Research snapshot / 2026-07-16
Sierra
customer-experience-ai201-1000 peopleResearch record · not company verified
Current tools / 23
Documented stack
Source, access date, and confidence stay attached to each row.
| Category | Tool | Since | Confidence | Evidence |
|---|---|---|---|---|
language | GoNamed directly as Sierra's backend systems language across independent job postings (frontend, payments infrastructure) and confirmed in production use for Sierra's internal agent-runner infrastructure. | — | confirmed | job-post ↗Accessed 2026-07-16 job-post ↗Accessed 2026-07-16 eng-blog ↗Accessed 2026-07-16 |
| TypeScriptFrontend language, paired with React. | — | confirmed | job-post ↗Accessed 2026-07-16 job-post ↗Accessed 2026-07-16 | |
| PythonConfirmed for Sierra Research's open-source evaluation tooling (tau-bench family, all Python repos). Not directly confirmed as a production agent-platform language — only listed as one acceptable option among Go/Scala/Python in a data-platform job posting. | — | inferred | code ↗Accessed 2026-07-16 job-post ↗Accessed 2026-07-16 | |
frontend | React | — | confirmed | job-post ↗Accessed 2026-07-16 |
backend-framework | GraphQLAPI layer between the React/TypeScript frontend and the Go backend, implemented with gqlgen. | — | confirmed | job-post ↗Accessed 2026-07-16 |
hosting | AWSExplicitly named as Sierra's cloud provider by the SRE team's own posting (distinct from a separate, weaker 'AWS, GCP, or Azure' generic candidate-skills list found in another posting, which was not used as evidence). | — | confirmed | job-post ↗Accessed 2026-07-16 |
| Terraform | — | confirmed | job-post ↗Accessed 2026-07-16 job-post ↗Accessed 2026-07-16 | |
| KubernetesConfirmed running Sierra's internal 'Pinecone' agent-runner platform. Not separately confirmed for the customer-facing production agent runtime, though plausible given shared infrastructure culture. Sierra states the same infrastructure also underpins Ghostwriter, its customer-facing "agent for building agents" — so this extends beyond internal tooling. | — | confirmed | eng-blog ↗Accessed 2026-07-16 eng-blog ↗Accessed 2026-07-16 | |
observability | DatadogNamed as one of several acceptable observability tools (alongside Prometheus, Grafana, OpenTelemetry) in two independent job postings, always as an 'e.g.' example rather than an explicit 'we use X' statement. Included at inferred confidence only because the same short list recurs independently across two job families. | — | inferred | job-post ↗Accessed 2026-07-16 job-post ↗Accessed 2026-07-16 |
queue | RedisRedis Streams used for live communication within Sierra's internal agent-runner platform (Pinecone). Not separately confirmed for the core customer-facing product. | — | confirmed | eng-blog ↗Accessed 2026-07-16 |
data-pipeline | Apache IcebergSierra's own data lakehouse table format for its Agent Data Platform. | — | confirmed | job-post ↗Accessed 2026-07-16 |
orchestration | Custom multi-model orchestration ("Constellation of Models")Sierra deliberately avoids single-vendor lock-in: agents are assembled from 15+ frontier, open-weight, and proprietary models, routed per task (latency-sensitive tool calling, classification, long-context reasoning, tone) by a custom orchestration layer. Sierra's own communications do not name the specific model vendors behind this system for the production platform. | — | confirmed | eng-blog ↗Accessed 2026-07-16 social ↗Accessed 2026-07-16 |
ai-eval | Custom LLM-as-judge evaluation ("Monitors")In-house always-on evaluation layer; each monitor goes through its own evaluation loop grounded in team-labeled conversations and multi-model agreement. | — | confirmed | eng-blog ↗Accessed 2026-07-16 |
| τ-bench / τ²-bench / τ³-bench / μ-bench (in-house benchmark suite)Sierra Research's actively-maintained open-source benchmark suite for evaluating tool-using conversational agents across text, voice, and knowledge-retrieval domains. | — | confirmed | code ↗Accessed 2026-07-16 eng-blog ↗Accessed 2026-07-16 | |
inference-infra | LiteLLMConfirmed via Sierra Research's own open-source code as the model-provider abstraction layer for the tau-bench evaluation tooling. Not confirmed for the production agent-serving path. | — | inferred | code ↗Accessed 2026-07-16 |
llm-provider | OpenAIOpenAI's Codex is confirmed in company-wide internal use as a coding agent, and Sierra's own tau2-bench voice benchmark integrates OpenAI's realtime API as a supported provider. Sierra has not publicly confirmed OpenAI as a model provider behind its customer-facing agent platform — the company deliberately describes a vendor-agnostic 'constellation of models' without naming production vendors. | — | inferred | eng-blog ↗Accessed 2026-07-16 code ↗Accessed 2026-07-16 |
| AnthropicClaude Code confirmed in company-wide internal engineering use. Not confirmed as a named production-platform model vendor — same caveat as the OpenAI entry. The Pinecone post also references Anthropic model names in default internal routing patterns. | — | inferred | eng-blog ↗Accessed 2026-07-16 eng-blog ↗Accessed 2026-07-16 | |
internal-tools | GitHub | — | confirmed | eng-blog ↗Accessed 2026-07-16 |
| Slack | — | confirmed | eng-blog ↗Accessed 2026-07-16 | |
| Linear | — | confirmed | eng-blog ↗Accessed 2026-07-16 | |
| CursorAI coding tool used company-wide by engineers. | — | confirmed | eng-blog ↗Accessed 2026-07-16 | |
| Codex (OpenAI)AI coding agent used company-wide by engineers. | — | confirmed | eng-blog ↗Accessed 2026-07-16 | |
| Claude Code (Anthropic)AI coding agent used company-wide by engineers. | — | confirmed | eng-blog ↗Accessed 2026-07-16 |