Tim Michaud

Building a synthetic insurance doc generator for AI training. Need commercial property underwriters to look at sample loss runs and tell me what looks fake. 20 min, paid. DM me.

@mikejulian Reading code/logs/plans (And the occasional direct editing of a plan)

For those who are 100% on Claude Code, what role does an IDE (eg, VS Code, Cursor, etc) play in your workflow, if any? Having trouble wrapping my head around this.

The SRD workflow is 1000x better than the traditional Apple developer workflow; and it pains me that they haven't replaced their "normal" workflow yet

Use it to: • Test SIEM rules without lab setup • Train SOC analysts on realistic scenarios • Train anomaly models on correlated auth + activity data • Demo security tools without touching customer data Try it: oktalog.getkashikoi.com

We just shipped a big Oktalog update. You can now generate Okta auth logs that are already correlated with Jira issues and GitHub commits/PRs. One ZIP. Time-aligned events. Built for people who actually have to investigate incidents, not just look at dashboards.

@vasuman I think it mostly comes down to if you have access to MNPI/what's in the contracts signed (IANAL ofc)

The advice we've gotten from Racoons has been very useful - would recommend. And it's free :)

Relaunched Oktalog, our free Okta log generator for security & eng teams. Generate realistic auth sequences, 20 logs no signup / 200 with a free account. Next up: chained, cross-app events for richer training data. Try it: oktalog.getkashikoi.com

@Qromerolauro I have been purposefully timing overnight research/projects to hit this window since late July. You also seem to get more leniency on credits used on the Anthropic plan at this time too; though that could just be coincidence since I don't watch these super closely

is it just me or are all of the coding agents better from 2am-6am?

Full technical breakdown: blog.getkashikoi.com/2025/11/18/sim…

LLMs generate logs that look right but are subtly garbage. We instead use world models to build our Okta logs. 85-90% realism, validated by SOC analysts. Try it yourself: oktalog.getkashikoi.com

Rich Sutton's Bitter Lesson Isn't the Whole Story The tech world has a favorite essay. Walk into any AI strategy meeting, and someone will inevitably reference it to justify why they need more compute, more data. But here's how to spot a pseudo-intellectual: they never mention Sutton's equally important essay on "Verification." blog.getkashikoi.com/2025/11/12/bey…

Read the full context on why simulation matters for AI verification: blog.getkashikoi.com/2025/11/12/bey…

We took the simulation approach that controls fusion reactors and applied it to security. Our Okta Log Generator creates realistic auth sequences: login→MFA→activity→logout with consistent context across events. Not random synthetic data. World models built from real security expertise. Security devs: Test your SOC rules properly. Enterprise: This verification approach scales to any domain. Try free: oktalog.getkashikoi.com

@hthieblot Anyone who needs realistic looking data for training/validating their AI agents - we're starting with AI soc analysts since many of them have high data requirements, and getting production data for training is very expensive

@TimGMichaud Who is it for

Explain your product in one sentence. Be clear about what it does. No buzzwords. if you can do that, I’ll consider investing. Hit me.

@CryptoGangsta Did you apply to get access to Aardvark? (You should! Would love to hear your thoughts on it)

My very opinionated rant on getting started with AI and static analysis. parsiya.net/blog/wtf-is-ai…

"Your demo is too clean. Real alerts are ambiguous." Fair. v2 now includes scenarios like: DB migration with 136GB egress (malicious or maintenance?) and C2 connections hiding in normal traffic. More realistic AI SOC testing: twitter.newsocanalyst.getkashikoi.com

@jspeedluk @hthieblot That's the vision! With a side of "End customer can plugin their own data to see which agent works best for them without having to buy and do scaffolding for each agent", but we'll get there!

@TimGMichaud @hthieblot This can be really good for monitoring of Ai agents and models to know if they are working up to the mark by comparing them to others in market

@ you who follows me I would love to hear your startup idea, or better see a demo!