Convex vs LangSmith

Convex

LangSmith

Convex · 18 features

• Actions — Non-deterministic functions for external I/O (fetch, AI APIs, email). Cannot rea…
• Authentication — Convex Auth (built-in) or BYO provider (Clerk, Auth0, Kinde, WorkOS). ID tokens …
• Convex Agents — AI agent framework with durable memory, threads, tool use. Works with OpenAI / A…
• Convex Auth — First-party auth library: passwords, magic links, OAuth, phone — stored in your …
• Convex Components — Reusable backend modules (rate limiter, workflow, aggregate, action-retrier, etc…
• Cron Jobs — Recurring schedules defined in convex/crons.ts. UTC, cron-style patterns.
• Durable Workflows — Long-running multi-step workflows with retries and at-least-once guarantees.
• Exception Reporting — Auto-capture errors to Sentry, Axiom, Datadog.
• File Storage — Upload/download via storage API. Returns storage IDs referenced in documents.
• Full-Text Search — BM25 search index on table fields. withSearchIndex query helper.
• HTTP Actions — Expose public HTTP endpoints for webhooks, OAuth callbacks, third-party integrat…
• Log Streams — Stream function logs to Axiom, Datadog, Sentry. Pro+.
• Mutations — Transactional write functions. All reads + writes in one mutation are ACID; conf…
• Preview Deployments — Every Git branch gets its own isolated deployment. Integrates with Vercel/Netlif…
• Queries — Deterministic read-only TS functions. Automatically cached and re-run when under…
• Real-Time Subscriptions — useQuery auto-subscribes; server invalidates when data a query read changes. No …
• Scheduler — schedule.after / schedule.at — enqueue functions to run later. Durable, survives…
• Vector Search — Native vector index on tables. withIndex + filter fields. Up to 4096 dims.

LangSmith · 14 features

• Alerts — Threshold alerts on latency, cost, eval metrics.
• Annotation Queues — Human-review workflows for trace quality rating.
• Custom Dashboards — Aggregate metrics dashboards per project/tag.
• Datasets — Collect examples → use as eval sets or training data.
• Evaluations — LLM-as-judge, embedding similarity, custom Python evaluators, offline batch eval…
• LangChain Integration — Auto-trace any LangChain/LangGraph run with env var.
• LangGraph Integration — First-class trace + eval for LangGraph agents.
• LLM Tracing — Automatic trace every LLM call + tool call + chain step.
• OpenTelemetry Export — Export traces as OTLP to Datadog/Honeycomb/etc.
• Playground — Test prompts + models inline before deploying.
• Prompt Canvas — Visual prompt editor with live test + eval.
• Prompt Hub — Public + private prompt library with versioning.
• Self-Hosted (Enterprise) — Docker + k8s deployment in your infra.
• Threads + Sessions — Group traces into conversational sessions.