Category Creation Improvements - Product Update | September 2024

Henry Scott-Green

Sep 2, 2024 — 2 min read

What’s been cooking at Context.ai? 👨‍🍳

Check out everything we’ve shipped in our latest product demo video 🎥

This month we’ve been focused on category creation, product latency, transcript filtering, custom graphs, and category backfills

Read the product update to learn more!

Category creation flow improvement

Category creation is at the core of the Context.ai product and getting it right is crucial. We now have much more powerful category definition tools, including random preview sampling, and filtering of preview results. This makes it easier for you to define categories as intended.

Filtering on message-level metadata and conversion events

It is now possible to filter transcripts by message-level metadata and conversion events. This lets you see only the transcripts that have any message level metadata characteristics, or that do (or don’t) contain conversion events.

Latency improvements

The application is now significantly faster after a sprint on product latency. You should notice this throughout the product, and particularly on the transcript pages.

Topic backfill status indicators

We now show a status indicator when backfilling updated topics. This lets you know if the backfill is complete and the matches are all using your new topic definition, or if there is still a backfill in progress.

Workspace improvements

The workspace allows you to create custom graphs of your data in Context.ai. This month we’ve added the ability to compare against a previous period, and to filter on role and language.

Custom Charts & Dashboards - Product Update | August 2024

July was all about configurability and scale at Context.ai We’ve always allowed the creation of custom graphs in our workspace, but these are now dramatically more powerful with many more dimensions available to filter and to group by, as well as a new UI. Custom dashboards can now

What product experiences are enabled by multi-agent LLM frameworks?

It feels like everyone is excited about multi-agent frameworks - even though their performance isn’t yet ready for prime-time. These performance problems are improving with increasingly powerful models like Claude 3 and GPT-4o - and great things are expected from GPT-5, a launch that will likely make agentic workflows

Launching Custom Conversion Events - Product Update | July 2024

Today we’re launching support for custom conversion events 🧾 This addresses one of the biggest challenges in the LLM ecosystem - proving ROI 📈 Context.ai users can now log custom conversion events with their LLM conversation transcripts, indicating where users completed an action: a purchase, a link click, or even

Are your LLM Products Guardrails working?

How do you know if the guardrails on your LLM product are working? 🛡️🎯 Some people wait until they show up in the The New York Times - like McDonald's, Air Canada, or Chevrolet Conversational LLM products are a challenging consumer experience as users can ask an infinite number