Les Agents IA débarquent sur Make : une révolution est lancée !

Les Agents IA débarquent sur Make : une révolution est lancée !

by Shubham SHARMA

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQMMachine learning
🎙 Shubham SHARMA 👥 313K 📅 April 14, 2025 ⏱ 18 min 👁 64K 📄 tutorial 🧭 2026-08-24
Available in: English (current) Français

Keywords

MakeAI agentsautomationno-codeworkflow

Summary

The video presents Make’s new AI agent feature, announced on the day of recording. The creator, Shubham Sharma, shares his experience after testing the feature for a month. He explains the shift from deterministic automation to agent-based automation where agents can make decisions and use tools. The tutorial covers creating an agent, connecting it to Slack, and adding tools like Airtable. A detailed example shows building a customer support agent that analyzes tickets, updates Notion, and sends SMS or emails based on priority. Other use cases include inventory management, email handling, and YouTube comment analysis. The creator emphasizes the importance of well-crafted prompts and suggests using Anthropic’s Workbench for prompt iteration. He advises starting from business needs rather than gadgets. The video concludes with a three-level vision of automation evolution, placing current capabilities at level two.

136 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides valuable, actionable information for users of Make, demonstrating concrete implementations of AI agents. The argumentation is solid, based on the creator’s direct experience and clear explanations of concepts like prompts and tools. The examples are practical and cover various business scenarios, making the content highly relevant for entrepreneurs and no-code developers. The creator also shares best practices, such as thinking on paper and starting from needs, which adds practical value.

Scientific Rigor, Source Quality, Title Accuracy

The video is a tutorial based on the creator’s personal experience and early access to Make’s AI agents. It does not cite external sources or provide verifiable references. The title accurately reflects the content, as the video indeed introduces and demonstrates the new feature. The description includes links to the creator’s own resources and a promotional link for a free month of Make Pro, but these are not scientific sources. The lack of external validation is a limitation, but the content is presented as a hands-on guide rather than a scientific study.

180 words

Title / Content Match

The title accurately reflects the content: the video introduces Make's AI agents and demonstrates their use, matching the promise of a 'revolution' in automation.

Quality & Reliability

7/10

The video is a hands-on tutorial by a practitioner with early access to Make's AI agents. It demonstrates real configurations and provides practical advice, but lacks external sources or verification of claims. The content is based on personal experience and may become outdated quickly.

Chapters

Cited Sources

Concurring Sources

  • Make.com official documentation — Official documentation for Make, which includes information on AI agents.

Dissenting Sources

  • n8n community discussions — Some comments mention n8n as an alternative, suggesting that Make's AI agents may not be unique or superior.

Contribution & Novelties

The video provides an early, hands-on look at Make’s AI agents, offering practical examples and configuration steps. It highlights the paradigm shift from rule-based automation to agent-driven workflows, which is a significant conceptual update for Make users. The creator’s emphasis on using Anthropic’s Workbench for prompt engineering is a useful tip. The video also outlines a three-level evolution of automation, placing current capabilities in perspective.

Pour aller plus loin :

  • Anthropic Workbench — Official tool for prompt engineering, mentioned in the video.
  • Make.com — Official website of the platform, where the AI agent feature is available.
  • AI agent concept — Wikipedia article on intelligent agents, providing background on the concept.

110 words

Radar Profile

The radar profile shows high scores in information quantity and technical level, reflecting the detailed tutorial nature. Quality and reliability are moderate, consistent with the lack of external sources. The overall balance indicates a useful but not deeply verified content.

Reliability 6/10

💬 Très positif. Sur les 30 commentaires analysés, la majorité exprime enthousiasme et gratitude pour la démonstration, avec quelques interrogations sur les coûts et la comparaison avec n8n.