yevyevyev

Hey HN,

We built Jolt to solve a fundamental problem with AI coding tools - they struggle with larger, real-world codebases and cannot accurately determine the context files for your prompt.

Jolt's public beta is live today, and we'd love your feedback. You can use Jolt on the web or in any VSCode-based IDE. Our free tier will let you work on codebases up to ~100K lines.

We developed a novel way for Jolt to understand large codebases and automatically determine context files. Our approach scales to multi-million line codebases - the largest codebase using us in production is over 8M lines.

Jolt is optimized for codebase understanding rather than response speed. That said, using Jolt is significantly faster than other tools when you include the time spent selecting context files.

Manually selecting context files is a non-starter when you're working on larger codebases or unfamiliar code. It's a broken product experience. Most AI coding tools rely on some flavor of vector-embedding RAG to determine the files related to your prompt. The reality is that vector-embedding search is not effective on code, and there is a sharp drop in efficacy as codebase size increases.

Here's what folks are using Jolt for: - Writing code, tests, and refactoring - Onboarding developers - Brainstorming a feature's implementation - Asking questions about OSS repos - Writing documentation, including mermaid charts - Contributing across the stack

Thanks for reading, and let us know what you think.

Web3 aka distributed ledger aka blockchain

Hi Dmitry, thanks for replying here. You raise some good points - I'll do my best to address them below. I'll also add that we have a fully-featured free tier that you can sign up for on our website (www.multiple.dev). Any hands-on feedback from our product or the TestGen feature would be extremely helpful.

Test feedback - during our TestGen flow, the user provides feedback on the sequence and contents of the API requests. And at the end of the flow, our users can manually edit the resulting JS code for additional customization.

Effort to create a load test - You can go from a Swagger or HAR file to a function load test, written in JS, in a few minutes. There is no learning curve, assuming you have basic knowledge of JavaScript. Maintenance is typically minimal.

CLI - we are launching our CLI shortly, where users can start tests from command line as you describe. It'll work similarly to Jest or other unit test frameworks, where the test scripts will live in our user's codebase.

The use of AI - we use AI to generate realistic-looking synthetic data, which can be challenging with strings. The AI matches each field to the most relevant faker-js function. We need the content of the string to look like something the target application would receive in production. And with HAR files, we use AI to help filter out irrelevant requests such as analytics.

I hope that was helpful, and I'm happy to go into more detail.

Postman generates data based on datatypes in the OpenAPI spec: strings, numbers, booleans, etc - but the data will not look realistic. The video outlined a rudimentary test that checked if required fields were present.

Our TestGen feature generates realistic-looking data, such as dates, names, addresses, URLs, etc, automatically based on the field names, examples, and other API spec metadata. It does this automatically, without human intervention. The output is JavaScript, so if further customization is needed, such as using a response value of an API call in a subsequent request, you can do that.

From my understanding, Schemathesis can generate data based on a value being a string, number, boolean, etc. It also seems fairly manual to set up and has a learning curve. Our output is JavaScript that can be run anywhere.

With our TestGen feature, the AI looks at example requests in a HAR file or Swagger examples, or it can solely rely on the name of the property. From there, it automatically generates the correct type and format of data - e.g., if a field is named "address," it generates a value that looks like an address and is formatted in the same way as examples. It wouldn't be practical to cover every potential edge case and scenario without AI.

That’s a great question. The TestGen feature generates JavaScript that uses faker-js functions to generate the test data, and axios to make http requests. You can copy and paste the JS output of TestGen and run it anywhere.

Hey, this is the author here. Thanks so much for sharing the post. We learned a ton about the nuances and limitations of prompting while building this feature. What are everyone's favorite AI features or integrations that they've seen?