Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
This term seems to be quite in use in English-speaking communities. I'm curious what it is? Is it like two students code together on a single PC or what? Is this organization (whatever it is) is only used in US?
Pair programming is one of the main practices in Extreme Programming (XP). It does literally mean two people working on one computer, usually one at the keyboard (often referred to as the driver) and a partner (referred to as the passenger or shotgun). It is reputed to improve productivity and the quality of the generated code as well as enforce group ownership of the code - another tenent of XP.
http://en.wikipedia.org/wiki/Pair_programming
Pair programming is a software development technique in which two programmers work together at one keyboard. One types in code while the other reviews each line of code as it's typed in. The person typing is called the driver. The person reviewing the code is called the observer1 or navigator. The two programmers switch roles frequently (possibly every 30 minutes).
While reviewing, the observer also considers the strategic direction of the work, coming up with ideas for improvements and likely future problems to address. This frees the driver to focus all of his or her attention on the "tactical" aspects of completing the current task, using the observer as a safety net and guide.
When in doubt, ask Wikipedia: Pair Programming. The general idea is to have one person writing code while the other scans for mistakes and cohesiveness.
An extension of Pair Programming sometimes used by practitioners of Test Driven Development is Ping Pong Pairing.
Ping Pong Pairing works something like:
Write a failing test (developer A)
Implement code that makes the test pass then (optionally) Refactor (developer B)
Write a failing test (developer B)
Implement code that makes the test pass then (optionally) Refactor (developer A)
and so on...
One of the benefits of Ping Pong Pairing is that it's tough for either developer to sleep very long ;-)
Paired programming is when two developer work on the same story card sharing a single computer and keyboard. It is considered an extreme programming practice. Extreme programming takes something positive, in this case a code review, and takes it to the extreme. The benefits beyond the continuous code review are as follows:
Improved quality: A pair of active programmers working on the same story card will complete the card with less defects
Improved productivity: a pair is less likely to be slowed down if not outright blocked when solving a problem. Furthermore, it is harder to take an email or web vacation when you are working with a partner ... you don't want to let the partner down. You will solve the problem with a cleaner design and less lines of code when working as a pair
Eliminate silos of knowledge: With rotating pairs, you will learn application and domain business knowledge across the team. The team is less likely to be blocked because Sue when on vacation and no one else knows her code.
Knowledge Transfer: Rotating pairs teach new skills (engineering and domain) to each other as they work together. The level of the team will rise for everyone and the knowledge propagates through the team.
Team self selects: The team learns one anther's skills and will quickly weed out someone that is not performing.
Related
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
... and how to prove to management that use-cases can be informal and still useful?
Hi folks,
I came in the middle of a project and found out that there are no use-cases, user-stories, requirements, neither anything similar to a specification. Since the deadlines are short, the current dev team don't want to spend time on such things. I wanted to join that project, but by digging more I found out that the current development adds features just by considering their "wow-effect" and chooses what to add just by using the easiness that the underlying technology provides. I was surprised how they have managed to go so far (more than 4 months) without requirements, but this is what we have now. I believe that the way they have chosen is the most sure one to kill the product which has a good marketing value.
Am I right, and what would you do in a similar circumstances to prove the dev team/management to make use-cases/requirements before moving forward? Thanks in advance, kh.
P.S. Two copies of Cockburn's book are on the bookshelf...
You should give your colleagues the use-case spiel :D Tell them that use-cases are useful as they're:
A way of capturing business processes in a manner which is reasonably comprehensible by all stakeholders. This helps to bridge the gap between programmers, clients and users.
Traceable units of functionality. Use-cases are formed (ideally) in the analysis phase, referenced in the design phase, and can be used as sources for test cases later on.
Quick and easy to write up and useful, even if informal.
If you need more ammunition, you might want to read Use cases - Yesterday, today and tomorrow by none other than Ivar Jacobson.
If your colleagues still can't see the potential usefulness of use cases as a business analysis tool, then they're probably beyond help :P You should remind them that they're developing software to meet other people's needs and solve their problems in the long term, not to ostentatiously impress them in the short term with petty gimmicks. And so a little bit of direction and specification helps. Even if the use-cases themselves don't prove to be that useful, the simple act of coming up with them will force your colleagues to consider the actual underlying purpose of the software.
Ask questions, of both sides. Of development, ask them if they are certain that all of the ways in which they have considered using the application are all of the ways in which the end-users will want to use it; if they say they have, ask for proof. Of management, ask if they've ever used software that does everything they want, but still ends up being hard to use (they will have). These questions will seed the concept that what will be delivered might not be what is desired, on both sides; use that seed of an idea, then, to open up discussions (not documents, not at the start) on how the software will be used, and in what way any differences can be resolved. They'll get around to use-case documents eventually.
I am a product manager by profession, and my first reaction to your post is that ideas can come from anywhere, and if the dev team has decent ideas they should be incorporated into the product.
Having said that, a product can not develop a soul (a simple message) through a string of disconnected ideas that do not serve the ultimate purpose: solving the needs of a target user. And, ultimately it boils down to making the case that time is better spent on requirements/use cases that make sense for the product, while the opportunity cost of not having a clear strategy/end goal will lead to too many chefs and a jaded product message.
The ultimate way to make this message hit home is to involve other stake holders and have development demonstrate their work. Eventually, there will be disagreement and a more formalized (less cowboy) approach will lead to a more refined and simple product.
One of the problems you mention is tight schedule and scope creep induced by the devs themselves. Explain them, that by using use cases you can earn time by dropping features, which will potentially end up on the "never used" pile. With use cases you can find out what are the features customers need and will pay for and by removing unimportant features out of the scope you would have time to implement. Use cases apart from defining the scope also help to identify all the stakeholders, which might help you to focus even better while defining the scope and prevent forgetting about trivial things, which are not so apparent, but are a must if the product should be usable. The third most important thing about use cases is that they allow you to start thinking about corner cases which might be important for the customer before development and therefore you can find out with the customer what would be the ideal solution instead of letting the coder decide on his/her own under pressure of deadline.
Just show them.
Example is not the best way of educating people, it is the only one.
Lead by example focusing on extensions and exceptions. In other words emphasize the failure scenarios because everyone knows how the system should work. The real value of written Use Cases is identifying what should happen when something goes wrong.
That noted, consider you may have to live without written use cases. And, for the environment you describe, a major win is any sort of requirements documentation. Screen comps and/or prototyping are often easier to introduce.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 1 year ago.
Locked. This question and its answers are locked because the question is off-topic but has historical significance. It is not currently accepting new answers or interactions.
I've been thinking about the on going "revolution" in UI design and metaphors for interacting with the computer via a GUI and I'm suprised that as long as computers have been accessible through GUI's that programmers are still searching for the best way to allow the user to interact with their programs. It seems that most of the work centers around astetics(which I understand are important) but I don't understand why we are still looking for the magic bullet in UI design.
My question is: Why is UI design and components not a solved problem with accepted and understood approaches?
Probably because like most things, design (and tech, in general) are constantly changing, being worked on and revised. To say that one of the most crucial elements in software can be 'solved' would be an understatement and would be constantly changed again. There is no true definition to the 'perfect' GUI, only because you don't know who your users will be (power users versus casual, more input required vs less).
perfection is a moving target
Jacob Nielsen rightfully said about ten years ago that users don't scroll. This isn't true anymore.
Users get trained to user interfaces. Windows 7 doesn't show a system menu icon in the top left corner for many apps (e.g. in explorer), but you can still go there and invoke the system menu. Took me a while to notice the icon was missing for some apps - while using it.
(There are probably much better examples.)
The optimum isn't obvious. Consistency is core in UI, but only deviation from consistency can lead to improvements. You just can't optimize for "most consistent" or "most creative", both will fail.
it's a cross-domain skill. How many people are programmers, designers and neuroscientists? How many CS university courses teach cognitive models and how they apply to user interfaces? How many programmers pondered muscle memory, feedback loops and cognitive load?
UI's are still designed largely by programmers and sometimes fixed by designers after the fact.
effect is hard to measure
Take the Microsoft Office Ribbon: Judging from the responses, it seems to work better for many, yet is harder by orders of magnitude for others. It was a bold step, no doubt, but was it good? Microsoft does run UI tests, and they did it for the ribbons - whether they screwed up the tests, whether office politics won over facts, or wether the backslash was just wasn't forseeable in the data, I don't know. (But I'd seriously like to)
How many shops can afford user tests? Everyone can do hallway usability, but that just ensures you don't suck.
Skimming along the line
There is low pressure for the perfect UI, there is high pressure for a good enough UI. Given the lack of common knowledge and the high cost of improvement, perfect would not be affordable. The "Apple tradeoff" involves a higher price and technical shortcomings. They are pushing the limits (good!) with bold steps (very good!), which captures a notable but not major market segment. Still they are far from perfect.
I think if you ask Henry Ford the same question about designing automobiles you would have gotten an answer that would equally apply to your question today.
And that answer is, we're still in the infancy of human computer interaction design and we don't yet have enough data to design genuinely ideal systems. And, even if we did we don't yet have the ability to manufacture such an ideal system at an affordable price point.
Much like Henry Ford could not have designed the Bugatti Veryon in his day, nor could he have built it if he could design it. Or the Prius for that matter.
No, User interfaces isn't that subjective. Ergonomical matter is a scientific topic.
Think about that :
Today, everybody uses a computer. That was not the case 30 years ago.
Today , everybody uses a glass surface to access data. That was not the case 30 years ago.
Today, you've got several devices to access your data. That was not the case 30 years ago.
Today, data is collected everywhere. That was not the case 30 years ago.
Today, you can even control your data with glasses. That was not the case 30 years ago.
There is no magic bullet. just like nature, we're talking about an evolutive and living ecosystem, in the pure darwinian way.
UI design is to make people who have less knowledge about it but can easily understand the application and use it comfortable. That is core challenge of the UI design. So it evolves just like a robot. There is no end to perfect design. As along it makes the users to use easily then it is a perfect design.
User Interface is a very subjective subject, what might be ideal (graphically pleasing, efficient) for one person or task might not be ideal for another task or even another person doing the same task.
Also, the different platforms on which GUIs are implemented is ever changing and thus needing GUIs to evolve to meet specific platform demands (touch screens, ie. lend themselves towards a completely different user interface, then a mouse based platform, or even something like an ATM)
However, there are classes and books written on the subject, so there is some level of continuity in the area that has been there for quite some time.
User Interface is a very subjective subject, what might be ideal (graphically pleasing, efficient) for one person or task might not be ideal for another task or even another person doing the same task.
Also, the different platforms on which GUIs are implemented is ever changing and thus needing GUIs to evolve to meet specific platform demands (touch screens, ie. lend themselves towards a completely different user interface, than a mouse based platform, or even something like an ATM)
However, there are classes and books written on the subject, so there is some level of continuity in the area that has been there for quite some time.
In short, TECHNOLOGY.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 5 years ago.
Improve this question
I have been doing TDD for the past 3 years. We were a small company, and we had very solid support for most aspects of the agile process from management. Everyone on the development team was sold on the process. And thus, the upfront investment it usually takes to build fixtures was accepted knowing it would pay off along the way. (Code that starts an http server, code that populates sql databases before tests, etc). Documentation mostly happened in the tests and help requests were usually presented in the form a failing test.
Now I moved to a bigger company, and while management is supportive of the Agile process, teammates are a mixed bag, some of them see it useful, some of them do it because of management and some don't see the value. It's been a challenge to convince people to spend some time building fixtures or to convince a team member the best way for me to help him if he took the time to write a failing test.
So what do you think is the best way to sell TDD to a hesitant teammate? The objections are usually : 'It's an unneeded cost', ' we can always write tests after the fact for parts that are important', 'it's a buzz word, teams pick it up and then it falls to the side as the heavy grind begins' etc.
"the best way to sell TDD to a hesitant teammate"
You can't. Don't waste time "selling".
Instead, invest time in "proving".
Just do it. Be successful. When people ask what the secret of your success is, then reveal the TDD. Not before.
simple -- maintainability. TDD gives you the ability to make changes, and see where those changes affect the rest of the code. The larger the code base, the more imperative it is that there be tests to validate any new changes.
correctness. Although tests can themselves be broken, eventually they reach a point where they make sure the components are doing what they are supposed to. The better the developer, the faster that is.
another advantage is that TDD informs the design of the components in the system. If you are trying to test something, and the test is too complicated, it probably means you need to break the problem down into smaller parts...
to sell it to people, you say that in the long run it makes adding new features cheaper, and reduces the risk of breaking existing functionality. So it reduces cost.
For the hesitant teammate, be patient, wait for an opportunity, then pounce. In software development there will undoubtedly be an problem where TDD would have prevented or mitigated the problem. Be on the lookout for such an opportunity. Work with him/her to create a test(s) that should have been developed from the beginning. However, make sure you craft your message in such a way to not embarrass your teammate.
I agree with S. Lott, you can't "sell" them you need to show the value.
One of the most effective ways to do that is with pair programming. Granted you have another "sell" problem convincing people that pairing is an effective approach, but after some time you may convince/convert a developer or too.
TDD was a tough concept for me initially, but now I can't imaging programming any other way.
I think Joel's post explains very well why testing is A Good Thing™.
I don't think he ever uses the phrase "TDD", but it's got some great info.
Show them this site: WeDoTDD.com - actual company team use cases. Those who are successfully practicing TDD in real companies.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
I have worked on a few multi-cultural projects (programming languages are universal, social norms and mores are not) and it's always interesting to see how the team dynamic works cross culturally. I'm not talking about coding differences, I'm talking about basic ground rules for communicating cross culturally at the start of the project. Good team building exercises, using small teams vs large teams, isolating functionality to make all developers feel as if they are contributing, fostering respect, and etc.
In our increasingly multi-cultural industry, what works and what has failed?
I looked into this in some detail a few years ago and came to the following conclusions (in no particular order):
The outsourcing organisations we looked at (all Indian) had a very strong process base. I don't know if this was cultural or just the way they chose to set themselves up (possibly a bit of both) but we felt this was likely to be a real issue.
They were talking about being a five on the Carnegie Melon Maturity Model (Google it but basically that means they've defined and documented everything up to and including what happens when someone farts), we were typically running around a 1 or a 2 (roughly equating to crossing your fingers and hoping for the best).
Our process level was largely driven by our clients who didn't have any interest in signing off specifications (for good reasons and bad), wanted people who understood their business and would fill in the gaps, and wanted to change their minds three times a day. As much as many of these factors infuriated the programmers in the UK we understood that they were never going to change.
This was possibly our biggest concern - we didn't feel we could come up with a process model that would work for all three groups involved (the clients, the UK based IT team and the Indian based outsource team).
So first thing is - work out what your process is and work out whether you honestly think you can make it work for all parties involved. It's easy to say "we're going to do agile" but how are you going to get that to work when one party is 1000 miles away? Alternatively if you want to go a solid waterfall route, is that realistic given your clients?
Second, understand the ingrained cultural differences within your teams.
My experience (and I obviously generalise here) is that programmers from the US and the UK willingly (sometimes too willingly) question authority and assumptions. Ask them to do something dumb and you're likely to find yourself being told that you've asked them to do something dumb in no uncertain terms and they'll then proceed to tell you what you really want.
That's not the norm globally. Many Indian developers I've worked with don't question things in the same way. That's not to say they aren't as bright, they just apply their intelligence to delivering what you've asked for, assuming that you had a good reason for doing so.
You can make a case for either of these being good / bad (I've lost count of the number of times I've heard developers question what they're told and say how things should be despite not understanding the basics of the industry they were working in), but the important thing is that they're different and they'll clash.
So the answer is likely to be that you're going to need to feel out the teams involved and, based on that, pick out ways of working that are comfortable for both of them.
Yes, get video conferencing set up, get each time to visit the other site (it makes a big difference) and where possible get people talking even when it's not strictly needed in the early stages, but most of all make the effort to understand the groups involved and design a dynamic that works for all of them - imposition of one world view on the other won't work.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
From time to time, there will be student attached to our projects, i would certainly like to assign him/her many things to do so can learn more. But alot of times we are resigned to assigning stuff like documentaiton, updating of ui mockup screens etc. As problem is that is it bit hard to trust the quality of work provided by students and another thing is that they are still young and their enthusiam may not be there.
How do we better utilize them such that they really cut down our workload and also in turns mean learning more stuff which will aid them in their future job opportunies?
I am afraid it might sound disappointing but it is not the best idea to utilise students to cut your organisational unit workload down. Probably, if your goal is cutting workload the best thing is not to take students. Read on to understand why.
Though you haven't specified the level of work-related expertise the students possess, nor did you mention the duration of their attachment, I assume from the tone of your question that their expertise is not sufficient to hit the ground running. It is also reasonable to assume that they are not staying for longer than 2-3 months.
The essential benefits your organisation can extract even given the limited timeframe are:
Notice and grab talented workers before they even get to the job market. Later in their working life they are likely not to be that easily available.
Turn every student into your organisation salesman. Let them tell everyone how good your product is, bring you in contracts in the future or make their peers envy their work experience increasing the pool of good candidates for your company.
Outsiders can help cast a fresh eye on your processes, procedures, product, expose inefficiencies etc.
Learn from them the latest stuff taught at universities.
Boost your time morale: Maslow theory, "esteem needs". Even the most junior member of your team becomes somewhat more senior, since these students have yet to achieve that position.
Cutting down workload means that you'd need to find a set of tasks which is fairly independent, does not require knowledge or skills that the students do not have and needs much of your team's time to transfer. The tasks cannot be strategically important in case they cock it up, not can it be operationally important. Hence you left with some dusty requests for management reports or research and development projects.
Chances are that R&D considered to be more desired work within your organisation and if you give exclusively to students some people feelings are going to get hurt.
How long are the students around for? When we have had students on-site for up to two weeks there was not much other then testing type work we could give them.
If the student has enthusiasm you code do some pair programming through a bug and let them write the unit tests for verifying the fix.
Even if you don't normally do pair programming, I find that with a junior dev it is sometimes productive to have him/her do pair programming with a more experienced developer, for the following reasons:
I wouldn't assign coding tasks to the junior developer alone, because his code would have to be closely reviewed by someone else anyway and quite probably rewritten or changed substantially.
On the other side, how can a junior developer learn if not by programming? So, you want him participating in some way in programming tasks.
You get some of the advantages of pair programming: the most experienced dev is less prone to make silly mistakes (even a very junior programmer can point things like 'hey, you made a typo there') and less likely to goof off checking stackoverflow.com every 10 minutes during the pair programming session.
Of course I also would rotate the junior with several seniors during the day, so they don't feel 'slowed down' or annoyed by the young guy for extended periods of time.
Why not assign one or more engineers as "sheperds" to the student and let them oversee their work or even better pair with them. The student will gain a good understanding of your project and real work and have a known fallback when in trouble and someone who can give provide direction.
The sheperd/mentor gains a fresh perspective, and the joy of teaching.