Jag Reehal's thoughts on things, mostly product development
AWS Emulator serves the AWS APIs from a container on your machine, with no AWS account. We moved our CDK ephemeral environments onto it and tested CloudFormation, SQS, SNS, EventBridge and three kinds of Lambda against it.
AWS’s durable execution test runner runs a Lambda durable function in your test process, skips its waits and lets you answer its callbacks. We used it to test every branch of a payment approval in under a second.
You should be using AI tools to do everything from drafting your retro agenda to summarising last sprint’s tickets.
But facilitation remains an art.
You still have to read the room, spot who has gone quiet and find the real reason work keeps slipping.
Customers reach you through your web app, API, AI agents, connectors, widgets in partner apps, docs and support. You reach them through notifications. Hire UX people who can understand and influence all of it.
Read More →
Start everyone on Gemini. Move people who keep asking engineers questions to Claude Tag in Slack. Give a Claude seat to the people who build things or do long, private work, inside engineering or outside it.
That approach keeps you out of two traps: seats nobody opens, and staff stuck on a tool that can’t do their job.
Read More →It’s true, anyone can lead.
In twenty years I’ve watched people grow into leaders, helped a few get there, and grown into the role myself. How far each of us got depended on the trust, backing and incentives around us as much as on what we brought.
Before you say yes to a lead role, find out who will stand behind you when the decisions get hard.
Your coding agents repeat mistakes you corrected last week. A gardener reads what your team accepted on recent pull requests each week and proposes a lint rule or a sharper instruction when the evidence supports one.
The gardener opens each proposal as a PR with its evidence, and you decide whether it merges.
Read More →Shepherd takes a pull request from opened to approved.
Its review loop runs in your coding agent, reviews the change, fixes what it can and repairs the build.
Its gate runs in CI and decides whether the result earns an approval.
I give approval to a separate reviewer. You keep the decisions that need a person.
Read More →Ollama 0.35 runs decision models on your own computer. You give one a support ticket and a question like “which team should handle this?”, and it returns a percentage for each team instead of writing a reply.
ai-sdk-ollama 4.4.0 lets you call them from the AI SDK.
I ran 12 support tickets through the three new models and a small chat model on a MacBook Pro.
The decision models routed every clear ticket correctly.
On the tickets I wanted a person to check, two of the three models still sounded sure, and that changes how you set the rule that hands work to a human.
Every company I have worked at has had the same documentation problem: teams need information they can find, share and trust.
At most of those companies, the answer has been Confluence, and the pages drift away from the code they describe.
At a payments client, we took a different approach. We created a convention: every repo keeps its docs in the same folder and carries the same GitHub topic. A small build discovers them, and Astro turns them into one site that engineers and AI agents can both read.
