Yupp, it’s already here. If you have no clue what TW Radar is about, feel free to check my post for the last year edition (http://gebski.tumblr.com/post/51321405824/bandit-on-your-6) or go straight to the Radar’s website: a picture’s worth the thousand words: http://www.thoughtworks.com/radar/#/

Short map:

  • Adopt - good stuff, mature stuff
  • Trial - promising, do some dogfeeding or try in non-critical scenario
  • Assess - not for everyone, not every time; PoC it first
  • Hold - no go

To the point then: what’s new, what’s cool, what’s interesting and are there any surprises - let’s go through the categories:

Techniques:
http://www.thoughtworks.com/radar/#/techniques

  1. DOM abstraction + JS testing on Node.js gets straight to Adopt - can’t agree more.
  2. Windows infrastructure automation finally gets some love (appears in Adopt)! It’s awesome and I’m all for, but IMHO there’s still very little contribution in the community (when compared to *nixes).
  3. Server-less provisioning with Chef/Puppet appears in Trial (both with provisioning testing!) - personally, I’m much more for the distributed version (client-server).

Tools:
http://www.thoughtworks.com/radar/#/tools

  1. Plenty, plenty of new entries - that’s both good and bad. Good, because things are going on and bad, because the potential maturity may not be sufficient for enterprise.
  2. Personally I’m happy with the following entries: D3 in Adopt (it requires a lot of effort, but the results may be ground-braking), grunt.js, Logstash & Phantomjs in Trial; Docker, Octopus & Xamarin in Assess. Where’s Icenium though?
  3. TFS remains in Hold. Die in fire.

Platforms:
http://www.thoughtworks.com/radar/#/platforms

  1. Now it should get really sexy, and it does, but not exactly in the way you expect: Adopt category didn’t change since last year, so there’s no new platform that got that proven within last 12 months. Not many changes in Trial as well - Hadoop 2.0 didn’t make a breakthrough either.
  2. Plenty of new stuff in Assess category: TypeSafe’s Akka (my favourite!), Google’s SPDY, Twitter Storm (as an adopter, can’t agree more) and at last but not least - Web Components as a standard.
  3. There’s also a lot of interesting stuff going on in Hold: bane of CMS as a platform for complex IT solutions (hail to that! do you hear that, Sharepoint?), death wish to traditional, rigid-structured enterprise DWHs.

Languages & frameworks:http://www.thoughtworks.com/radar/#/languages-and-frameworks

  1. No surprises - Adopt stays the same as it was a year ago (but it was some kind of surprise then). I really wonder how many people really use Clojure in production code and how hard is it to hire a Clojure programmer.
  2. Some new interesting contestants in Trial category - Go (ain’t it too early yet?), Hive (yepp, it’s so much more convenient that writing the Map/Reduce jobs on your own) and … Reactive Extensions. About the last one - personally, I am a big fan and I find it a true masterpiece created by ultrasmart minds - but in my opinions people still are learning how (or rather “where”) to use it. It’s that different to stuff that was available before.
  3. Assess is a big bag of new stuff. Most noticeable: Elixir (Erlang ain’t so hipsta anymore? :D), TypeScript (my new web dev love) and Yeoman (Yo + Grunt + Bower, can’t work w/o them).

To summarize:

There are no big surprises, in general I totally agree with the TW report (well, that’s why I’ve investigated many of these technologies before), but I’d still add few points that are missing:

  • web app frameworks are completely missing and IMHO it’s a mistake - they matured & proven themselves a lot within last year
  • if MongoDB is in Adopt for platforms, where should Apache Cassandra be? ;P
  • Personally, I give all my votes to bring Apache Cordova to Adopt - I believe that it’s a matter of (short) time until native dev dies on mobile - unification is the key, so everyone can make money of that.
  • I am very happy to see that TW keeps “big enterprise solutions” in Hold category for the next year - it should be emphasized as strong as possible - XXI century says ‘no’ to humongous, untestable clusterf*cks of 20yo code, that give job to armies of drone consultants who don’t know any honest work.
Share this post