I did have an initial key insight which led to a repeatable strategy to ensure a high level of fidelity between DTU vs. the official canonical SaaS services:
Use the top popular publicly available reference SDK client libraries as compatibility targets, with the goal always being 100% compatibility.
You've also zeroed in on how challenging this was: I started this back in August 2025 (as one of many projects, at any time we're each juggling 3-8 projects) with only Sonnet 3.5. Much of the work was still very unglamorous, but feasible. Especially Slack, in some ways Slack was more challenging to get right than all of G-Suite (!).
Now I'm part way through reimplementing the entire DTU in Rust (v1 was in Go) and with gpt-5.2 for planning and gpt-5.3-codex for execution it's significantly less human effort.
IMO the most novel part to this story is Navan's Attractor and corresponding NLSpec. Feed in a good Definition-of-Done and it'll bounce around between nodes until it gets it right. There are already several working implementations in less than 24 hours since it was released, one of which is even open source [0].
https://threeemojis.com/en-US/play/globs
It was inspired by 2025 by thomaswc, a 45x45 connections-like puzzle. Globs jumped off from there and it's been very fun to make. I have AI generating the puzzle groups and it keeps surprising me everyday with what it comes up with. I've got demos up for over 20 different languages, and many different sizes of puzzle. Just recently, I got the puzzle to be generated daily for American English, British English, High German and European Spanish. It can also do custom theme puzzles like the following:
Big YC https://threeemojis.com/en-US/play/globs/en-US/demo?size=big...
Jumbo HN https://threeemojis.com/en-US/play/globs/en-US/demo?size=jum...
There is still some bugs I am tracking down (open the page in a private browser if you hit stale data) but the game has really come together lately and been a lot of fun, I hope you all like it!