Make Review August 2026: Maia Builds Your Scenarios, Gemini 3.7 Flash Lands, and Whether the 4.5 Holds
Make added Maia, a natural-language co-worker that builds scenarios in the Scenario Builder, and Gemini 3.7 Flash just landed in its AI modules. Updated rating, current pricing, the cycles-per-run change coming October 1, and the per-persona pick vs n8n.
- ✓Maia builds and edits scenarios from plain-text prompts inside the Scenario Builder, on every paid plan, so a non-developer can describe a workflow and get a working draft to iterate on
- ✓Paid plans get Maia's first 70 messages free for 30 days before credits start, which is a real runway to decide whether it earns its keep
- ✕Maia cannot read the execution log from a past run or see any scenario but the one open in front of it, so it can't debug a production failure from its log or build from an existing scenario
- ✕Each Maia reply burns credits after the promo window, and the docs show single messages costing 140 to 160 credits, so heavy use draws down the same pool your scenarios run on
Make holds at 4.5 in August 2026. Maia is a genuine building and iteration aid on every paid plan, and Gemini 3.7 Flash adds a cheaper, faster model to the AI modules, but Maia's inability to read past execution logs caps its value for the exact production-debugging work an ops lead needs most, and the two structural cons (no self-hosting, credit fan-out at volume) are unchanged. For a solo non-developer operator, Make is still the pick, and Maia makes the first build faster. For a mixed-technical ops team that needs managed spend caps and custom access roles without running a server, Make edges n8n. For a fully technical team that can run Docker at volume, n8n still wins on cost, because self-hosting deletes the per-credit meter and nothing in August changes that.