Decagon Interview Questions — Page 1

Decagon·Software Engineer·Technical Phone Screen

Apr 2026

Decagon Software Engineer interview had a coding round focused on implementing undo/redo functionality for a shopping cart. Pretty niche problem that caught me a bit off guard.

Implement undo and redo functionality for a shopping cart, where performing a new operation clears the redo history, and no-ops are handled gracefully for empty stacks.

“My first instinct was two stacks, which is the right call, but I fumbled the part where a new operation wipes the redo stack.”

View Post

Decagon·Software Engineer·Technical Phone Screen

Apr 2026

Coding round at Decagon for a software engineer role. The whole thing was one design problem around a shopping cart for a cooking app, which sounds chill until you get into the discount aggregation logic.

Design a shopping cart for a cooking app where users can add recipes, each recipe has a list of ingredients, and overlapping ingredients across recipes qualify for bulk discounts. Implement add_recipe, remove_recipe, and get_total_discount.

“The add/remove part was fine, pretty standard set operations.”

View Post

Decagon·Software Engineer·Technical Phone Screen

Apr 2026

Got a coding question from Decagon that was pretty squarely in the stack-based simulation category. Nothing about the format stood out, felt like a standard technical screen.

Given logs of function calls on a single-threaded CPU, each formatted as function_id:start|end:timestamp, compute the exclusive time for each function (time the function itself ran, excluding any time spent inside nested calls). Return an array of length n with the exclusive time for each function ID.

“The stack approach clicked for me pretty quickly but I fumbled the timestamp math at first.”

View Post

Decagon·Software Engineer·Technical Phone Screen

Apr 2026

Decagon SWE interview had me extending a sliding-window score tracker with percentile queries. The problem builds on a previous round's work, which felt clever in retrospect but was a lot to hold in your head at once.

You have a sliding-window conversation score tracker from a prior round. Now add a method that, given a percentile p and a rank n, returns the score of the n-th conversation at that percentile among all conversations currently in the active window. How do you define percentile here, and what data structure supports this efficiently?

“The percentile definition part tripped me up more than the implementation.”

View Post

Decagon·Software Engineer·Onsite - System Design / Architecture

Apr 2026

Decagon software engineer interview with a meaty system design question around building an enterprise chatbot from scratch. One question, but it covers a lot of ground so expect to stay organized or you'll lose the thread fast.

Design an enterprise chatbot system for a single customer and business domain. It should handle multi-turn conversations, answer questions from approved documents with citations, avoid making things up, allow admins to update the knowledge base, fall back to a human agent when unsure, and meet reasonable latency and cost targets. Walk through the full design including APIs, session management, document ingestion, retrieval, prompt construction, model serving, safety, monitoring, and scaling.

“This one sprawls in every direction and the hard part is not going down a rabbit hole on any single piece.”

View Post

Decagon·Software Engineer·Technical Phone Screen

Apr 2026

Had a system design-flavored behavioral round at Decagon for a software engineer role. The whole thing was basically one big open-ended question about voice AI architecture, which sounds cool until you're actually in it trying to remember what you know about ASR pipelines on the spot.

If you were designing a real-time AI voice system from scratch, what engineering decisions would you make across the full stack? Think streaming speech-to-text, text-to-speech, turn-taking, latency budgets, pipeline architecture, and on-device versus cloud tradeoffs, and how you'd prioritize given real constraints.

“This is a massive question and I kind of froze for a second figuring out where to even start.”

View Post

Decagon·Software Engineer·Onsite - System Design / Architecture

May 2026

System design round at Decagon focused entirely on building an AI gateway for internal teams routing requests to LLM providers. The scope kept expanding as the interview went on, which was either a feature or a bug depending on how you look at it.

Design an AI gateway that internal product teams use to send requests to LLM providers, with a primary provider and a fallback. What does the overall architecture look like?
What fields would you include in a request log entity for this gateway, and why?
How would you ensure full auditability of requests through the gateway, including immutable storage, retention policies, and access control?
The requirements now include caching, PII redaction, and LLM response evaluation. How do you layer these in without redesigning everything?

“This is where I spent most of my time and honestly probably over-indexed on the API gateway and load balancer pieces before getting to the more interesting stuff.”

View Post

Decagon·Software Engineer·Technical Phone Screen

May 2026

Phone screen for a software engineer role at Decagon. One coding problem, I talked through everything out loud and got all test cases to pass, but the interviewer seemed completely checked out the whole time. A bit of an odd vibe.

Build a recipe shopping cart: given a list of recipes and their ingredients, implement a system to manage and aggregate items for a shopping cart.

“Kept narrating my thinking out loud the whole time, which I think actually helped me stay on track.”

View Post

Decagon·Software Engineer·Onsite - System Design / Architecture

May 2026

System design round at Decagon for a software engineer role, one big question about building an AI gateway layer in front of multiple LLM providers. Pretty dense problem that kept branching into new sub-problems every time I thought I'd covered something.

Design an AI gateway that sits between internal services and multiple LLM providers. It should route requests to a chosen provider and fall back to a backup when the primary fails, is rate-limited, or is degraded. What signals drive the failover switch, and how do you prevent the system from flapping back and forth?
How would you design the structured logging system for this gateway? Cover the data model for request and response logs, what metrics surface in dashboards, how you handle retention and PII, and how the fallback policy gets configured (static versus adaptive).

“I started with the obvious stuff: watch for 5xx errors and 429s, track latency p99.”

View Post

Decagon·Software Engineer·Onsite - System Design / Architecture

May 2026

Two-hour technical session at Decagon for a Software Engineer role where you actually write code live with an AI assistant and then pivot into a full system design discussion. The coding part was surprisingly open-ended and the design conversation went pretty deep into multi-tenant concerns and observability.

Using an AI coding assistant of your choice, implement a component of an AI Gateway. Options included request routing across multiple LLM providers, retry and fallback logic, or token-budget enforcement.
Walk through the broader system design of an AI Gateway, covering provider abstraction, per-tenant and per-model rate limiting, prompt caching, streaming response handling, observability across providers, authentication and quota management, and how the architecture evolves as new model providers are added.

“I went with retry/fallback logic because it felt most concrete and I could show real decision-making fast.”

View Post