What a fabulous experience report from @brunopassos, who leads Developer Experience at booking dot com, who supports over 3,000 developers, on how they're using GenAI help them be more productive!!!
This is one of the best experience reports I've seen on this topic, complete with ambitious goals and rigor — he co-presented with the fantastic @beyang, CTO, Sourcegraph.
I've been meaning to write about this for week — but in the meantime, here are some of the fantastic highlights from their talk:
- Booking faced challenges with a sprawling codebase full of legacy code and features long-disabled from feature flags , causing developers to spend 90% of their time on unproductive tasks.
- They used Sourcegraph's AI and tools and rigorous measurement: they found 30% increase in merge requests, with smaller merges, and reduced review times.
- One of the discriminants of devs who experience these benefits vs. those who didn't: training. Bruno's team helped them with multi-day training, hackathons, etc.
- One sticking point: their GraphQL schema was over 1MM tokens, ensuring that any LLMs would generate poor results. They did a joint weeklong hackathon in Amsterdam, creating agents to navigate the schema.
So cool!
- They created another agent to help with legacy migration, able to parse and decompose functions over 10,000 lines long — this saved months of developer work.
- They built another code review agent automated the enforcement of coding guidelines, resulting resulting in cleaner, higher-quality code merges.
What a fantastic talk to show how vibe coding techniques can work at scale, and how it requires more than technology —
Keep up the amazing work, all!!!! cc @Steve_Yegge@sqs
✨ this sparks joy! ✨
Gemini 2.5 Pro in Agent Mode has quickly helped me tidy up one of the directories cluttering my desktop, @MarieKondo would be proud
Some people today are discouraging others from learning programming on the grounds AI will automate it. This advice will be seen as some of the worst career advice ever given. I disagree with the Turing Award and Nobel prize winner who wrote, “It is far more likely that the programming occupation will become extinct [...] than that it will become all-powerful. More and more, computers will program themselves.” Statements discouraging people from learning to code are harmful!
In the 1960s, when programming moved from punchcards (where a programmer had to laboriously make holes in physical cards to write code character by character) to keyboards with terminals, programming became easier. And that made it a better time than before to begin programming. Yet it was in this era that Nobel laureate Herb Simon wrote the words quoted in the first paragraph. Today’s arguments not to learn to code continue to echo his comment.
As coding becomes easier, more people should code, not fewer!
Over the past few decades, as programming has moved from assembly language to higher-level languages like C, from desktop to cloud, from raw text editors to IDEs to AI assisted coding where sometimes one barely even looks at the generated code (which some coders recently started to call vibe coding), it is getting easier with each step.
I wrote previously that I see tech-savvy people coordinating AI tools to move toward being 10x professionals — individuals who have 10 times the impact of the average person in their field. I am increasingly convinced that the best way for many people to accomplish this is not to be just consumers of AI applications, but to learn enough coding to use AI-assisted coding tools effectively.
One question I’m asked most often is what someone should do who is worried about job displacement by AI. My answer is: Learn about AI and take control of it, because one of the most important skills in the future will be the ability to tell a computer exactly what you want, so it can do that for you. Coding (or getting AI to code for you) is a great way to do that.
When I was working on the course Generative AI for Everyone and needed to generate AI artwork for the background images, I worked with a collaborator who had studied art history and knew the language of art. He prompted Midjourney with terminology based on the historical style, palette, artist inspiration and so on — using the language of art — to get the result he wanted. I didn’t know this language, and my paltry attempts at prompting could not deliver as effective a result.
Similarly, scientists, analysts, marketers, recruiters, and people of a wide range of professions who understand the language of software through their knowledge of coding can tell an LLM or an AI-enabled IDE what they want much more precisely, and get much better results. As these tools are continuing to make coding easier, this is the best time yet to learn to code, to learn the language of software, and learn to make computers do exactly what you want them to do.
[Original text: https://t.co/HdI3Jb9HmF ]
@myntra it is a massive family risk when a delivery agent from Myntra visits our house with a package and takes advantage of the elder member in the family. When I call Myntra agent (Anmol), I am told we cannot do anything as we cannot trace the person who visited our house.
In 2009, Stanford business professor Tina Seelig split her class into groups and issued a challenge:
Each group had $5 and 2 hours to make the highest return on the money.
At the end, they'd give a short presentation on their strategy.
What happened next was fascinating:
For the first time in a really long time the $250B Indian IT services & business outsourcing market can be disrupted
Let’s dive into where we see large opportunities for new entrants, and how founders should be thinking about this space as a whole
🧵
It's a QR sound box. It's a card terminal.
It's both.
Introducing The Mini.
A 2-in-1 payment device for those who always want more.
At 1/3 the cost of a regular PoS terminal, the Mini is truly an innovation built for Bharat.
Coming soon at a counter near you.