# Verb

> An AI agent that companies embed inside their own SaaS product, so their
> users can ask for an outcome and get it. The part that is hard to build, and
> the reason to buy rather than build: every action runs with the asking user's
> own access rather than a service account, anything that writes stops for a
> confirmation showing the real arguments, and every action is logged against a
> named person. That is what an in-house build usually lacks when it stalls in
> security review.

Site: https://askverb.com
Status: live since 2026-09-30, open to anyone. Free while Verb launches, live site included.

## What it is

Verb is embedded in a customer's web product with one script tag. The customer
describes their product's capabilities in a plain-markdown file called verb.md,
one section per tool, declaring whether each tool reads or writes. The assistant
can call those tools and nothing else.

Tools execute in the end user's own browser against the customer's own API,
carrying the credential that user already holds. Verb never holds a wider key,
so the customer's existing authorisation is unchanged.

## Who it is for

Product and engineering teams at B2B SaaS companies whose users have to be
walked through the product. It is not a website support chatbot and it is not a
documentation search box. The typical buyer has already decided they want an
in-app agent, and is weighing building one against the months of identity,
approval and audit work that follow the first working demo.

## How it is added

1. Paste one script tag into the product's HTML.
2. Verify the domain in the Verb dashboard.
3. Write a verb.md describing the tools, import it, and switch on the ones you want.

There is nothing to install on the customer's server and no framework
requirement: React, Next, Rails, Django, Laravel and plain PHP all work, because
the widget is a script tag that talks to the customer's API from the browser.
Most people have a first working tool in about five minutes.

## Safety model

- Every tool is classified read, write or destructive. Reads run; writes stop
  and show the user a confirmation card naming the real action and arguments,
  and nothing happens until a human clicks it.
- The assistant can only call tools declared in the customer's verb.md. No
  general internet access, no database access, no capability it was not given.
- It acts as the signed-in user, never as an administrator, so the customer's
  own API makes the same authorisation decision it always did.
- It answers only on domains the customer has verified, which is what
  makes a copied script tag worthless.
- Tool results are fenced as untrusted data, so text arriving from an API that
  reads like an instruction is reported rather than obeyed.
- Every call is logged: who asked, what ran, what came back, and whether the
  outcome was verified rather than merely claimed.
- Every site has a test site whose key only answers on localhost, so you try it
  inside your own app, against your development data, before your users can reach it.

## Pricing

Free while Verb launches, live site included, no card. Every message somebody
sends is one request; the actions inside it are never counted. Verb pays for
the AI usage; customers do not connect or pay a model provider. Enterprise
(custom volume, custom integrations, a signed DPA) by conversation.

## Limitations, stated plainly

- No vision and no image generation. It cannot read a screenshot or make one,
  and hands back manual steps instead.
- It has no capability beyond the tools the customer wrote down.
- Anonymous visitors are read-only; writes require the customer's backend to
  identify the user first.
- Confirmation protects a user from the assistant. It does not protect data
  from a user who was already allowed to delete it.

## Pages

- https://askverb.com/ : what Verb is, with a live assistant on the page
- https://askverb.com/demos : a live scheduling app with Verb installed, at cal.askverb.com. Three one-click demo accounts, 35 tools, real bookings changed behind a confirmation. Our own install into open source software, not a customer
- https://askverb.com/compare : Verb against building your own agent, a docs chatbot, or a person on a call. What each is best at, why most in-house builds stall after the demo, and when Verb is the wrong choice
- https://askverb.com/vs/kapa : Verb compared to kapa.ai specifically. kapa answers from your documentation at real enterprise scale; Verb calls your product's own API to finish the task. Sourced and dated, updated 2026-08-16
- https://askverb.com/vs/sitegpt : Verb compared to SiteGPT. SiteGPT trains a chatbot on your website and documents and hands off to a person; Verb is an AI agent inside the signed-in product that does the user's work through your own API. Sourced and dated, updated 2026-09-23
- https://askverb.com/vs/copilotkit : Verb compared to CopilotKit. CopilotKit is a stack for building your own agent into your app; Verb is an AI agent for a product with signed-in users that you set up rather than build. Sourced and dated, updated 2026-10-30
- https://askverb.com/vs/chatbase : Verb compared to Chatbase. Chatbase builds customer experience agents across chat, email, voice and messaging; Verb is an AI agent inside the signed-in product that does the user's work through your own API. Sourced and dated, updated 2026-10-13
- https://askverb.com/security : what stops it changing data it should not, and the security controls running today
- https://askverb.com/docs : quickstart, four steps to a working assistant
- https://askverb.com/blog : writing on building agents that act on real data
- https://askverb.com/security.md : the same page as plain markdown
- https://askverb.com/.well-known/security.txt : where to report a vulnerability
- https://askverb.com/llms-full.txt : everything on this page plus every docs page in full, security and the full FAQ
- https://askverb.com/about : who builds AskVerb, and where it stands
- https://askverb.com/contact : how to reach the founder, for trials, security reviews and anything else
- https://app.askverb.com/sign-up : sign up

## Documentation

- https://askverb.com/docs/mcp (markdown: https://askverb.com/docs/mcp.md) : Let Claude Code or Cursor create the site, import your tools and take it live.
- https://askverb.com/docs/verb-md (markdown: https://askverb.com/docs/verb-md.md) : The file that decides what the assistant can do. Format, classification, and how to have your coding agent write it.
- https://askverb.com/docs/adapter-tools (markdown: https://askverb.com/docs/adapter-tools.md) : For anything that is not a same-origin fetch. Supabase, Firebase, tRPC, an API on another host.
- https://askverb.com/docs/identity (markdown: https://askverb.com/docs/identity.md) : The step it is easiest to miss and the one that matters most. Nothing writes until this is done.
- https://askverb.com/docs/testing (markdown: https://askverb.com/docs/testing.md) : The test site, and the four things worth deliberately breaking in it.
- https://askverb.com/docs/appearance (markdown: https://askverb.com/docs/appearance.md) : Name, greeting, starters, avatar, colour and placement. No redeploy.
- https://askverb.com/docs/archiving (markdown: https://askverb.com/docs/archiving.md) : The kill switch for a key that ended up in a screenshot. Nothing is deleted, and restoring takes one click.
- https://askverb.com/docs/troubleshooting (markdown: https://askverb.com/docs/troubleshooting.md) : Nothing showing, writes refused, or a tool failing. The four real causes.
- https://askverb.com/docs/numbers (markdown: https://askverb.com/docs/numbers.md) : The Overview, weekly summaries, Analytics tab by tab, and alerts. All counted in requests.

## Writing

- https://askverb.com/blog/ai-agent-take-actions-in-your-app : Tools instead of retrieval, the user's own permissions instead of a service account, and why the hard part is reporting failure honestly.
- https://askverb.com/blog/safe-database-writes-for-ai-agents : Classification, confirmation with real values, and the difference between an action verified and an action merely claimed.
- https://askverb.com/blog/postgres-rls-multi-tenant-ai-agent : The isolation boundary, the tables that deliberately sit outside it, and why the loud failure is the one worth engineering for.
- https://askverb.com/blog/confirming-destructive-actions-ai-agent : Why a model asking 'shall I?' is not a confirmation, what the card must show, and what to do when nobody answers it.
- https://askverb.com/blog/ai-agent-says-it-worked-but-it-didnt : The 200 that lied: why a successful response is not evidence, and the per-tool success shape that stops an agent claiming work it never did.
- https://askverb.com/blog/writing-tool-error-messages-for-ai-agents : Why "failed" produces a guess, the four parts of an error a model can act on, and why descriptions are advisory but validation is binding.
- https://askverb.com/blog/stop-ai-agent-retrying-failed-tool-calls : The 23-call spiral, why per-tool caps let a model walk the tool list, and budgeting failures by cause.
- https://askverb.com/blog/identify-signed-in-user-embedded-ai-assistant : Why the assistant cannot see your session, why it needs a function and not a token, and the encoding detail that fails every signature silently.
- https://askverb.com/blog/ai-chat-widget-sign-out-conversation-leak : A real shared-device leak: permissions held, the transcript did not. Keying on the subject, not the token, and why sign-out has no single choke point.
- https://askverb.com/blog/prompt-injection-ai-agents-that-take-actions : Why offering a tool list is not enforcement, the switch that is the allowlist, and bounding what an obeyed injection can reach.
- https://askverb.com/blog/embedded-script-blocked-content-security-policy : The failure that cannot report itself, the second directive everybody forgets, and why strict-dynamic makes your allowlist irrelevant.
- https://askverb.com/blog/test-ai-agent-without-production-data : Run it for real against development data, the five cases worth deliberately breaking, and why a timer on real execution backfires.
- https://askverb.com/blog/choosing-llm-model-for-in-app-ai-agent : Why prompt engineering cannot fix a routing problem, the asymmetric classifier, and the settings that silently stop applying after a model swap.
- https://askverb.com/blog/best-ways-to-add-ai-assistant-to-saas-2026 : Documentation chatbot, build your own, or embedded action assistant: the one question that decides between them.
- https://askverb.com/blog/ai-assistant-for-legal-practice-management-software : Why most of a lawyer's time in practice software is small updates after court, and what an assistant needs before a firm lets it make them.
- https://askverb.com/blog/ai-agent-for-marketplace-admin-panel : Moderation queues, bulk changes and broadcasts: what an agent can take off a marketplace operator's hands, and the confirmations bulk actions need.
- https://askverb.com/blog/ai-assistant-for-scheduling-software : Why most of what people do in a scheduling tool is procedures rather than questions, and what an assistant has to get right to take them on.
- https://askverb.com/blog/nextjs-build-out-of-memory-small-server : Why a build takes down a small server when the app it produces runs fine, and the one-line cgroup fix.
- https://askverb.com/blog/why-in-app-ai-agents-never-ship : The demo takes a weekend and the sign-off takes a quarter. The identity mistake that causes it, and the day our own test suite turned out to be pointing at production.
- https://askverb.com/blog/add-ai-agent-to-saas-from-claude-code-cursor : The setup that used to mean a dashboard, three tabs and a key to paste is now one sentence to the coding agent you already have open.
- https://askverb.com/blog/set-up-in-app-ai-agent-in-one-conversation : The whole setup as a conversation you can copy: the prompts, what your coding agent does with each one, and the two moments it stops to ask you.
- https://askverb.com/blog/protect-ai-agent-on-your-website-from-abuse : A real jailbreak attempt on our landing page, why it failed, and the six guardrails any public AI agent needs, including two that readers added.
- https://askverb.com/blog/product-tour-or-ai-agent-complex-workflow : Where product tours help, why users get stuck somewhere else entirely, and what an AI agent inside the product has to get right to take that moment on.
- https://askverb.com/blog/users-ask-for-features-you-already-have : Why the most common feature request is for something already shipped, why docs and tooltips rarely fix it, and what does.
- https://askverb.com/blog/how-to-add-ai-to-your-app : The five steps from an app with no AI to one where users get work done by asking, without rebuilding anything.
- https://askverb.com/blog/copilotkit-alternatives : Five alternatives to CopilotKit, sorted by whether you want to build the agent or have one, with prices from each product's own site.
- https://askverb.com/blog/feature-adoption-rate : The formula, what the benchmarks really say, and why most low adoption is a path problem rather than a feature problem.
- https://askverb.com/blog/digital-adoption-platform-vs-ai-agent : What a DAP does, who it is really for, and when an AI agent that does the work fits a product better than guidance.
- https://askverb.com/blog/how-to-add-ai-agent-to-your-website : The script, the signed-in user, the actions, and the two things that break an agent on a real website most often.
- https://askverb.com/blog/chatgpt-or-in-app-ai-agent : Why an AI agent inside your product and ChatGPT in its own tab do different jobs, and how to tell which one your users need.
- https://askverb.com/blog/what-is-an-in-app-ai-agent : A plain definition of an in-app AI agent: what it does, what it is not, and the four things that make one safe to ship.
- https://askverb.com/blog/cost-of-an-in-app-ai-agent : The model bill, the engineering that follows the first demo, and the list to price before deciding to build or buy.
- https://askverb.com/blog/measure-an-ai-agent-pilot : The four numbers that decide a 30-day AI agent pilot, the baseline to take first, and the bar to set before day one.
- https://askverb.com/blog/walkme-pendo-whatfix-alternatives : Guidance tools for your own product with published prices, the enterprise options, and when an AI agent that does the work fits better.

## Free tools

- https://askverb.com/tools/ai-agent-roi-calculator : The hours and money an AI agent saves your users each month, from your own numbers.
- https://askverb.com/tools/agent-readiness-checker : Nine tests for whether AI assistants and agents can read and use your website, with a score and the fixes.
- https://askverb.com/tools/llms-txt-generator : A ready-to-publish llms.txt in the llmstxt.org format, built in your browser.
- https://askverb.com/tools/llms-txt-checker : Validates an llms.txt against the llmstxt.org format, line by line, pasted or live.
- https://askverb.com/tools/openapi-to-mcp-tools : Every operation in an OpenAPI 3 spec as an MCP tool definition, with read, write and destructive marked.
- https://askverb.com/tools/llm-api-cost-calculator : What an AI feature costs to run on Claude, GPT and Gemini, side by side, from your own usage.
- https://askverb.com/tools/ai-crawler-robots-txt-generator : A robots.txt that blocks AI training crawlers, AI search crawlers or both, crawler by crawler.
- https://askverb.com/tools/faq-schema-generator : FAQPage JSON-LD from your questions and answers, ready to paste.
- https://askverb.com/tools/organization-schema-generator : Organization JSON-LD with contact point, address and profiles, ready to paste.
- https://askverb.com/tools/csp-checker : Whether a third-party script would load under your CSP, and the policy's weak spots.
- https://askverb.com/tools/email-signature-generator : A clean HTML email signature for Gmail, Outlook and Apple Mail.
- https://askverb.com/tools/sitemap-checker : Finds a site's sitemaps from robots.txt and the usual paths, and checks each one.
- https://askverb.com/tools/sitemap-validator : Checks a sitemap or sitemap index against the sitemaps.org protocol.
- https://askverb.com/tools/sitemap-generator : A valid XML sitemap from a pasted list of URLs.
- https://askverb.com/tools/sitemap-url-extractor : Every URL in a sitemap, as text or CSV.
- https://askverb.com/tools/website-url-extractor : Every link on a web page, internal and external, with anchor text.
- https://askverb.com/tools/sitemap-urls-comparison : Added, removed and shared URLs between two sitemaps.
- https://askverb.com/tools/sitemap-split-merger : Split a sitemap into parts with an index, or merge several into one.
- https://askverb.com/tools/sitemap-index-generator : A sitemap index that lists all your sitemaps.
- https://askverb.com/tools/sitemap-analyzer : URLs per section, freshness of lastmod dates, changefreq and priority in use.
- https://askverb.com/tools/html-to-markdown : Clean Markdown from HTML, with tables and code blocks kept.
- https://askverb.com/tools/paste-to-markdown : Rich text from Docs, Word, Notion or the web as Markdown.
- https://askverb.com/tools/webpage-to-markdown : Any public page's main content as clean Markdown.
- https://askverb.com/tools/csv-to-markdown : A Markdown table from CSV, quoting and pipes handled.
- https://askverb.com/tools/json-to-markdown : JSON as a Markdown table or nested list.
- https://askverb.com/tools/xml-to-markdown : XML as a readable Markdown outline.
- https://askverb.com/tools/docx-to-markdown : A Word document as Markdown, read in your browser.
- https://askverb.com/tools/google-docs-to-markdown : A shared Google Doc as Markdown, by link.

## Set up from an AI agent

- https://askverb.com/agents/claude-code : connect Verb's MCP server to Claude Code and set Verb up from it
- https://askverb.com/agents/codex : connect Verb's MCP server to Codex and set Verb up from it
- https://askverb.com/agents/cursor : connect Verb's MCP server to Cursor and set Verb up from it
- https://askverb.com/agents/vscode : connect Verb's MCP server to VS Code and set Verb up from it
- https://askverb.com/agents/windsurf : connect Verb's MCP server to Windsurf and set Verb up from it
- https://askverb.com/agents/claude-app : connect Verb's MCP server to Claude and set Verb up from it
- https://askverb.com/agents/chatgpt : connect Verb's MCP server to ChatGPT and set Verb up from it

## Integrations by stack

- https://askverb.com/integrations/nextjs : Add an AI agent to a Next.js app: the script tag in app/layout.tsx, a route handler that signs who is logged in, and actions through your own API as that user.
- https://askverb.com/integrations/rails : Add an AI agent to a Ruby on Rails app: the script tag in the application layout, a controller action that signs the current user, and actions through your own routes.
- https://askverb.com/integrations/django : Add an AI agent to a Django app: the script tag in your base template, a view that signs request.user, and actions through your own views as that user.
- https://askverb.com/integrations/laravel : Add an AI agent to a Laravel app: the script tag in your Blade layout, a controller that signs the authenticated user, and actions through your own routes.
- https://askverb.com/integrations/react : Add an AI agent to a React single-page app: the script tag in index.html, a token endpoint on your backend, and actions through your API as the signed-in user.

## Contact

vishnu.ps@askverb.com reaches the person who built it. More at https://askverb.com/contact.

## More

https://askverb.com/llms-full.txt carries every docs page in full, the security page and the full FAQ.