TL;DR
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
Software engineer Neil Kakkar reports merging 11 times more pull requests per month at AI-native startup Tano than at PostHog, based on his own work data. His account describes faster individual output alongside new challenges in context, focus and design; it is a personal comparison, not an industry-wide study.
Software engineer Neil Kakkar says he merged 11 times more pull requests per month after joining AI-native startup Tano than he had at PostHog, according to a personal comparison published by The Pragmatic Engineer. The account offers a data-backed view of how AI tools and workplace culture can change one engineer’s output, while also describing new costs in focus and shared context.
Kakkar compared work at PostHog, where he spent four years, with his first eight months at Tano, where he joined as a founding engineer. He says he shipped 2.4 times as many pull requests at PostHog as at Bloomberg, where he began his career, and 11 times as many at Tano as at PostHog. He also summarizes his Tano output as roughly tenfold higher. The figures are his own records, not a controlled industry study.
At PostHog, which Kakkar describes as a fast-moving pre-AI company, the main AI assistance he used was tab completion. At Tano, he says agent tools could take on much larger tasks. His work there included building an affiliate platform, improving a content-monitoring system and migrating the company’s agent architecture. He says similar breadth of work that took 45 months at PostHog was compressed into eight months at Tano.
The change also reflects different company stages and working methods. Kakkar describes Bloomberg as a large organization with defined processes and PostHog as a startup that emphasized ownership, speed and customer response. At both earlier workplaces, he says, code was peer-reviewed and he spent substantial time reviewing others’ work. His essay argues that AI adoption depends not just on tools but on teams being willing to experiment and adapt their processes, a theme explored in software engineering and computer science education.
More Output, Different Bottlenecks
Kakkar’s account points to a practical workplace question: if AI agents make it possible to produce and submit code more quickly, review, coordination and product judgment may become limiting factors. He says some earlier constraints, including communication overhead and code review, diminished at Tano, but that faster work brought its own problems.
He describes context switching, lost shared understanding and reduced attention to design as new concerns. He also worries about the difficulty of pacing himself and potential AI plan limits. Those observations matter to engineering teams considering agent-based workflows: a higher pull-request count does not by itself show that software is better, safer or more valuable to users.
The comparison is useful as an individual case study, not proof that AI causes an 11-fold rise in engineering productivity. Kakkar worked at different companies, at different stages of his career and under different conditions. His figures record one output measure, while leaving quality, maintenance costs and business impact unquantified.
Products Worth Considering
Logitech MX Mechanical Wireless Illuminated Keyboard, Tactile Quiet, Graphite
Samsung 27-inch Odyssey G5 QHD Gaming Monitor (G51F)
Samsung 27-Inch Odyssey OLED G5 QHD Gaming Monitor
As an affiliate, we earn on qualifying purchases.
From Tab Completion to Agents
Kakkar has nine years of professional experience, according to the newsletter, including three years at Bloomberg, four at PostHog and eight months at Tano at the time of writing. He says he was the first engineer at Tano, which had grown to around 10 people, while PostHog grew from about 10 people when he joined to roughly 200.
His comparison treats PostHog’s earlier period as a pre-AI baseline: he says AI use there was largely tab completion and automating repetitive tasks such as writing test cases. He describes Tano as an AI-native startup founded after AI agents had emerged. He also cautions that PostHog has since adopted AI tools and that its output is increasing, so the contrast is between periods and practices, not a permanent comparison of the two companies.
The Pragmatic Engineer published the essay as the winner of a challenge marking the newsletter’s fifth anniversary. The publication said it received 125 submissions and awarded a $10,000 grand prize to Kakkar. It said a later issue would feature runner-up essays.
“I’m shipping 11x more PRs at Tano than at PostHog, where I shipped 2.4x as many as I did at Bloomberg.”
— Neil Kakkar, software engineer, in his essay published by The Pragmatic Engineer
What the Counts Cannot Show
The published comparison does not establish how much of the difference came from AI rather than company size, role, project mix, career experience or other changes between jobs. Kakkar calls the pull-request figures an honest record, but the newsletter does not provide an independent audit or a shared methodology for comparing the three workplaces.
It is also unclear whether the higher volume produced better outcomes overall. The essay’s figures do not measure code quality, defects, maintenance burden, customer satisfaction or revenue, and it does not offer a controlled comparison of time spent. Kakkar’s concerns about lost context, design attention and AI plan limits are personal observations, not quantified findings across a workforce.
Further Essays and Open Questions
The Pragmatic Engineer said it plans to publish a follow-up featuring runner-up essays and links to other submissions. Those accounts may add experiences beyond Kakkar’s, but the supplied material does not establish what they will conclude or when they will appear.
For now, the next test of Kakkar’s claims is whether faster code production can be sustained without eroding review quality, shared understanding or software reliability. The essay gives a snapshot of one engineer’s first eight months at an AI-native startup; longer-term results and comparable data from other teams remain unavailable.
Key Questions
Who reported the increase in pull requests?
Neil Kakkar, a software engineer, reported the comparison in the winning essay published by The Pragmatic Engineer.
How large was the reported increase?
Kakkar says he merged 11 times more pull requests per month at Tano than at PostHog. He presents this as a personal comparison based on his own work records, not a general industry result.
Does the essay prove AI caused the increase?
No. Kakkar credits AI as a major factor, but the comparison also spans different companies, roles, periods and project conditions. It does not isolate AI’s effect through a controlled study.
What challenges did Kakkar describe?
He points to context switching, loss of shared context, less focus on design, difficulty pacing work and concerns about AI plan limits. He says faster output can create new coordination and attention problems.
What happens after the essay?
The Pragmatic Engineer said it would feature runner-up essays in a later issue. The source does not specify a publication date.
Source: newsletter.pragmaticengineer.com
