
title: "Auth Migration",
questions: [...]
})
→ response
id: "PF-K8M3N"
url: "profer.dev/v/PF-K8M3N"
publish
▼
▲
feedback
profer.dev/v/PF-K8M3N

Feedback

Which approach?

Do you approve this spec?

Send. Review. Return.

Three operations. That's the entire API.

1

Send

$ publish({ html, title, questions })
→ { id: "PF-K8M3N", url }

Agent generates HTML: specs, reports, proposals. Profer carries it forth, serves it at a URL with a feedback widget.

2

Review

$ profer.dev/v/PF-K8M3N
→ Paste in Slack, email, anywhere

Anyone can open the URL and review. No login, no repo access, no account needed. Just click and respond.

3

Return

$ get({ id: "PF-K8M3N" })
→ { feedback: [...], status: "approved" }

Agent reads structured feedback back. Acts on it. Updates the artifact. The loop closes.

See Recipes →

Built for real workflows

Any time an agent produces something a human needs to see, validate, or decide on.

  • Spec Review — Agent writes a technical spec, stakeholder validates before implementation begins.
  • Client Deliverable — Agent generates a report. PM reviews and approves before sending to client.
  • Cross-Team Input — Get a decision from another team without sharing your codebase.
  • Code Review Without Access — Share changes with a contractor who shouldn't see the repo.
  • Architecture Decision — Agent proposes approach with options. Team reviews async, picks an option.
  • Webhook-Driven Automation — Agent publishes, waits for webhook notification when feedback arrives, auto-continues.
See all recipes →

The missing piece in agent workflows

Other tools trap agent output in conversations or require repo access. Profer carries it forth with structured feedback.

FeatureProferClaude ArtifactsGoogle DocsGitHub Issues
Works with any MCP client✓✗✗✗
Agent can publish natively✓✓✗✗
Shareable URL✓✗✓✓
Structured feedback✓✗✗✗
Agent reads feedback back✓✗✗✗
No login for reviewers✓✗✗✗
Version tracking✓✗✓✓
Webhook notifications✓✗✗✓
No repo access needed✓✓✓✗

Pricing

Pages are distribution. Publishing is always free.

Free

$0

Unlimited pages forever

  • ✓Unlimited pages
  • ✓All question types
  • ✓Public URLs
  • ✓MCP tools
Recommended

Team

$29/mo per workspace

Collaboration features

  • ✓Everything in Free
  • ✓Slack integration
  • ✓Webhooks
  • ✓Analytics
  • ✓Custom branding
  • ✓Multiple API keys

Enterprise

Custom

For large organizations

  • ✓Everything in Team
  • ✓SSO for reviewers
  • ✓Audit trail
  • ✓SLA
  • ✓Dedicated support

Frequently asked questions