Blog

Agents are the new users. Here's the practical stack (CLI, MCP server, Skills, markdown landing pages, OAuth for agents, and agent-issued tokens with human email verification) that makes a product actually usable by them.

DAU, retention D7, session length — these metrics were built for apps where users tap buttons. Your core loop is a conversation. Here's the analytics framework that actually works for AI-native products.

Model capabilities are commoditizing fast. GPT-5, Claude 4, Gemini Ultra — they're converging on every benchmark that matters. The companies that actually win the AI era will be the ones that build the best agent experience on top of these models. AX is the new moat.

Your agent's task completion rate can be 90% and your users can still quietly hate using it. Here's why resolution and satisfaction diverge in agent products, what the three archetypes of bad completions look like, and how to close the gap before users drift away.

Claude Code ships with regex-based frustration detection, LLM-powered session satisfaction labeling, and a skill improvement loop. Agent builders deploying Claude in their own products have none of this visibility. Here's what Anthropic built — and how to replicate it.

Your error logs are green. Your latency is fine. But your users are quietly losing trust in your AI agent. Here are the 6 failure modes that destroy agent experience without triggering a single alert.

QA scores say your voice AI is performing. Sentiment says callers are happy. A case study running four analytics pipelines on the same calls tells a very different story, and shows what your current metrics are missing.

Task completion rate, path efficiency, trust signals, recovery rate, delegation depth. These are the five metrics that actually tell you whether your AI agent is delivering a good experience, and how to instrument each one in production.

Task completion rate is the first metric every team tracks for AI agents. It's also deeply misleading on its own. Here's what success rate misses, why teams keep optimizing for it anyway, and what to measure instead.

The AX Score is a composite metric that rolls up Task Completion Rate, Path Efficiency, Trust Retention, and Recovery Rate into one number that tells you exactly how your agent is performing in production.

Founders who built apps before AI think in UX terms. That mental model breaks when the interface is an agent taking actions on your behalf. Here's how to make the shift before it costs you.

UX measures how users interact with an interface. AX measures the quality of what an AI agent does on their behalf. They're completely different problems, and almost nobody is tracking the second one.

Most vibe coding platforms are great at acquiring users and terrible at keeping them. Here's the specific product and analytics difference between the ones that build durable retention and the ones that don't.

Time in app is the go-to engagement metric for consumer apps. For AI companions, it's one of the most misleading numbers you can track. Here's what it's hiding and what to measure instead.

The explicit prompts AI companion users send don't tell you what they actually need. Here's how to read between the lines of companion conversations — and what most teams miss entirely.

There's a specific moment in the vibe coding journey where the AI stops being faster than a developer. Most platforms never see it coming. Here's what that inflection point looks like in the conversation data.

The most common behavior pattern in vibe coding platforms isn't 'build and ship' — it's 'start, get stuck, abandon, start again.' Here's what the build-abandon loop looks like in the data and how to break it.

The vibe coding wave brought millions of new builders to AI-assisted development. Most of them don't stick around. Here's the structural retention problem baked into the category, and what the best platforms are doing about it.

Not all code generation is useful. Here's how to measure whether your AI coding assistant is actually accelerating your users' development velocity — or just producing plausible-looking output that doesn't work.

The upgrade moment on vibe coding platforms isn't random. There's a specific conversation pattern that precedes it almost every time. Here's what it looks like, and how to engineer more of it.

Running paywall A/B tests without understanding what led users to the upgrade moment gives you noisy results and wrong conclusions. Here's the conversation data layer that makes paywall testing actually work.

User frustration with AI limits is one of the highest-intent signals you'll ever see. Most products waste it. Here's how to build a pipeline that turns that frustration into paid conversions.

High-activity free users who won't upgrade aren't being held back by price. They're missing something else — and it shows up clearly in their conversations.

Most AI products show upgrade prompts based on usage limits or time. The conversations that actually predict upgrade intent are completely different — and almost nobody is using them.

Activation in AI companion apps isn't a feature click or a setup step. It's a specific emotional moment in a conversation. Here's how to find it, measure it, and engineer it at scale.

Every SaaS product has an activation event. AI-native products have one too, but it's not a feature click or a setup step. It's a conversation. Here's why that changes everything about how you find and optimize it.

When users close your AI product and tell themselves they'll try again later, they usually don't. Here's what that moment looks like in your data, and how to stop it from becoming churn.

A power user and a frustrated user can have the same session count, same average session length, and same return rate. Standard analytics can't tell them apart. Conversation analytics can.

There's a specific combination of conversation signals that reliably predicts churn in AI products, weeks before the user cancels. Here's what it is and how to build an early warning system around it.

Users don't quit AI products suddenly. There's a behavioral pattern in the weeks before they leave — a specific kind of silence. Here's what it looks like and how to catch it early.

When users repeat themselves in a conversation, it's not persistence. It's a failure signal. Here's why message repetition is one of the most predictive churn indicators in any AI product.

Frustration in AI products is real, measurable, and predictive. Here's how to build a Frustration Index from conversation signals — and why it's one of the most useful metrics you're not tracking.

Most AI product churn is invisible. Users don't rage-quit, they quietly drift. Here are the 4 abandonment patterns that kill retention before your funnel ever catches them.

Learn how to build a Conversation Health Dashboard for your AI product: the 5 views you actually need, how to instrument for it, and the weekly review ritual that turns data into better decisions.

Turn count is one of the most-tracked metrics in AI products and one of the most misread. Here's what conversation depth actually tells you — and how to segment it correctly.

30-day retention benchmarks for AI companion products, why standard mobile app benchmarks don't apply, and the conversation patterns that actually predict whether users stick around.

IRR is the single most important metric for any conversational AI product. Here's what it actually measures, three ways to track it in production, and why moving it by 10 points is a revenue decision.

Most teams measure AI chatbot performance wrong. Usage stats and benchmark scores tell you nothing about whether real users are getting what they need. Here's the framework that does.

Your session numbers look great. Your users are churning. Here's why event-based analytics was never built for conversational AI products, and what to do instead.

Anthropic just published evidence of three Chinese AI labs running coordinated campaigns to extract frontier AI capabilities using 24,000 fake accounts and 16 million exchanges. Here's what distillation attacks are, how they work, and why the entire AI industry should care.

WebMCP is a fundamental paradigm shift in how AI agents interact with the web. It's the difference between teaching a robot to recognize a door vs. giving it a doorbell.

Anthropic donates Model Context Protocol, OpenAI contributes AGENTS.md, and Block brings goose to the newly formed Agentic AI Foundation under Linux Foundation mentorship. Here's what this massive governance shift means for developers building the next wave of AI agents.

OpenAI sparked controversy with 'app suggestions' in ChatGPT Plus. Leaked code reveals ad infrastructure, but Sam Altman hit pause. Here's what the financial math and user backlash tell us about ChatGPT's ad future.

Model Context Protocol celebrates its first anniversary with four major spec releases - from basic stdio servers to OAuth 2.1, tasks, and server-side agentic loops. Here's the technical evolution that made MCP the industry standard.

OpenRouter just dropped two frontier models with 1.8M token context windows, excellent tool calling, and they're free during alpha. Here's what actually matters for AI agents.

Stop switching between Claude and the Supabase dashboard. Supabase MCP lets you execute queries, design schemas, and deploy Edge Functions from chat.

Deep dive into SEP-1686 and how the Model Context Protocol now handles hours-long operations without blocking. Learn about task lifecycle, polling patterns, security considerations, and real production use cases from healthcare to multi-agent systems.

Claude generates code with APIs that don't exist. Context7 solves it with 3.8M+ downloads. Here's how.

Comprehensive technical guide to Google's MCP Toolbox for Databases (formerly Gen AI Toolbox). Learn about Model Context Protocol integration, database connectivity, OAuth2 security, OpenTelemetry observability, and production-ready AI agent development with AlloyDB, Cloud SQL, Spanner, and more.

Learn how the upcoming Uber MCP Server will integrate with Claude and ChatGPT. Book rides, check fares, order food delivery - all through conversational AI. Everything you need to know before launch.

A technical deep-dive into why we inherited natural language for agent-to-agent communication, the computational overhead it creates, and the emerging research on direct vector and latent space communication between AI agents.

Learn how to install and use the Zomato MCP Server with your LLMs. Browse restaurants, create orders, and pay with QR codes, all through AI. Complete step-by-step guide with examples.

The best MCP servers for developers in 2025. From file operations to databases.

OpenAI Apps SDK technical guide: Build interactive ChatGPT apps with MCP, React widgets, and the window.openai API. 800M users, zero downloads required.

After spending months perfecting prompts, Skills made most of it obsolete. Here's what actually changed - and what didn't.

Claude Code plugins just launched. Here's how to actually build one that people will use - from structure to team deployment.

Learn how to test and debug Model Context Protocol servers like a pro. From MCP Inspector to mcpjam and automated testing strategies - everything you need to ship reliable MCP servers.

You've built an MCP server. Now what? Learn the exact strategies to increase adoption, reach more developers, and track what's actually working.

Building an MCP server isn't just wrapping endpoints. It's about designing for how models actually think and work.