# Continual learning starts with traces, replay and training

Markdown copy of https://realalpha.app/s/continual-learning-starts-with-traces-replay-and-training/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Ronak Malde](https://realalpha.app/builders/ronak-malde/) · Ronak Malde is cofounder of Trajectory. · Built SWE-1 at Windsurf and now leads Trajectory's continual-learning platform for improving agents from production use.
- Host: [Pat Grady](https://realalpha.app/people/pat-grady/) · Co-steward, Sequoia Capital · Joined Sequoia in 2007; backed Snowflake, Zoom, ServiceNow and OpenAI.
- Host: Lauren Reeder · Sequoia Capital
- Show: Training Data
- Episode: [Bringing Continual Learning to Every Company: Trajectory’s Ronak Malde](https://realalpha.app/v/32vxW6GMeLY/), Nov 5, 2026
- Moment: 10:27 to 12:56 of the episode (2 min), playing on https://realalpha.app/s/continual-learning-starts-with-traces-replay-and-training/; the episode from there: https://realalpha.app/v/32vxW6GMeLY/?t=627

## Quote

> “you need to be able to **trace all of your trajectories** that are happening in production.”
> — [Ronak Malde](https://realalpha.app/builders/ronak-malde/) at [10:49](https://realalpha.app/v/32vxW6GMeLY/?t=649) · Training Data

## Takeaways

1. Capture full production trajectories, including user feedback.
2. Replay traces to evaluate what good looks like.
3. Training translates tasks and rewards into model improvements.

## About this segment

Ronak Malde lays out the practical pipeline: capture production traces, replay them for evaluation, then modify the training algorithm. The hard part is turning a company’s idea of good into model improvements.

From “Bringing Continual Learning to Every Company: Trajectory’s Ronak Malde”, Nov 5, 2026. [Watch the full episode](https://realalpha.app/v/32vxW6GMeLY/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[10:30](https://realalpha.app/v/32vxW6GMeLY/?t=630) Yeah, so our goal at Trajectory is to actually limit these ingredients so that it is literally just, you know what good looks like. However, right now, there are a lot of components that companies need. And then we as our product as well, try to bridge that gap and make that as easy as possible. So right now, as a company, you need a couple of things. One, you need to be able to trace all of your trajectories that are happening in production.

[10:57](https://realalpha.app/v/32vxW6GMeLY/?t=657) And there's lots of AI native companies that have gone through this transformation where they're logging not just the main agent call, but also all the sub agents, what's happening in the product as well, any feedback that the user is giving. The ideal world is you get this kind of perfect timeline of all of those things so that you can track them. So that's the first step. And just on that, what are people doing that in today?

[11:18](https://realalpha.app/v/32vxW6GMeLY/?t=678) Like where do those traces live? Yeah. In my view, I think the entire ecosystem of continual learning needs to be a lot of players that basically build up all this infrastructure. So some companies are doing this in-house, but there's also a lot of great products out there like LangChain, like Braintrust, Raindrop, where you can basically plug into your infrastructure or your production agents and then basically trace all of these things.

[11:43](https://realalpha.app/v/32vxW6GMeLY/?t=703) So what we're finding is a lot of AI native companies will use a lot of these products in order to get that first step out of the way. Okay, so we got traces and then what? So that's traces. The second part is then making these replayable. You need some sort of infrastructure to say, hey, okay, given a trace that I've seen in production, how can I actually then replay that for an eval to see what good looks like?

[12:04](https://realalpha.app/v/32vxW6GMeLY/?t=724) Or right now for training as well. And so that's where companies also need to invest some sort of time. What we make really easy in our product as well is to bridge that gap. And so if you bring your traces and you say, okay, here's just the concept of an environment that I might want, in more technical terms, it's a Docker file or some sort of system requirements, then you can basically replay that entire trace.

[12:30](https://realalpha.app/v/32vxW6GMeLY/?t=750) That's the second part. And then the third part is then the actual modification of the algorithm. And I think that's where it's really difficult to do this in-house as a company, is basically the entire training stack, the entire loss function, the reward function, all of these sort of components that need to be built up to translate these tasks into actual improvements for the model. And so that's the main part that we want to abstract away off the bat.