September 2026 Summaries

Mintlify announced an analytics-focused agent that can answer natural-language questions about documentation performance, helping teams investigate traffic changes, compare page metrics, identify differences between human and AI-agent behavior, and find unsuccessful search queries. Available through the Mintlify editor’s “Ask agent” panel, the feature supports questions about top user agents, pages disproportionately visited by agents, search gaps, and page-level trends over time. The company says it is also developing additional analytics capabilities, including attribution tools intended to measure how documentation and knowledge sites affect business performance, and invites users to suggest future features through its roadmap.

Mintlify has relaunched its free Starter plan to help teams avoid the long-term maintenance burden of building documentation sites internally. The company argues that modern documentation must support not only human readers but also AI agents, requiring capabilities such as MCP server access, interactive API playgrounds, secure authentication, customization, and optimization for search, answer engines, and generative AI discovery. Mintlify says homegrown documentation platforms often stagnate after launch as engineering resources shift toward the core product, leaving content and infrastructure outdated. The free plan includes a custom domain, web editor, authentication, MCP server, API playground, CSS and JavaScript customization, built-in SEO and GEO optimization, and five editor seats, with no time-limited trial, reflecting the company’s view that teams should focus on their products rather than recreating documentation infrastructure.

Mintlify has introduced Mintlify Desktop, a beta application for Mac, Windows, and Linux that brings its documentation editor into a dedicated desktop environment for managing internal knowledge bases and public documentation. The app supports persistent tabs, horizontal or vertical layouts, separate windows, and independent organization sessions, allowing users to work across multiple projects without repeatedly navigating in a browser. Documentation files can be edited offline and synchronized once connectivity returns, while updated collaboration features provide greater visibility when multiple teammates edit the same page in either visual or Markdown source modes. Mintlify Desktop also uses saved sessions and cached projects to improve launch speed and make new tabs open more quickly, and the company is seeking user feedback as it continues refining the interface, sign-in process, and performance.

Mintlify has introduced Narration for customers on Pro plans and above, allowing readers to listen to supported documentation pages with sentence-by-sentence highlighting and automatic scrolling. Powered by ElevenLabs’ Turbo v2.5 model, the feature streams audio within seconds, supports multiple languages through configured locales or automatic language detection, and offers playback speeds from 0.5× to 2×. Narration is designed for technical material by reading primary page content and providing cues for elements such as steps, tabs, callouts, and accordions, while skipping code blocks, tables, media, and API fields that are less suitable for audio. It can open relevant collapsed sections and switch tabs during playback, supporting users who are multitasking, working in terminals, using mobile devices, or seeking an alternative to on-screen reading. The feature costs 50 AI credits when a new or updated page is first narrated, while replays of the same version are free and failed generations are not charged; it can be enabled through the Mintlify dashboard’s General settings.

Mintlify has added support for WebMCP, a proposed web standard that allows websites to expose typed, structured tools directly to browser agents, reducing reliance on agents interpreting and interacting with visual web interfaces. For Mintlify documentation sites on Pro plans and higher, five tools are automatically available: searching documentation, reading pages as Markdown, viewing a site overview, accessing agent skills, and navigating between pages. These tools aim to let agents complete documentation tasks such as finding SSO configuration guidance through explicit tool calls rather than multiple browser-based actions. No configuration is required from documentation teams, and sites remain unchanged for browsers without WebMCP support. Mintlify plans to refine the tools based on real-world use and expects broader adoption as Chrome plans to enable WebMCP by default in version 157, anticipated in early November 2026.

AI agents are emerging as a distinct audience for company documentation, using structured machine-readable resources such as Markdown pages, llms.txt files, and Model Context Protocol tools rather than browsing like humans. Mintlify’s traffic and survey data indicate that agent and documentation-assistant usage is growing substantially faster than human readership, while controlled tests found that pairing Markdown with an llms.txt navigation map sharply reduced agent 404 errors and token consumption compared with HTML alone. The report argues that documentation quality, structure, and currency increasingly affect product adoption because agents may act on inaccurate information without the skepticism human users apply. Although many teams now use AI agents to draft documentation updates, most retain human review, and organizations continue to struggle with fragmented knowledge spread across documentation, support, community, sales, and product systems. Survey findings suggest few companies have made all knowledge surfaces accessible to agents or assigned clear ownership for doing so, prompting a growing emphasis on “knowledge engineers” and unified knowledge infrastructure that can keep content synchronized, discoverable, and continuously improved for both humans and AI agents.

AI agents are becoming a major audience for company knowledge, accounting for 66% of measured traffic on Mintlify-powered documentation in July 2026, which increases the importance of accurate, structured, and retrievable information. The article argues that organizations need “knowledge engineers” to govern the systems behind internal and external knowledge, reducing risks such as agents retrieving outdated documentation, conflicting policies, or incorrect product information that can spread through automated support, generated code, and workflows. This role combines content strategy, technical infrastructure, and organizational governance by establishing authoritative sources, linking product and support changes to documentation updates, publishing information in agent-accessible formats such as Markdown, llms.txt, APIs, and MCP tools, and monitoring unanswered questions or retrieval failures. While agents require detailed specifications, schemas, and procedures, human readers benefit more from mental models and guidance about choices and trade-offs. A knowledge engineering approach can accelerate updates, expose content gaps through agent behavior, and allow experts to focus on review and higher-value work, but it requires clear accountability for maintaining trustworthy knowledge across the organization.

Mintlify’s 2026 State of Knowledge Report finds that AI agents have become a major audience for company knowledge, generating 257 million requests across Mintlify-powered sites in August 2026 versus 131 million human page loads. The report argues that agents should not be treated like indiscriminate bots because they are typically acting on users’ behalf, with most traffic arriving through machine-readable resources such as Markdown pages, llms.txt files, and agent skills. Controlled navigation tests across 20 documentation sites showed that linking Markdown pages to an llms.txt content map substantially reduced failed requests and token consumption, while documentation-update workflows are increasingly agent-assisted: nearly 367,000 update requests were made through Mintlify between February and August, though humans usually retain publishing oversight. The report also highlights that company knowledge extends beyond formal documentation to support, forums, changelogs, and internal or customer resources, often scattered across teams and tools, leaving many organizations less prepared for agent access than they believe.

Mintlify has introduced fixed, outcome-based pricing for its AI features, replacing token-based charges that varied by run and were difficult for customers to predict. Assistant responses now cost 25 credits only when they successfully answer a question, while documentation automations cost 250 credits only when they make an update; unsuccessful answers and checks that find no needed changes are free. The company estimates that 96% of teams will use the same or fewer credits for the assistant, more than 99% will do so for automations, and automation users may spend about 70% fewer credits because most no-change runs will no longer be charged. Pro and Enterprise plans now also include unlimited editor and Slack agent usage, while existing plans, included credits, prepaid credits, and per-credit prices remain unchanged. The new model applies automatically and is intended to make AI costs predictable by charging for delivered results rather than computational effort.

Mintlify has redesigned its llms.txt generation system to prevent oversized files from overwhelming AI agents with irrelevant documentation, which can increase token costs and slow retrieval. Instead of using a single file capped at 100,000 characters, the new architecture creates a navigation-based hierarchy in which sections such as guides, API references, and integrations are moved into descriptive child files under /_llms/, allowing agents to follow only relevant paths. The generator uses a site’s docs.json navigation structure to identify logical groupings and repeatedly moves the sections that save the most space until each file fits the character limit. In tests across 200 retrieval tasks on ten documentation sites using Claude Sonnet 5 and GPT-5.6 Terra, the hierarchical approach reduced average task completion time by 52.1%, token use by 44.8%, and agent 404 errors by 88.1%. The feature is now available to all Mintlify customers and regenerates automatically whenever documentation is published.