iiinova — where your digital self keeps evolving

Jason Kealey @softwareengineering.ca · 25/03/2026

Well that didn’t take long. Linear’s launching a code aware agent.

Jason Kealey @softwareengineering.ca · 22/03/2026

Mine decided to jump onto my frozen in-ground pool yesterday and run away from us (yet remain on the surface of the dangerous pool) when we tried to help it out.

131

Jason Kealey @softwareengineering.ca · 22/03/2026

I know I could argue that this workflow’s superfluous if copilot can actually do the code changes and I could review that but I don’t want to be doing many iterations on PRs, I just want to offer technical guidance to avoid going down the wrong path.

000

Jason Kealey @softwareengineering.ca · 22/03/2026

I know I can checkout the code and run it in planning mode, or just use Claude Code or other, but am looking for a solution that runs fully in the browser and is codebase aware.

120

Jason Kealey @softwareengineering.ca · 22/03/2026

I like the workflow when I just assign a ticket to github copilot and it gets done, but sometimes I just want it to expand the ticket, let me review/adjust and assign to a human.

100

Jason Kealey @softwareengineering.ca · 22/03/2026

Any fun AI tools to recommend that take a ticket from Linear, checks out the code and rewrites the ticket with architectural/technical guidance and planning (change these files in this way) without actually implementing it ?

100

Jason Kealey @softwareengineering.ca · 17/03/2026

What’s the secret? My list of cold calling secrets: - Not mentioning their car’s extended warranty in my script - That is all

100

Jason Kealey @softwareengineering.ca · 15/03/2026

I think it conveys what it does well. It does make me wonder what actually does a report look like. I’d be hesitant if all it does is tell me random facts like “people love my puppy” as opposed to actionable growth tactics for future content (which may merge my comments with external trends)

110

Jason Kealey @softwareengineering.ca · 20/02/2026

Didn’t need incremental loads for that project but would likely attack that with some dagster wizardry should the need arise

000

Jason Kealey @softwareengineering.ca · 15/02/2026

Hoping you don’t stumble into a new gif-like debate

000

Jason Kealey @softwareengineering.ca · 15/02/2026

Problem is we’re in the small window before all of AI’s answers are guided by advertisers and the cycle repeats itself

270

Jason Kealey @softwareengineering.ca · 08/02/2026

Is using 67 AI agents better than 12 or 4? My LinkedIn feed is full of these humble brags.

000

Jason Kealey @softwareengineering.ca · 07/02/2026

What are your thoughts about the inverse direction? Can a developer use AI to become a CFO? You’ve done it the hard way, but are these new tools letting anyone with a thirst for knowledge do it a lot faster?

110

Jason Kealey @softwareengineering.ca · 07/02/2026

It’s gonna be a fun ride for everyone who isn’t afraid to learn new things

040

Jason Kealey @softwareengineering.ca · 06/02/2026

Not 4pm deploy to production and leave for the weekend?

110

Jason Kealey @softwareengineering.ca · 06/02/2026

What we’re working with • LLMs • AI agents • Machine learning models • Unstructured data (video, voice, text) • Modern data engineering and cloud tooling Location • Gatineau / Ottawa, NYC or remote DM me.

000

Jason Kealey @softwareengineering.ca · 06/02/2026

Open roles • Head of Data Engineering: pipelines, modeling, and foundations • Head of Applied ML Engineering: predictive models and interpretable signals • Head of AI Agent Engineering: agent workflows • Founding Product Engineer (Full-Stack): product surfaces and system integration

100

Jason Kealey @softwareengineering.ca · 06/02/2026

I’m hiring four technical leaders for a new AI company in the multi-unit space. The team • Two cofounders, both exited CEOs • Backgrounds in data and analytics and multi-unit operations • Backed by top-tier NYC VCs

110

Jason Kealey @softwareengineering.ca · 23/04/2025

Vanna is good for the loading up the schema plus docs into a vector db for RAG part, just the charts part are weaker.

100

Jason Kealey @softwareengineering.ca · 23/04/2025

I want the graph part too, that’s where Vanna w/ plotly is failing. It’s not rendering when I use booleans or timestamps and it does scatter plots at inappropriate times

100

Jason Kealey @softwareengineering.ca · 23/04/2025

Anyone got open source alternatives to vanna.ai for text to SQL? The SQL part is pretty good but the plotly charts it recommends are wonky.

vanna.ai

Vanna.AI - Personalized AI SQL Agent

310

Jason Kealey @softwareengineering.ca · 16/04/2025

I’ve also been playing with dbt - and considered sqlmesh instead. Chose to go deeper with dbt as I feel like sqlmesh’s real value shines when you want to avoid transforming the data both in dev and prod. … and I’m just prototyping stuff locally to play with different open source BI frontends.

000

Jason Kealey @softwareengineering.ca · 16/04/2025

Last week I did some experimentation with unstructured.io to extract content out of some pdfs. Also played with github.com/getomni-ai/z... as a more lightweight option. Overall, vision models do a much better job than classic OCR (ex: tesseract) on tables in docs.

010

Jason Kealey @softwareengineering.ca · 16/04/2025

Here’s a decent overview of the data pipeline orchestration tools on the market. dataengineeringcentral.substack.com/p/review-of-...

dataengineeringcentral.substack.com

Review of Data Orchestration Landscape

... and honest one ...

010

Jason Kealey @softwareengineering.ca · 10/04/2025

Does this API exist in both the hosted and self-hosted versions? When reading the docs last week I sometimes got mixed up in what features needed a subscription.

000

Jason Kealey @softwareengineering.ca · 09/04/2025

Nice! Hello! Is the api giving you just the metadata of the metric or also translating to the SQL you’d run to build charts like you do in lightdash itself?

100

Jason Kealey @softwareengineering.ca · 04/04/2025

Lightdash may be a good UI option for me, but then I’m defining metrics at the presentation layer and tightly coupled with it.

110

Jason Kealey @softwareengineering.ca · 04/04/2025

I’m looking for something to be able to express KPIs centrally and cleanly, and have the BI layer autogenerated from it. Dbt semantic layer could be that, but doesn’t seem like many open source BI layers support it.

000

Jason Kealey @softwareengineering.ca · 04/04/2025

I spent some time this week playing with some tools to setup a data pipeline for simple BI and data science. Played with airbyte, dbt, duckdb and metabase. Planning on trying lightdash next week. Trying to avoid hosted data warehouses and use open source for the full chain.

390

Jason Kealey @softwareengineering.ca · 26/03/2025

Keep it up! I’ve never felt motivated by hyping whatever I’m building to peers who’d never be clients/users.

000

Jason Kealey @softwareengineering.ca · 26/03/2025

I sold my solution by ignoring the sales rules and just flat out asking “how do you do <process>?” and replying we had an app for that when they outlined their manual process. I felt dirty not outlining benefits at first, but I later realized this opener was better aligned with my ICP (operations)

110

Jason Kealey @softwareengineering.ca · 25/03/2025

My past experiment with a tax form was bad because the LLM used basic OCR instead of something fancier for tables. And here I’m trying to do something more generic without knowing the form format ahead of time.

000

Jason Kealey @softwareengineering.ca · 25/03/2025

Imagine a government form with some weird tabular layout to shove as many fields into a condensed space as possible. Generalized use case is read/write to forms. Basically reverse engineering a domain model from a form. Azure DocIntel lets you do it well for a known form via training.

100

Jason Kealey @softwareengineering.ca · 25/03/2025

If making zip files named _final-website(2)-final-tuesday-3.zip is too complicated maybe something like dropbox with revision history baked in could work - at least for one file at a time.

120

Jason Kealey @softwareengineering.ca · 25/03/2025

That’s ironic but I guess totally expected since it’s their main revenue source hah

010

Jason Kealey @softwareengineering.ca · 24/03/2025

Interesting compensation model.

060

Reposted by Jason Kealey

Simon Willison @simonwillison.net · 20/03/2025

I published some notes on OpenAI's new text-to-speech and speech-to-text models. They're promising, but like other LLM-driven multi-modal models they appear to suffer from the prompt-injection-adjacent problem of mixing instructions and data in the same token stream simonwillison.net/2025/Mar/20/...

simonwillison.net

New audio models from OpenAI, but how much can we rely on them?

OpenAI announced several new audio-related API features today, for both text-to-speech and speech-to-text. They’re very promising new models, but they appear to suffer from the ever-present risk of ac...

3557

Jason Kealey @softwareengineering.ca · 21/03/2025

I like hearing “I used X library to do Y and it worked/failed”. Helps broaden my perspective about what’s out there. I dislike hearing “do like me and bathe in virgin blood to succeed”.

110

Jason Kealey @softwareengineering.ca · 21/03/2025

I don’t know. I’ve been deep in home renos last couple weeks. Haven’t been checking here much!

120

Jason Kealey @softwareengineering.ca · 20/03/2025

You’re right, she seems gone!

120

Jason Kealey @softwareengineering.ca · 19/03/2025

It’s sometimes easier to get something extra that doesn’t cost the founders more in the short term, such as an extra week of vacation or extra stock options.

030

Jason Kealey @softwareengineering.ca · 19/03/2025

My main lesson learned about economics is everyone is mostly wrong when predicting the future even if they have very logical reasons for their predictions. Because predicting the future is hard. But you still learn about the motivating factors behind people’s actions in the present.

110

Jason Kealey @softwareengineering.ca · 19/03/2025

Love that #econsky is here. A few years ago, I started listening to podcasts about the economy during my runs and I feel like it massively helped me learn more about how the world works.

120

Jason Kealey @softwareengineering.ca · 19/03/2025

I should get into the penetration testing business because there will be so many security holes to find these coming years.

010

Jason Kealey @softwareengineering.ca · 19/03/2025

C’est un peu inquiétant de voir qu’avec le climat géopolitique qui se réchauffe que le SCRS rémunère ses agents la moitié ou moins que des postes au privé www.canada.ca/fr/service-r...

canada.ca

Salaires et avantages sociaux - Canada.ca

Des salaires concurrentiels et un ensemble d’avantages flexible.

010

Jason Kealey @softwareengineering.ca · 19/03/2025

Toujours mieux qu’avoir à insérer une série de 25 disquettes pour installer un système d’exploitation comme dans le temps. 😂

110

Reposted by Jason Kealey

Jason Cohen @asmartbear.com · 16/03/2025

It’s surprising how much N, and how much separation you need to detect something like a 10% difference in A/B testing results. And a 10% lift in something (e.g. conversions) is pretty large. The math:

longform.asmartbear.com

Easy statistics for A/B testing and hamsters

A/B testing tools often lie about whether something is “statistically significant.” Here’s an extremely simple, mathematically sound formula to compute it for yourself.

281