Blog

Writing about websites, questions and the systems behind them.

Two views. Sachin writes about the website owner side: product, conversion and website operations. Vishal writes about the systems side: retrieval, routing, reliability and data boundaries. No invented statistics, no invented customers.

Content gaps

What visitor questions reveal about your website

Every question a visitor types is a place your website failed to answer first. Here is how to read that as a content map rather than a

SSachin7 min read
Content operations

How to turn chat transcripts into a content roadmap

A repeatable monthly process for converting raw chat logs into a prioritised list of page briefs, without a research budget or a dedica

SSachin8 min read
Conversion

The questions your pricing page fails to answer

Most pricing objections are not about price. They are about missing information that the pricing page could have supplied.

SSachin6 min read
Content gaps

Support tickets and pre sale questions are different signals

Mixing post sale support with pre sale questions produces an average that describes nobody. Separate them and both become useful.

SSachin6 min read
Content gaps

Measuring content gaps without a research budget

You do not need a user research programme to find out what your website fails to explain. The people already visiting will tell you for

SSachin6 min read
Content operations

Why FAQ pages go stale and what replaces them

An FAQ page written once at launch describes the questions a team imagined, not the questions people ask. Here is how to keep one hones

SSachin6 min read
Analytics

Reading intent from question phrasing

How a visitor phrases a question predicts what stage they are at more reliably than the page they were on when they asked it.

VVishal7 min read
Deployment

Choosing what to train a website assistant on

More sources produce worse answers, not better ones. Source selection is the main quality lever you control.

SSachin7 min read
Deployment

One click deploy: what actually has to be true first

Embedding a widget takes a minute. Making it worth embedding takes longer. Here is the honest checklist.

VVishal7 min read
Deployment

Adding an assistant to a Webflow site

Where the embed goes in Webflow, what breaks, and the constraints specific to the platform.

SSachin5 min read
Deployment

Adding an assistant to a WordPress site

Three ways to add the embed, which one to choose, and the caching and consent issues specific to WordPress.

SSachin6 min read
Reliability

Keeping an assistant in sync with a changing site

Retraining cadence is a product decision, not a maintenance chore. Here is how to decide it rather than default to it.

VVishal6 min read
UX

Widget placement, and when not to show a chat launcher

A chat launcher on every page at all times is a default, not a decision. Restraint improves both conversion and how the brand reads.

SSachin6 min read
Conversion

Lead capture inside a conversation without killing it

Asking for an email before answering anything is the fastest way to end a conversation. Sequence matters more than form design.

SSachin6 min read
Support

When to hand off to a human, and how to decide

Handoff triggers should be written rules you can audit, not a judgement made fresh each time.

SSachin6 min read
Support

What a good handoff actually contains

Escalating a conversation without context makes the visitor start over. Here is the minimum payload a human needs.

SSachin5 min read
Conversion

Qualifying without an interrogation

Two questions asked at the right moment beat six asked upfront. Most qualification signal is already in the transcript.

SSachin5 min read
Analytics

Chat analytics that change decisions

Message volume is a vanity metric. Here are the four numbers that actually cause someone to do something differently.

SSachin6 min read
Retrieval

Retrieval augmented generation, a practical explanation

For a website assistant, retrieval quality dominates model quality. Here is why, and what that means for where you spend effort.

VVishal8 min read
Retrieval

Chunking website content for retrieval

Chunk boundaries decide answer quality more than chunk size does. Where you cut matters more than how big the pieces are.

VVishal8 min read
Retrieval

Embeddings, what they do and what they do not do

Embeddings measure similarity, not truth and not relevance. Understanding the difference prevents a specific class of bad answer.

VVishal7 min read
Architecture

Why multi model routing exists

Cost, latency and task fit differ by query. Routing is how you stop paying frontier prices for questions that do not need them.

VVishal7 min read
Reliability

Measuring answer quality without a labelled dataset

You will not have a golden dataset. Two proxies get you most of the way, and both are already being generated.

VVishal7 min read
Reliability

Handling questions the assistant should refuse

Refusal design is a product feature. Deciding the boundary in advance is what stops confident wrong answers.

VVishal6 min read
Performance

Latency budgets for a chat widget

Perceived latency is a UI problem as much as a model problem. Here is where the time goes and which parts are worth optimising.

VVishal6 min read
Data

Where your website content goes when you train an assistant

Draw the data flow before you promise anything about it. Here is the map, and the questions it forces you to answer.

VVishal7 min read
Data

Data boundaries, a plain explanation for site owners

What you can and cannot honestly tell your visitors about an AI assistant on your site, without a legal team.

VVishal6 min read
Data

What to tell visitors about AI chat and data

The disclosure that belongs next to the chat box, and how to write it without turning it into a legal document.

SSachin5 min read
Data

Retention decisions are product decisions

How long you keep conversation data determines what analysis is possible. Copying someone else's number decides your product by acciden

VVishal6 min read
Reliability

Reliability when a model provider goes down

Provider incidents happen. What your assistant does during one is a design decision you make now or by accident later.

VVishal6 min read
Architecture

Rate limits, abuse and cost control

A public endpoint that calls a paid API is a spending endpoint. Budget guards belong in the design, not in an incident review.

VVishal6 min read
Buying

Questions to ask any AI chat vendor before you sign

A checklist for evaluating a website assistant, including the questions we would have to answer ourselves.

SSachin7 min read