Zapier’s AI orchestration pricing changes your build math

Zapier’s pricing page now frames the product as AI orchestration plans, and the key detail is that AI steps, code, and SDK all sit on the same task-based pricing model. That matters because Lindy also moved from vague packaging to concrete plans, with a $29.99 per user per month entry point plus an Enterprise tier with SSO, SCIM, audit logs, and HIPAA/BAA. On top of that, Clay added MCP plus Agent plugin CLI/API support, which makes the integration path more explicit. If you are choosing an automation layer this week, the check is simple: does your cost model and integration path still match how your team actually ships agents?

See what changed on Zapier's listing →

What changed on the ground

Changes we detected on each tool's own pages — pricing, features, platform reach — via our daily crawls. Often ahead of any press coverage; each links to the scored listing.

Agenticness Leaderboard

This week's most-clicked tools, re-ranked by rubric score. The score is the editorial signal; the popularity is what drew the directory's traffic here this week.

• Claude Code · 20/36 · Domain Specialist · L3

Claude Code is Anthropic's agentic coding tool that lives in your terminal. It understands your entire codebase, makes multi-file edits, runs commands, manages git workflows, and uses MCP for tool integration. Built with a Unix philosophy — it reads, plans, edits, and verifies in a loop. The fastest-growing product in the coding agent category.

• Cursor · 18/36 · Adaptive Collaborator · L2

Cursor is a developer-focused AI environment that adds agents, context, and automation around your repositories. It combines an editor-like interface, a CLI, and a cloud agent API to automate code review, bug fixing, CI hygiene, and more. Designed for individual developers and engineering teams who want AI to take real actions in their code and infrastructure, not just chat.

• Cline · 18/36 · Adaptive Collaborator · L2

Cline is an AI coding assistant for VS Code that can inspect your project, edit files, run terminal commands, and use a browser while asking for permission at each step. It is aimed at developers working on real codebases who want more than code completion.

• GitHub Copilot · 17/36 · Adaptive Collaborator · L2

GitHub Copilot helps you write, review, and adapt code directly in GitHub, your IDE, and the terminal. It supports everything from inline suggestions to agentic coding workflows with broader model choices and enterprise controls.

• Devin Desktop · 17/36 · Adaptive Collaborator · L2

Devin Desktop (formerly Windsurf, and distinct from Cognition's cloud agent Devin) is an AI-native desktop app for developers. It keeps the full IDE — editor, syntax highlighting, autocomplete, debugging — and adds a command centre for running and coordinating multiple coding agents in one place. Available for Mac, Windows, and Linux.

What operators are searching for this week

A week's demand signal — what operators are typing into the directory's search. Suggestion-chip defaults + off-topic / greetings filtered.

• "best coding agent"
• "AI agent to triage and reply to my email inbox"
• "best coding agent for a large existing codebase"
• "tools to automate customer support ticket triage"
• "AI agent that can browse the web and fill out forms"

Learn: Adaptation: when a step fails, does it re-plan - or just stop?

Adaptation is the agent’s ability to notice a failed step, change course, and try a different path. A tool with weak adaptation follows a script: if one API call errors, one file is missing, or one assumption is wrong, the run ends. A stronger agent keeps going. It can inspect the failure, revise its plan, and pick another action without a human restarting it.

That’s one clean line between a real agent and a chatbot wrapped around fixed steps. To judge it, look for a failure case in the docs or demo. Ask: when a task hits an error, does the system branch into a new plan, or just return an exception and stop?

How our 9-dimension rubric works →

One tool worth testing

Clay — Clay is the one to test if your team builds outbound or enrichment workflows and wants to wire them into coding agents. Today’s site update adds MCP plus an Agent plugin CLI/API path, which turns Clay into more than a no-code workspace. Test it against your current enrichment stack in a 30-minute pilot: can an agent call Clay cleanly, move data through the workflow you already run, and keep the handoff understandable for your team?

Our pick: ChatGPT Deep Research

The use case: research & deep analysis.

Tops our independent /36 — strongest on autonomy and planning, ahead of Gemini Deep Research. Pricing: Subscription (quotas undisclosed).

Ranked by our 9-dimension Agenticness rubric — not by who pays us (nobody does). The full scorecard, true-cost pricing, and the reliability evidence behind every score are in the report.

Read the full report →