RXed AI News

Your AI intelligence briefing
SCORE 6.2/1017/20 elements Audited 2026-07-05 · RXed table v1.0

Make (formerly Integromat)

The friendliest way to put AI agents to work across 3,500+ apps — as long as you watch the credit meter and don't need self-hosting or real evals.

SMB toolAutomation & AgentsProductivityFreemium
Vendor
Make (Celonis, Inc.) · www.make.com
Origin
CZ — Prague
Pricing
Free (1,000 credits/mo) · Core ~€12 · Pro ~€21 · Teams ~€38 per month for 10k credits (annual billing, USD list) · Enterprise custom. Native AI features (agents, AI toolkit) burn extra credits per action.
Users (official only)
400,000+ organizations (homepage claim); 3.1M registered users per official 2024 wrap-up (source, 2026-06)

Element scores

Reactive
Retrieval & Memory
Orchestration
Validation
Models
Primitives
Pr7
Prompts
Em6
Embeddings
Cx6.5
Context
Tr6.5
Tracing
Lg7.5
LLM
Compositions
Fc8.5
Function calling
Vx5.5
Vector store
Rg6.5
RAG
Gr4.5
Guardrails
Mm6
Multimodal
Deployment
Ag7.5
Agents
Ft
Fine-tuning
Fw7.5
Frameworks & harnesses
Ev2
Evaluations
Sm6
Small models
Emerging
Ma4.5
Multi-agent
Sy
Synthetic data
Pc7.5
Protocols
In
Interpretability
Th6.5
Thinking models
Tap or hover any element to see why it got that score.

Strengths

The widest no-code tool surface in the category: AI agents that call any of 3,521 app modules plus external MCP tools in one reasoning loop, a mature visual harness (routers, iterators, error handlers, subscenarios), fast frontier-model onboarding, and a native Knowledge RAG store. Make Grid adds fleet-level visibility for teams running dozens of automations, and agents are available on every plan including Free.

Honest dings

Credits burn fast on multi-step and AI-heavy workflows (native AI actions cost multiple credits; Code app is 2 credits/second), audit logs are locked behind Enterprise and log retention is ~30 days below it, there is no evaluation surface for AI outputs at all, no self-hosting, and multi-agent coordination is chaining, not primitives. The August 2025 operations→credits switch left recurring pricing-opacity complaints in reviews.

Best for: SMB and mid-market ops teams that want trustworthy AI agents acting across their existing SaaS stack with zero code and zero infrastructure — and are willing to pay per step for it.

Sources

Every audit lists the research it rests on — transparency and traceability are the product. Tools evolve: each audit is a snapshot of its audit date, and re-audits supersede older versions (kept below for reference).