BuildNot yet confirmed elsewhere1 publisher2 min readPublished
DoorDash's GenAI platform went API-first after an engineer asked what a notebook was
DoorDash's GenAI Platform team, started around April 2023, chose APIs and SDKs after finding its users were product engineers across the company. Swaroop Chitlur's talk sets out the rules behind it, though the transcript breaks off before any cost or results data.
The Engineer · Build desk
What happened
- Chitlur said he was sweating over the size of the spend when he signed DoorDash's OpenAI contract, a number he now calls minor in hindsight.
- The team took its operating rules from tenets DoorDash already had, including customer obsession, building products instead of systems, and making the right thing easy.
- The team chose to focus on business impact in DoorDash's product and deliberately kept chatbots, and later coding agents, out of its scope.
- Talks with product engineers sorted the company's 2024 demand into three broad buckets: automation, recommendations and personalization.
Why it matters
- constraint Excluding chatbots and coding agents keeps the platform on product features, and leaves internal assistant and coding-agent demand for some other part of DoorDash to serve.
- exposure When best practice lives in platform defaults, one bad default reaches every calling team at once, so the platform team now carries risk that individual teams used to carry.
- capability Chitlur credits fixed principles with carrying the team from models to workflows to agents, so a platform with stated rules can change its product without re-arguing its scope each time.
The first interface choice followed the org chart. Swaroop Chitlur, who started DoorDash's GenAI Platform with a colleague he introduced as Sidd [1], said the group became a team under the ML platform org and was used to talking to machine learning engineers [8]. So in one conversation he told a prospective user to just try an idea in a notebook, and the reply was "what's a notebook?" [9]. The team's first user research turned out to be a glossary check. Chitlur said that exchange moved the team to APIs and SDKs, and away from thinking in notebooks, GPUs or access to compute [10].
I think API-first is the right call for a shared LLM service. The reason is control. A notebook leaves each caller holding the model choice and the credentials. Behind an API, those become platform defaults that one team can change for every caller at once. Chitlur stated the rule behind that design: "If you say, do best practices, nobody's going to do it. You need to bake in best practices into how your platform operates" [7].
Accountability was one of the first questions. Chitlur said that at the time of the contract signing, he was asking: "if this thing takes off, how do we support this in such a large company? How do we make this productive? How do we make this accountable?" [4]. The talk promises "a balance of what was our strategy and what was the technical proof and what was the results" [13]. The transcript excerpt breaks off mid-sentence during the use-case discussion [14], before any technical project appears. It does not show how the team attributed spend to calling teams or measured business impact.
Two conditions decide whether this operating model carries over to another company. The callers have to be engineers building product features, the audience DoorDash found once it asked [10]. The platform also has to own its defaults outright. Chitlur's best-practice rule only works if the platform can change behaviour for every caller [7].
What to watch
- The technical projects and results sections of the full talk, especially any per-team cost attribution or business-impact metric that answers Chitlur's accountability question.
- Whether DoorDash's platform keeps coding agents out of scope now that they exist, since the exclusion was set before any were available.
Clarity's read
What the record supports and how the coverage leans. The claims behind it follow.
Reality
- Evidence35
- Adoption50
- Hype gap+20
- Incentives55
- Confidence40
Claim ledger
Ranked by verification strength, evidence, and original report placement.
- [1]
Swaroop Chitlur and a colleague he introduced as Sidd started the GenAI Platform team at DoorDash.
- [2]
The GenAI Platform team's journey started roughly in April 2023, a few months after the ChatGPT moment in November 2022.
- [3]
Chitlur was tasked with signing DoorDash's OpenAI contract when the company decided to start using OpenAI: "I remember I was sweating, like, are we really going to spend this much money? Of course, in hindsight, that number seems minor now."
- [4]
"if this thing takes off, how do we support this in such a large company? How do we make this productive? How do we make this accountable?"
- [5]
The team had initial principles and bets, adapted as the industry evolved, and was able to navigate the changes because of those principles as its work went from models to workflows to agents.
- [6]
The team's operating principles were already part of DoorDash's foundations or tenets: be customer obsessed, build products not systems, treat the product engineer as the customer, think of end-to-end workflows including onboarding and support, make the right thing easy, and prove value to customers and stakeholders.
- [7]
"If you say, do best practices, nobody's going to do it. You need to bake in best practices into how your platform operates."
- [8]
The GenAI platform became a team under DoorDash's ML platform org, and the team was used to thinking about and talking to machine learning engineers.
- [9]
In one conversation Chitlur suggested trying something out in a notebook and the engineers replied, "what's a notebook?", after which the team realised its audience was no longer ML engineers.
- [10]
The team concluded its audience was all engineers and decided to move to APIs first and think in terms of SDKs, not notebooks, GPUs or getting access to compute.
- [11]
The team explicitly decided to focus on business impact and product, not on chatbots, and by the same principle not on coding agents, which did not exist at the time; Chitlur called it "a conscious decision we took."
- [12]
Conversations with product engineers in 2024 showed use cases falling into broad buckets: automation, recommendations and personalization.
- [13]
"You get a balance of what was our strategy and what was the technical proof and what was the results."
- [14]
The transcript text ends mid-sentence while describing automation use cases: "We noticed that automation is decreasing the bott".
Sources
1 independent publisher whose own reporting we read for this story.
- infoq.comPresentation: Building GenAI Platform at DoorDash
1 article · October 3, 2026
Topics and entities
Follow any of these and your For You feed starts watching them — no settings page required.