Learnings from our first Software Teams Survey of Developers and Collaborators
This post was originally shared on April 11, 2024 on Medium. I'm experimenting with Substack, and figured a good start would be to migrate my earlier content here.
In December 2023, we conducted a survey with a goal of hearing from developers and their collaborators building software products, projects, and companies to learn about how we might better support these individuals and their teams.
Two weeks ago, as part of an experiment to open-source more of my own learnings as a founder and product manager, I asked on LinkedIn if anyone was interested in an aggregated, anonymized version of the results of this survey. The answer was universally “Yes” so this post is a follow up to share our learnings.
Disclaimers
This survey was not meant to be indicative of global trends or patterns. Rather, it’s a point-in-time snapshot of trends amongst the respondents. We had 55 responses to the survey, although many questions were optional and we segmented certain questions depending on whether the respondent currently codes or not.
Additionally, we shared this survey primarily through our personal social networks, so responses from specific demographics, such as founders, CEOs, CTOs, experienced developers, and people based in California (both SF/the Bay Area and Southern California) and New York City, are more prevalent.
For more quantitative data and generalizable trends, if that’s what you’re looking for, you might instead look at surveys run by larger enterprise organizations or developer groups. Three larger surveys that our team found interesting were:
2023 Stack Overflow Developer survey results
JetBrains 2023 State of the Developer Ecosystem survey results
Hired’s 2023 State of Software Engineers survey results
Reveal Survey Report: Top Software Development Challenges for 2023
While we should not generalize the results of our much smaller-scale survey, we were heartened to see that there were certain consistencies with patterns shown in the much larger scale surveys listed above, which will be called out once we get into insights and analysis.
Let’s dig in!
2023 Developer and Collaborator Insights and Analysis: Demographics
Demographic information is helpful because it grounds the rest of the information collected through a better understanding of who is responding to this survey and their relevant experience and circumstances. The vast majority of our respondents identified their work status as employees of a company (50%), founders (38%) or self-employed (16%). Note that the total is >100% because respondents could check multiple options if relevant to them.
In terms of experience levels of their current position, the majority of respondents again identified as founders (38%). This was followed by lead/principal level (29%), then senior level (20%), then mid-level (7%). A much smaller percentage of respondents identified as executives or junior level.
In terms of the description of their role, CEO (25%) was the most common, followed by CTO (15%). Given the levels of experience, the CEO and CTO respondents seem like they are mostly or all founders as well.
Outside of CEOs and CTOs, product manager (15%) and backend developer (10%) were the next most common. There were a number of other developer respondents, with specific roles varying from Security Developer to Frontend Developer, Data Engineer, and Full Stack.
Survey respondents were overwhelmingly technical, with the majority coding for both work and personal projects (44%). Some coded only for personal projects (17%) while others code only for work (9%). Just over a quarter of respondents (26%) responded that they do not code.
Background and Experience with Coding for Technical Respondents
Of the 40 respondents who identified that they code, we had specific questions about their background and experiences coding. The majority of respondents (35%) had 10+ years of professional programming experience. This likely reflects our network demographics and has a bias towards more experienced respondents.
In terms of which platforms respondents develop for, the most popular answer by far was web, with a nearly even split between a frontend focus (70%) and with a backend focus (68%). This is likely indicative of respondents who build web applications as full stack engineers, writing code across the entire application. Another popular platform was mobile, with iOS (30%) getting nearly double the development attention of Android (15%). A smaller percentage of respondents develops for terminal (23%) and other more specialized platforms such as IoT / embedded, gaming platforms, and infrastructure.
In terms of the primary programming languages used, where each respondent could list multiple languages, we saw significant overlap between our 40 respondents’ answers and the wider developer surveys referenced above.
The most popular language by far was JavaScript (70%) which lines up with the focus we saw on web application development from our respondents. We unfortunately had a survey bug where Javascript was duplicated among the responses, so we manually de-duplicated the data and created the chart below.
The next most frequently used language was Typescript (53%) followed by Python (43%). HTML / CSS (38%) and SQL (30%) were also frequently used. Other notable languages included Go (15%), Rust (10%), Java (10%), Elixir (8%) and Ruby (8%).
Smart contract languages such as Solidity and Move were write-ins as an “other” option, as was Cypher, so potentially those were slightly underrepresented by respondents since it was not an immediately available options.
Developer Tools: How Much Is AI Used for Writing Code?
When asked if developers currently use any AI tools when coding, of the 31 respondents the majority use ChatGPT (68%) and GitHub Copilot (55%). Other tools, if mentioned at all, were significantly less popular, with Claude and Cursor each only getting one response. That said, this survey was in December 2023 and it would not surprise us if the discovery and usage of other AI tools has meaningfully increased. We would also expect ChatGPT and Copilot to continue to dominate AI usage among developers for coding in the near-term.
Developer Tools: Resources, Technologies, and Discovery
Of our respondents who code, most discover new tools, resources, and technologies through friends (62%) and colleagues (54%). Communities such as Discord groups (49%) are also popular, as are specific news sources such as hacker news (46%) and blogs they follow (44%). Interestingly, search (36%) and Product Hunt (13%) and social media were identified as far less popular sources.
When it comes to paid resources, books were the top resource people paid for personally, followed by hosting costs, and courses. This indicates a significant investment in growth and learning among respondents who code. For folks paying for hosting, we expect they are likely either working on their own projects or early-stage founders.
Resources used by those who coded, and which were paid for by their company, were topped by hosting, messaging (e.g. Slack), and project management (e.g. Jira).
Tools that were most likely to have been used for free included component libraries, design systems, data / API access (e.g. weather API), testing / CICD (e.g. CircleCI) and build / pipeline tools (e.g. Expo).
Tools that were most likely to be used if a company paid for them included paging / monitoring (e.g. Sentry), Hardware (e.g. AI GPUs) and the previously mentioned project management and messaging tools.
Interestingly, wellness apps (e.g. Headspace) were equally likely to be paid for by an individual or their organization, and twice as likely to be paid rather than free usage. Professional coaching was mostly not used by respondents, but if it was, their organization most likely paid for this service.
Background and Experience: Collaborators Who Do Not Code
26% of our respondents said they don’t code, and so we have a much more limited set of results from this group. Of those who do not code, when asked how coding relates to their personal and professional experience, most had learned to code but do not actively use this skill (60%), some have never learned and have no plans to but work with developers (33%) and some are currently learning (13%) or would like to learn to code (13%).
As for the respondents who code, when it comes to using AI tools (in this case at work and not to write code), ChatGPT dominated (over 73% responded using it). Nothing else came close. The next most common response was not using AI tools (13%) and we had one response each for different tools such as Bard, Notion AI, Grok, Otter, and others. Note that this was an extremely small sample size however, with only 15 respondents.
In terms of discovering new tools, resources, or technology, responses were similarly likely to rely on colleagues (67%) and friends (53%). Communities (47%) and blogs (47%) also were popular. Search (40%) was slightly more popular than for coders, but this might also be due to small sample size.
In terms of resources that were paid for personally, this cohort responded overwhelmingly with books and courses.
Of resources paid for by their company, messaging (e.g. Slack) and design collaboration tools (e.g. Figma, FigJam) were the most common, followed by note taking (e.g. Notion) and project management tools (e.g. Jira). This group was understandably less likely to use tools for paging / monitoring, hardware (e.g. AI GPUs), and technical collaboration (e.g. Storybook). This potentially indicates a gap in tools for non-coding product team members and founders who are still working on or responsible for software products, but not as intimately involved in the development and testing of their product’s code. We will be delving into this more as a team in the future.
Bonus: What Did ChatGPT “Think” Of Our Survey?
In addition to the questions synthesized above, we fed survey results into ChatGPT and requested analysis and synthesis. This included more free-form responses, and led to ChatGPT identifying a set of themes and experiences.
Here is the verbatim response we got from ChatGPT which identified a number of challenges and pain points among developers and collaborators when it comes to creating and managing software products:
“The responses you’ve provided span a wide range of challenges and experiences in software engineering and technology leadership. Here’s a grouped summary:
Project Management and Development Challenges:
- Environment setup and maintenance.
- Struggles with clarity, prioritization, and speed in teamwork.
- Merge conflicts and wasted effort on unused features.
- Difficulty with context switching and managing time demands.
- Release cycles being too long and lack of customer feedback.
- Challenges with database scaling and understanding cloud expenses.
- Tooling fatigue, syntax issues, and dependency management.
- Slow build processes and deployment times.
Team and Collaboration Issues:
- Need for better team communication and collaboration.
- Challenges in integrating with poorly designed APIs.
- Difficulties in getting engineers involved in the design process early.
- Remote collaboration issues and lack of spontaneous interaction.
- Cross-team work inertia and knowledge imbalances among teammates.
- Poor communication and passive-aggressive behavior in teams.
- Misalignment on strategy and vision.
Business and Leadership Struggles:
- Business growth challenges and financial pressures.
- Difficulty in finding a cofounder and identifying real problems.
- Navigating internal politics and bureaucratic structures.
- Leadership making uninformed decisions.
- Maintaining visibility on developers’ day-to-day production.
- Difficulty achieving product-market fit.
Personal and Professional Development:
- Lack of coding practice leading to skill atrophy.
- Learning new technologies and keeping skills updated.
- Adapting to the use of AI in workflows.
- Seeking high-quality feedback and user engagement.”
What’s Next: Continued Learning, Building, and Experimentation
Our team is exploring three fronts in parallel. First, we are conducting ongoing research to better understand the challenges, experiences, and needs of software product teams and developers and collaborators working in these organizations.
Second, our developers are spearheading a technical R&D exploration into what we can do in terms of providing a valuable solution to some of the challenges we’ve identified, specifically around helping software product teams build high quality products faster and facilitate better understanding of changes.
Finally, we are also taking on a limited number of early design partners to provide a personalized software simulator solution for their teams.
Right now, we are focused on helping early-stage software startup teams and software consultancies in this category. If you’re interested in this, please reach out at nadia [at] ethoswallet [dot] xyz.
Survey 2.0
We recently kicked off a new survey to learn more about product teams and software collaboration processes. If you’re interested in sharing your feedback, you can take that survey here: https://bit.ly/2024-software-survey . Note that all questions are optional.