Use cases
Users get stuck halfway through a workflow, not on day one
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.
3 min read
AskVerb
Blog
Safety · Building · Reliability
Users get stuck halfway through a workflow, not on day one
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.
3 min read
Your users keep asking for features you already built
Why the most common feature request is for something already shipped, why docs and tooltips rarely fix it, and what does.
3 min read
Someone tried to jailbreak the AI agent on our website. Here is what held.
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.
5 min read
Your coding agent can set up your product’s AI agent now
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.
3 min read
Five prompts from an empty account to a working AI agent
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.
3 min read
What an AI assistant should do inside a law firm's 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.
4 min read
An AI agent for the back room of a marketplace
Moderation queues, bulk changes and broadcasts: what an agent can take off a marketplace operator's hands, and the confirmations bulk actions need.
3 min read
Your agent works. That was never the hard part.
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.
6 min read
What an AI assistant is actually worth inside a booking product
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.
3 min read
The Next.js build, not the app, is what runs the server out of memory
Why a build takes down a small server when the app it produces runs fine, and the one-line cgroup fix.
3 min read
Why your AI agent says an action worked when it didn't
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.
3 min read
Tool error messages are prompts, so write them like one
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.
3 min read
How to stop an AI agent retrying a failing tool forever
The 23-call spiral, why per-tool caps let a model walk the tool list, and budgeting failures by cause.
3 min read
How to tell an embedded AI assistant who is signed in
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.
2 min read
Your AI chat widget is showing the last user's conversation
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.
3 min read
Prompt injection in an agent that takes actions: contain it, don't hope
Why offering a tool list is not enforcement, the switch that is the allowlist, and bounding what an obeyed injection can reach.
3 min read
Why your embedded script silently does nothing under a Content Security Policy
The failure that cannot report itself, the second directive everybody forgets, and why strict-dynamic makes your allowlist irrelevant.
2 min read
How to test an AI agent that takes actions, without touching real data
Run it for real against development data, the five cases worth deliberately breaking, and why a timer on real execution backfires.
3 min read
Choosing a model for an in-app AI agent, and routing the turns that don't need it
Why prompt engineering cannot fix a routing problem, the asymmetric classifier, and the settings that silently stop applying after a model swap.
3 min read
The best ways to add an AI assistant to a SaaS product in 2026
Documentation chatbot, build your own, or embedded action assistant: the one question that decides between them.
3 min read
How to let users take actions with AI 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.
3 min read
Letting an AI agent write to your database, safely
Classification, confirmation with real values, and the difference between an action verified and an action merely claimed.
3 min read
Postgres row-level security for a 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.
3 min read
How to confirm a destructive action, so the confirmation is real
Why a model asking 'shall I?' is not a confirmation, what the card must show, and what to do when nobody answers it.
3 min read