Build Client-Screening AI Agents with Make.com — No Code Required
Make.com has integrated AI agents directly into its automation scenarios — the same visual canvas where you build multi-step workflows. Instead of rigid field-mapping rules, an AI agent step can read unstructured email content, decide whether it's a genuine client request, and route it to the right place. This tutorial builds the full Gmail → AI agent → Trello intake pipeline with no code required.
"AI Agents That Screen Clients and Reply for You" by Kevin Stratvert — Watch on YouTube →
Key Takeaways
- Make.com AI agents are now embedded inside scenarios (not a separate product). Any scenario can include an agent step that makes intelligent decisions between other automation steps.
- The core advantage: agents bridge semantic gaps between apps. Where a traditional automation fails because "Subject: following up on quote" doesn't match a Trello field, an agent understands intent and extracts what's needed.
- Grid view makes the agent's decision process visible — you can see which step ran, what it decided, and adjust the agent's instructions without touching code.
- Workflow: Gmail trigger watches inbox → AI agent reads each email and decides if it's a client project request → approved emails create a Trello card with extracted details → irrelevant emails are ignored.
- A second workflow variant uses a different trigger (not Gmail) for scenarios like form submissions or webhook payloads, showing the pattern generalises beyond email.
- No coding required at any step — the agent's behaviour is controlled by a plain-text instruction field, similar to a system prompt.
Why AI Agents Beat Traditional Automation Rules Here
Traditional automation tools require exact field matches. If you want to route emails about "project quotes" to Trello, you write a filter: subject contains "quote". But real client emails are unpredictable — "hi, saw your work, interested in something similar", "quick question about rates", "I'd like to commission you for a project". None of these would match a keyword rule.
An AI agent step reads the full email body, understands intent, and makes the routing decision the way a human assistant would. It also extracts relevant details (client name, project type, budget mentioned) and populates the Trello card fields without any rigid mapping. The result is a workflow that handles the messy reality of incoming email rather than a sanitised ideal version of it.
Related on OpenClawDatabase
- Hermes Hub — for email automation that runs as a persistent agent rather than a triggered workflow
- OpenClaw Hub — terminal-based agent automation with MCP tool integrations
- AI Agent Glossary — definitions for tool use, agentic workflows, and automation patterns
← Back to News digest · See also: Hermes guide