Sanket Saurav
@sanketsaurav.com
Co-founder/CEO, DeepSource. YC alum. Veritas vos liberabit.
This turns the vicious cycle of AI slop → more AI slop to a virtuous one where the AI agent helps you move faster and compound productivity gains.
November 20, 2025 at 9:35 PM
This turns the vicious cycle of AI slop → more AI slop to a virtuous one where the AI agent helps you move faster and compound productivity gains.
Solution?
- Adopt better development practices in the code base that helps AI build on top of a good foundation.
- Invest in tools *around* your AI agent. Test suite that can run locally. Typechecking/codeformatting/linting tools.
- Invest in code observability — coverage, complexity.
- Adopt better development practices in the code base that helps AI build on top of a good foundation.
- Invest in tools *around* your AI agent. Test suite that can run locally. Typechecking/codeformatting/linting tools.
- Invest in code observability — coverage, complexity.
November 20, 2025 at 9:35 PM
Solution?
- Adopt better development practices in the code base that helps AI build on top of a good foundation.
- Invest in tools *around* your AI agent. Test suite that can run locally. Typechecking/codeformatting/linting tools.
- Invest in code observability — coverage, complexity.
- Adopt better development practices in the code base that helps AI build on top of a good foundation.
- Invest in tools *around* your AI agent. Test suite that can run locally. Typechecking/codeformatting/linting tools.
- Invest in code observability — coverage, complexity.
Most orgs are stuck in this vicious cycle: bad code + unchecked AI → worse code produced by AI.
November 20, 2025 at 9:35 PM
Most orgs are stuck in this vicious cycle: bad code + unchecked AI → worse code produced by AI.
Lack of a "clean" engineering environment — good code coverage (and the ability to track code coverage), good coding patterns, low-complexity modules — accelerates codebase entropy, degrading the future AI performance on tasks.
November 20, 2025 at 9:35 PM
Lack of a "clean" engineering environment — good code coverage (and the ability to track code coverage), good coding patterns, low-complexity modules — accelerates codebase entropy, degrading the future AI performance on tasks.
Apply: go.deepsource.com/aae
Associate Account Executive at DeepSource | Y Combinator
DeepSource (https://deepsource.com) is transforming how engineering teams ship secure, high-quality code. Our AI-powered DevSecOps platform helps companies identify and resolve security vulnerabilities, code quality issues, and open-source risks before they reach production, utilizing static analysis, Autofix™ AI, and Autonomous AI Agents.
The Opportunity
We have several hundred paying customers, including large enterprises such as Visa, Ancestry, WEX, among others. In the last 3 months, we've launched DeepSource SCA (https://deepsource.com/sca)and DeepSource Agents, (https://deepsource.com/agents)where we're thinking about code security in the age of AI from first principles. We've received incredible customer feedback on these new products, and we're now ready to scale our sales motion to capitalize on this momentum.
The Role
You'll be an Associate Account Executive, working directly with our CEO to build and execute our outbound sales strategy. This is a full-cycle sales role wher
www.ycombinator.com
November 11, 2025 at 6:53 PM
Apply: go.deepsource.com/aae
Original post: codemanship.wordpress.com/2025/09/30/...
Comprehension Debt: The Ticking Time Bomb of LLM-Generated Code
An effect that’s being more and more widely reported is the increase in time it’s taking developers to modify or fix code that was generated by Large Language Models. If you’ve wo…
codemanship.wordpress.com
September 30, 2025 at 3:41 PM
Original post: codemanship.wordpress.com/2025/09/30/...
Full article here:
www.theregister.com/2025/08/18/...
www.theregister.com/2025/08/18/...
Generative AI does nothing for 95 percent of companies
: MIT NANDA study finds only 5 percent of organizations using AI tools in production at scale
www.theregister.com
August 19, 2025 at 3:43 AM
Full article here:
www.theregister.com/2025/08/18/...
www.theregister.com/2025/08/18/...
This quote is quite telling, but I'm not sure the situation is that grim. I do believe most companies are building valuable stuff with AI and do have enough differentiation.
But if the user thinks you're just re-skinning ChatGPT, it might be time to re-think that UX.
But if the user thinks you're just re-skinning ChatGPT, it might be time to re-think that UX.
August 19, 2025 at 3:43 AM
This quote is quite telling, but I'm not sure the situation is that grim. I do believe most companies are building valuable stuff with AI and do have enough differentiation.
But if the user thinks you're just re-skinning ChatGPT, it might be time to re-think that UX.
But if the user thinks you're just re-skinning ChatGPT, it might be time to re-think that UX.
I suspect a key reason for this could be that most companies are still retrofitting ChatGPT's chat box into an established product UX, with very few people doing 0→1 innovation.
If your product reminds the user of ChatGPT, they'll invariably think ChatGPT can do a better job.
If your product reminds the user of ChatGPT, they'll invariably think ChatGPT can do a better job.
August 19, 2025 at 3:43 AM
I suspect a key reason for this could be that most companies are still retrofitting ChatGPT's chat box into an established product UX, with very few people doing 0→1 innovation.
If your product reminds the user of ChatGPT, they'll invariably think ChatGPT can do a better job.
If your product reminds the user of ChatGPT, they'll invariably think ChatGPT can do a better job.
Learn more: deepsource.com/agents
DeepSource Agents
DeepSource Agents are autonomous AI agents that secure your code.
deepsource.com
April 25, 2025 at 10:02 PM
Learn more: deepsource.com/agents
DeepSource Agents are available to all teams on DeepSource Cloud starting today on the free plan, with limits. Over the next few weeks, we will roll this out to our enterprise customers. We have an exciting roadmap, and we can't wait to see how this helps developers ship!
April 25, 2025 at 10:02 PM
DeepSource Agents are available to all teams on DeepSource Cloud starting today on the free plan, with limits. Over the next few weeks, we will roll this out to our enterprise customers. We have an exciting roadmap, and we can't wait to see how this helps developers ship!
Finally, we've given the agents long-term memory. So you can teach them important facts and context about your code and your organization.
April 25, 2025 at 10:02 PM
Finally, we've given the agents long-term memory. So you can teach them important facts and context about your code and your organization.
3. False Positive Triage Agent: It removes noise from code security alerts. It reasons about every security issue with the code's context and suppresses it if it's not relevant.
April 25, 2025 at 10:02 PM
3. False Positive Triage Agent: It removes noise from code security alerts. It reasons about every security issue with the code's context and suppresses it if it's not relevant.
2. CVE Prioritization Agent: It uncovers critical vulnerabilities in your 3rd-party dependencies by automatically triaging new CVEs introduced in your dependency chain.
April 25, 2025 at 10:02 PM
2. CVE Prioritization Agent: It uncovers critical vulnerabilities in your 3rd-party dependencies by automatically triaging new CVEs introduced in your dependency chain.
We're starting with releasing three agents today.
1. Autofix™ Autopilot Agent: It autonomously fixes new security vulnerabilities in your code. It can create PRs with security patches for your first-party code and third-party dependency upgrades.
1. Autofix™ Autopilot Agent: It autonomously fixes new security vulnerabilities in your code. It can create PRs with security patches for your first-party code and third-party dependency upgrades.
April 25, 2025 at 10:02 PM
We're starting with releasing three agents today.
1. Autofix™ Autopilot Agent: It autonomously fixes new security vulnerabilities in your code. It can create PRs with security patches for your first-party code and third-party dependency upgrades.
1. Autofix™ Autopilot Agent: It autonomously fixes new security vulnerabilities in your code. It can create PRs with security patches for your first-party code and third-party dependency upgrades.
For example, if the agent sees a new potential SQL injection issue, it can reason about it using the code's AST, spanning across multiple files, and even third-party dependencies.
If it determines that the issue is high-priority, it patches it and opens a PR. All on its own.
If it determines that the issue is high-priority, it patches it and opens a PR. All on its own.
April 25, 2025 at 10:02 PM
For example, if the agent sees a new potential SQL injection issue, it can reason about it using the code's AST, spanning across multiple files, and even third-party dependencies.
If it determines that the issue is high-priority, it patches it and opens a PR. All on its own.
If it determines that the issue is high-priority, it patches it and opens a PR. All on its own.
Enter DeepSource Agents.
Our agents observe every line of code added to your codebase. Using static analysis and built on top of our DevSecOps platform, the agents reason about every observation and autonomously take actions. — like creating PRs.
deepsource.com/agents
Our agents observe every line of code added to your codebase. Using static analysis and built on top of our DevSecOps platform, the agents reason about every observation and autonomously take actions. — like creating PRs.
deepsource.com/agents
DeepSource Agents
DeepSource Agents are autonomous AI agents that secure your code.
deepsource.com
April 25, 2025 at 10:02 PM
Enter DeepSource Agents.
Our agents observe every line of code added to your codebase. Using static analysis and built on top of our DevSecOps platform, the agents reason about every observation and autonomously take actions. — like creating PRs.
deepsource.com/agents
Our agents observe every line of code added to your codebase. Using static analysis and built on top of our DevSecOps platform, the agents reason about every observation and autonomously take actions. — like creating PRs.
deepsource.com/agents
Check it out: deepsource.com/directory
DeepSource Directory | Static Analysis, SAST, and Integrations
Explore all code quality and SAST analyzers, code formatters, and integrations on DeepSource.
deepsource.com
March 3, 2025 at 10:32 PM
Check it out: deepsource.com/directory