iiinova — where your digital self keeps evolving

Jason Bosco @jasonbosco.bsky.social · 02/10/2026

Just about to make a DNS change that affects hundreds of thousands search requests per minute on Typesense Cloud. No big deal. All in a day's work.

010

Jason Bosco @jasonbosco.bsky.social · 01/10/2026

Having your agents pay down the tech debt you've created over the years is so strangely satisfying 😬

000

Jason Bosco @jasonbosco.bsky.social · 30/09/2026

Ok, with all that talk about MCP Servers... If you were wondering, does Typesense have an MCP Server? Funny you should ask. Yes! Yes we do. We recently launched an MCP Server for Typesense Cloud! So you can now tell your agent:

100

Jason Bosco @jasonbosco.bsky.social · 29/09/2026

Signs that an MCP Server is well built: 1) It thoughtfully limits the number of tools it exposes to the agent (to improve instruction following and reduce context bloat), and instead designs them as parameters to tool calls.

320

Jason Bosco @jasonbosco.bsky.social · 28/09/2026

We hit 1 MILLION downloads a WEEK for our Typesense JavaScript library! 📈 4x increase from same time last year

000

Jason Bosco @jasonbosco.bsky.social · 21/09/2026

For a while it was just telephone and physical mail That’s how you did business with customers. Then came this little idea of connecting computers together in a network. A global little network called the Internet.

100

Jason Bosco @jasonbosco.bsky.social · 18/09/2026

I was recently looking for a SaaS product. Having experienced the usefulness of MCP Servers recently, my evaluation criteria sub-consciously included “MCP Server availability” to my checklist.

100

Jason Bosco @jasonbosco.bsky.social · 17/09/2026

I don't think MCP Servers are going to fully replace web / mobile UIs. There are plenty of things where I want to look around, browse, inspect things visually, etc. But for "I know exactly what I want done, please just go do it" workflows

100

Jason Bosco @jasonbosco.bsky.social · 15/09/2026

When I first started using an MCP Server, I thought “cool, I guess” and left it at that. Didn’t really get the hype. Then months later, I installed a second MCP Server from another SaaS platform into the same agent and that is where things got interesting for me.

100

Jason Bosco @jasonbosco.bsky.social · 11/09/2026

One thing I really like about MCP Servers: I don't have to remember where a SaaS product put a particular feature. Which menu was it under? Which settings page? Was it under the three dots? 😅 I can just tell my ChatGPT / Codex / Claude instance what I want done, and it will figure it out.

010

Jason Bosco @jasonbosco.bsky.social · 10/09/2026

Repulsed by the hype around MCP Servers? This is for you. When it launched, MCP was so hyped up that it left a bad taste in my mouth. But now after having used MCP Servers from a few SaaS services in my day-to-day, I've seen the light. Here's the framing that helped me:

100

Jason Bosco @jasonbosco.bsky.social · 09/09/2026

I’m pretty sure funny people are safe from AI I’m hiring comedy writers at the moment and it’s a great reminder that being funny is hard So much is about timing, instinct and human experience

000

Jason Bosco @jasonbosco.bsky.social · 07/09/2026

My biggest regrets about bootstrapping Typesense instead of raising VC THREAD ⬇️

000

Jason Bosco @jasonbosco.bsky.social · 04/09/2026

Codex added a test for... the text inside docs that assert that certain keywords are present in the markdown files in the repo We are leaving no stone unturned alright. Them bugs could be anywhere

000

Jason Bosco @jasonbosco.bsky.social · 03/09/2026

Time to switch to my trusty old self-hosted coding agent in my brain today

000

Jason Bosco @jasonbosco.bsky.social · 18/08/2026

Exhibit N for why you still need to review agent authored code:

100

Jason Bosco @jasonbosco.bsky.social · 30/07/2026

Looks like Kiwi considers an Orange its competitor Someone at the Kiwi company took a SaaS marketing class I guess

000

Reposted by Jason Bosco

Evil Martians @evilmartians.com · 22/07/2026

Entering the speaker lounge: Jason Bosco (@jasonbosco.bsky.social) He's the founder of Typesense, a bootstrapped, open-source search engine built on Rails. It handles 10+ billion searches every month. We're excited to have him on stage.

052

Jason Bosco @jasonbosco.bsky.social · 08/06/2026

The allure of automating every little thing is even more hard to resist in the age of coding agents. Gotta remind myself of this classic xkcd often

100

Jason Bosco @jasonbosco.bsky.social · 03/06/2026

I tried running 3 agent sessions in parallel yesterday, each working on an independent project (git worktrees ftw).

100

Jason Bosco @jasonbosco.bsky.social · 27/05/2026

AI-powered strawberries 🤨 And here I was thinking only SaaS companies were stuffing AI features down everyone’s throats Also TIL Dyson (the vacuum company) is into farming

000

Jason Bosco @jasonbosco.bsky.social · 22/05/2026

On one hand, I appreciate our AI overlords keeping us safe from harm... On the other hand, I worry about what happens when safety guardrails misunderstand your intent and refuse to do legitimate work.

100

Jason Bosco @jasonbosco.bsky.social · 19/05/2026

Time to author code (with LLMs): 1 hour Time to review said code: 1 week

120

Jason Bosco @jasonbosco.bsky.social · 15/05/2026

The year is 2030. We've all gotten so used to LLM chat interfaces that instead of typing `ls` into our bash prompts, we type: $ list files in directory <requests goes off to an LLM to parse...> 5s later... tool_call: ls 5s later...

110

Jason Bosco @jasonbosco.bsky.social · 12/05/2026

PSA: If you’re vibe coding this is great advice.

110

Jason Bosco @jasonbosco.bsky.social · 07/05/2026

The liability for safety relies on you when you use self-driving in a car. Similarly, the burden of making sure your LLM generated code works for all edge cases relies on you, and not the reviewer. Don’t throw slop over to your colleagues. They can generate slop themselves.

000

Jason Bosco @jasonbosco.bsky.social · 05/05/2026

Ok which one of you is buying RAM, together with an Air Fryer?! Enough of y'all are doing it, why else would Amazon recommend this as a "Frequently bought together" item? Do you put the RAM in the air fryer or something? That's one way to cook I guess.

010

Jason Bosco @jasonbosco.bsky.social · 01/05/2026

“No one reads compiler output, so no one will review LLM code.” Yeah, no. Compilers are deterministic transformations over a formally-defined programming language. They guarantee that your program’s semantics will be remain intact through the transformation. You learn this as a CS major.

100

Jason Bosco @jasonbosco.bsky.social · 24/04/2026

I see a wedge developing among early-career software engineers: Those who use LLMs mindlessly to generate code, and call it day, which causes their skillset to plateau vs those who use LLMs to satisfy their curiosity and learn, while still helping them move faster.

100

Jason Bosco @jasonbosco.bsky.social · 21/04/2026

This is the sobering reality of “agent max-ing” as of today. (Yes I know this won’t age well). But having a list of AI generated PRs waiting for me to review is such a big mental overload for me personally,

100

Jason Bosco @jasonbosco.bsky.social · 17/04/2026

Can some of my AWS friends pass this on to the powers that be at Amazon, and make this happen? Pretty please? 🙏 Benefit to AWS: you get to spark interest in data center tech and build yourself a pipeline of candidates and potential users for life.

000

Jason Bosco @jasonbosco.bsky.social · 14/04/2026

This mechanical keyboard from Apple used to feel so good. Bring 'em back!

000

Jason Bosco @jasonbosco.bsky.social · 08/04/2026

Imagine starting an open source project You bootstrap it, and refuse to take venture capital And then 10 years later... You see your project's name plastered on 50+ buses in San Francisco Surreal. Feeling.

110

Jason Bosco @jasonbosco.bsky.social · 07/04/2026

Free startup idea: an IDE hyper-focused on making PR reviews created by agents easy to review, while allowing navigation of the code base easily, providing helpful context, etc.

010

Jason Bosco @jasonbosco.bsky.social · 02/04/2026

The day I can finally weed out ALL flaky tests in my test suite by letting an agent run tests in various combinations, would be a fantastic day. Still not quite there yet, at least not with Capybara. Even the best models, churning for an hour, only seems to get me so far.

000

Jason Bosco @jasonbosco.bsky.social · 01/04/2026

I like that Grok mentions Typesense before Algolia 😎

000

Jason Bosco @jasonbosco.bsky.social · 31/03/2026

Perfect analogy for what happens if you don’t review code that agents write. That feature you asked it to implement works, sure. But at the expense of a sprawling monstrosity under the hood.

100

Jason Bosco @jasonbosco.bsky.social · 27/03/2026

I've had this laundry list of TODOs sitting in my backlog, that I've always wanted to get to, but couldn't convince myself of the value vs effort involved. Thanks to coding agents, that list is now finally shrinking in size. This actually feels... really good!

100

Jason Bosco @jasonbosco.bsky.social · 26/03/2026

I still haven’t recovered from the time when Claude just deleted an integration test case because it was flaky, after it had attempted to fix it several times. Would I have done the same thing had I been frustrated with that flaky test? May be. But I have higher standards for coding agents.

010

Reposted by Jason Bosco

Jeremy Smith @jeremysmith.co · 24/03/2026

We've got some haikus going! Login with GitHub and vote for your faves! 😄 haiku.blueridgeruby.com

haiku.blueridgeruby.com

Blue Ridge Ruby Haiku Giveaway

Submit a haiku for a chance to win a ticket to Blue Ridge Ruby 2026!

041

Jason Bosco @jasonbosco.bsky.social · 24/03/2026

I see a new form of tech debt coming for dev teams: Comprehension debt. As more and more code is generated by LLMs, if teams don’t take the time to understand deeply what the generated code is doing, as well as code they write by hand…

101

Jason Bosco @jasonbosco.bsky.social · 20/03/2026

After about 3 years of using Safari as my daily browser, I've begrudgingly switched back to Chrome. There's a bug in Safari that randomly shows up and requires that I double-click on every link / button for it to register as a single click.

100

Jason Bosco @jasonbosco.bsky.social · 17/03/2026

“We traced the root cause of the issue that caused the downtime, and turns out it’s all <model provider>’s fault. They generated bad quality code that was subtly wrong, and other agents did not catch it either, and it was pushed to production. We’ve updated our prompts to fix the situation.”

100

Jason Bosco @jasonbosco.bsky.social · 16/03/2026

AI Slop spares no job functions

000

Jason Bosco @jasonbosco.bsky.social · 13/03/2026

Once you get over the novelty of prompting LLMs to build stuff, you then slowly start craving the joy that originally drew you to your craft

000

Jason Bosco @jasonbosco.bsky.social · 11/03/2026

If you love software engineering and want to one day start your own company: Know that you’ll spend less time on software engineering than you’d like, when you own a company! “It’s my company and I can do whatever I want”. Nope. This is a common misconception.

100

Jason Bosco @jasonbosco.bsky.social · 06/03/2026

LLM-generated (slop) PRs are going to fundamentally reshape how open source communities function.

000

Jason Bosco @jasonbosco.bsky.social · 05/03/2026

To the folks using LLMs to auto-reply to posts: Might I recommend you prompt your agent to use your tone of voice, and have it say something unique? All I see is either a rehash of what was said, or a bland follow-up question. It’s super easy to see through this.

100

Jason Bosco @jasonbosco.bsky.social · 03/03/2026

TIL that the Federal Reserve has a status page, and that ACH payments had an incident today.

000