The Agentability Blog

Field notes and data from auditing how agent-ready the web is — what AI agents can and cannot operate, and what to fix.

20 article(s)
Agentability Snapshot

Where Zoho CRM Stands in the Race to Agent-Ready Software

Zoho CRM lands in the middle tier of agentability performance across 100 audited SaaS products, reflecting industry-wide challenges in transparency and shadow-UI patterns that limit AI agent integration.

Agentability Spotlight

Mixpanel and the Agent-Readiness Gap: What 100 SaaS Homepages Reveal About Transparency

Mixpanel joins 83% of leading SaaS products scoring zero on transparency for AI agents. A deep look at what the data reveals about the current state of agent-ready software design.

Agentability Spotlight

PagerDuty and the Agentability Challenge: What 100 SaaS Products Reveal About AI-Readiness

New research measuring how well 100 leading SaaS products support AI agent operation reveals systemic design gaps. PagerDuty and its peers face a common challenge: building software that humans and autonomous systems can both operate effectively.

Agentability Spotlight

ClickUp Scores 42/100 for AI Agent Readiness—What Product Teams Can Learn

ClickUp falls into the middle tier of agentability among the top 100 SaaS products, exemplifying the industry-wide gap between machine readability and true agent-first design.

Agentability Analysis

LastPass and the Password Manager Paradox: Why Security Tools Struggle With Agent Readability

Password managers like LastPass promise seamless credential access, but their agentability scores reveal fundamental tensions between security design and AI agent operation. New data from 100 SaaS products shows where the category—and the industry—falls short.

Refresh Spotlight

Gong Earns 49/100 Agentability Score as Conversation Intelligence Platforms Face Agent Integration Challenges

Gong's homepage scores above the SaaS industry average for AI agent compatibility, but shares common weaknesses in transparency and shadow-UI patterns that affect 80% of major platforms.

Agentability Spotlight

Expensify and the Agent Automation Gap: What 100 SaaS Products Reveal About API-First Design

New research measuring how well AI agents can operate software reveals systemic blind spots across enterprise SaaS. Expensify's audit illuminates where the industry stands on machine readability, transparency, and the eight principles that determine whether products are ready for autonomous operation.

Agent Factor Engineering

GitLab and the Agentability Blind Spot: Why Most SaaS Products Fail Transparency and Shadow-UI Tests

An audit of 100 leading SaaS products reveals systemic design failures that block AI agent access. GitLab's agentability profile illuminates widespread issues with transparency and shadow-UI patterns that most product teams haven't begun to address.

Agentability Audit

n8n and the Agentability Gap: What 100 SaaS Products Reveal About AI Agent Readiness

A systematic audit of the top 100 SaaS products shows an average agentability score of just 38.3 out of 100, with workflow automation platform n8n among those measured. Two critical weaknesses—transparency and shadow-UI avoidance—are holding nearly the entire industry back.

Agentability Analysis

Dropbox Scores 42/100 for AI Agent Usability: A Case Study in Shadow-UI Overuse

The popular file-sharing platform sits squarely in the middle of the Agentability Index with strong machine readability but critical weaknesses in transparency and shadow-UI that limit agent effectiveness.

Agentability Research

Google Analytics and the Agentability Gap: What 100 SaaS Audits Reveal About AI-Ready Interfaces

New data from 100 leading SaaS products shows analytics platforms and their peers struggling with basic agent-readiness principles. Only 22% qualify as Agent-Ready, while transparency and shadow-UI patterns remain widespread barriers.

Index Spotlight

FreshBooks and the Agentability Gap in Modern SaaS

Our audit of 100 leading SaaS products reveals systemic barriers to AI agent operation. FreshBooks exemplifies both the industry's challenges and the path forward.

Agentability Analysis

DocuSign and the Agentability Gap: Why Most SaaS Products Struggle With AI Agent Access

DocuSign exemplifies a widespread challenge across enterprise SaaS: products built for human users aren't ready for AI agents. New data from 100 leading platforms reveals the specific barriers blocking automated workflows.

Index Spotlight

WordPress.com's Agentability Challenge: What the Data Reveals About AI Agent Access

WordPress.com scores 43/100 for agentability, placing it in the Developing tier. Like most SaaS platforms, it faces critical challenges in transparency and shadow-UI avoidance that limit AI agent effectiveness.

Index Spotlight

Freshworks and the Agentability Gap: What 100 SaaS Homepages Reveal About AI-Ready Design

An audit of the top 100 SaaS products shows most aren't ready for AI agents. Freshworks and its peers face a common challenge: making software navigable by machines, not just humans.

Agent Factors Engineering

The clean handoffs gap: what most top SaaS products get wrong for AI agents

Clean handoffs—how well software returns control to AI agents—averages just 40/100 across the top 100 SaaS homepages. One in five products scores below 20, creating a critical barrier to agent-driven workflows.

Agent Factors Engineering

The sensible defaults gap: what most top SaaS products get wrong for AI agents

Across the top 100 SaaS homepages, sensible defaults averages just 35 out of 100, with nearly a quarter of products scoring under 20. This gap represents a critical barrier to AI agent operability that product teams can systematically address.

Agent Factors Engineering

The shadow-UI avoidance gap: what most top SaaS products get wrong for AI agents

80 of the top 100 SaaS products score under 20/100 on shadow-UI avoidance, creating a critical barrier for AI agent interaction. Product teams need concrete strategies to close this gap.

Agent Factors Engineering

The transparency gap: what most top SaaS products get wrong for AI agents

An analysis of 100 leading SaaS homepages reveals that transparency—the principle enabling AI agents to understand what actions are possible—scores just 5 out of 100 on average. This gap represents a fundamental oversight in how products communicate their capabilities to autonomous systems.

Agentability Research

Machine-readable, but not agent-ready: what 100 SaaS audits reveal

The top 100 SaaS products have mastered machine readability but score near zero on the agent-era principles that enable verification and action. A new audit reveals the invisible gap between readable interfaces and truly agentic software.