Braintrust — AI-Native Evals & Observability Platform for Production LLM Agents (Brainstore + Loop + MCP)

SF, founded 2023 by Ankur Goyal (ex-Impira), Series B $80M led by ICONIQ Feb 2026 (~$ 800M val, $124M total). AI-native evals + observability for LLM apps/agents. No acquisition, no sunset. Category ai-productivity-data, pipeline_stage=none. File under Dev (LLM-eval/observability sublane). This is a re-run of your prior Braintrust turn with verified 2026-09 figures.Official site: https://www.braintrust.devPricing: https://www.braintrust.dev/pricing

Docs: https://www.braintrust.dev/docs

Snapshot

Field	Value
Status	Active
Origin	Braintrust Data Inc., SF, 2023, Ankur Goyal
Lane	LLM/agent observability + evaluation + prompt registry + quality gates
Core parts	Tracing, Evals, Brainstore (AI-trace DB, 80× faster), Loop (eval agent), Topics (pattern discovery), Gateway, MCP server
Customers	Notion, Stripe, Vercel, Cloudflare, Replit, Ramp, Dropbox, Zapier, Instacart, Coursera
Compliance	SOC 2 Type II, HIPAA BAA (Ent), GDPR, DPA
Category	`ai-productivity-data` / Dev (eval/obs sublane)

Features (table)

Layer	Capability	Notes
Tracing	Per-step agent traces (prompt/tool/retrieval/latency/cost), SDK Py/TS/Go/Ruby/C#/Java, OTel-compatible	Backed by Brainstore, 80× faster query vs PG
Evals	Dataset + task + scorer model, batch run vs prompts/models, CI gates (GitHub Action posts PR comment + blocks merge)	LLM-as-judge / code / human scorers; one-click prod trace → eval case
Prompt registry	Env-labeled versions (prod/staging/dev), playground side-by-side, no-deploy promote	Fetch by env name at runtime
Loop	AI agent: draft better prompts, build/refine scorers, synthesize eval datasets from NL	Uses model-credit quota (Topics-grade tokens)
Topics	Auto pattern discovery across traces (issues/sentiment/tasks)	Metered separately, $0.06/$ 0.40 per MTok overage
Gateway	Multi-provider routing, caching, cost tracking, built-in obs	Optional proxy
MCP	MCP server → pull traces/evals into Cursor/Claude Code/Cline	IDE-native debugging
Deploy	SaaS, BYOC, self-hosted data plane (Ent)	Control plane managed
No	No agent runtime/deploy (≠ LangSmith Deploy), no APM for non-LLM services, no OSS community edition (SDKs MIT/Apache, platform closed)	Scope = AI apps only

Pricing (2026-09, USD)

Tier	Platform fee	Included usage	Overage / notes
Starter	$0	1 GB processed data/mo, 10k scores/mo, $10 Topics/model credits, 14-day retention, unlimited users/projects/datasets/playgrounds	Data $4/GB, scores$ 2.50/1k, Topics $0.06 in /$ 0.40 out per MTok
Pro	$249/mo (promo$ 249 credit till 2026-09-01, then $100/mo credit from 2026-09-01)	5 GB data, 50k scores, 30-day retention ($0.50/GB/mo beyond), custom charts, env, RBAC basic, priority email	Data $3/GB, scores$ 1.50/1k, lower token rates
Enterprise	Custom (annual invoice)	Custom limits, SAML/OIDC SSO, SCIM, audit log, BAA, BYOC/self-host, S3 export, Slack channel, SLA	Early-stage startups (≤Series A, ≥$100K raised) get 6–12 mo free Pro

starting_price=$0; first paid $249/mo (no per-seat fee at any tier — bill = platform fee + data + scores + Topics tokens).

Reviews (2026)

Source	Signal
Vendor benchmarks / Notion case study	Notion: 3→30 AI issues fixed/day after adopting Braintrust evals (10×)
ToolRadar / Voiceflow / AITrendTool	Praised: trace→eval→CI gate loop, Brainstore speed, Loop autonomy, MCP IDE pull, seat-unlimited billing. Criticized: $0→$ 249 jump steep, Topics/Loop token burn, compliance (SOC2/HIPAA/SSO) Enterprise-gated, closed-source platform (vs Langfuse)
Aggregate	Best-in-class eval-first observability for eng-led LLM teams; less turnkey for non-LangChain PMs than Humanloop/PromptLayer

Access / Integration (table)

Method	Supported
SDK	Python, TypeScript, Go, Ruby, C#, Java
Framework	OpenAI, Anthropic, LangChain, Vercel AI SDK, OpenTelemetry
Gateway	Braintrust Gateway proxy (multi-provider, cache, cost)
MCP	MCP server → Cursor / Claude Code / Cline
CI	GitHub Actions eval gates (`braintrustdata/eval-action`)
Deploy	SaaS / BYOC / self-hosted data plane (Ent)
No	No REST “score my text” free endpoint for non-customers, no frontend analytics

Best For / Not For

Best For	Not For
Eng-led LLM/agent teams running CI eval gates	PM-only prompt-editing shops (→ PromptLayer/Humanloop)
Notion/Stripe-scale trace volume (breaks PG)	LangChain-locked teams wanting agent runtime (→ LangSmith Deploy)
Framework-agnostic stacks (OpenAI+Anthropic+Vercel)	Tiny side-projects unwilling to watch data/score/Topics meter
Air-gap/BYOC regulated (Ent: HIPAA/SAML/self-host)	Teams needing OSS self-host free (→ Langfuse/Phoenix)
Cursor/Claude Code users wanting MCP trace pull	Non-LLM APM needs (→ Datadog)

Competitors (lane map)

Lane	Tool	Braintrust edge / gap
Eval-first platform	LangSmith	LangSmith deeper LangChain + agent runtime + seat pricing; Braintrust framework-agnostic + Brainstore + Loop + seat-unlimited
OSS observability	Langfuse, Arize Phoenix	OSS/self-host free; Braintrust managed Brainstore + Loop + MCP
Prompt mgmt	PromptLayer, Humanloop	Lighter prompt-registry; Braintrust broader eval/obs/trace-to-dataset
Gateway/obs	Portkey, Helicone	Routing focus; Braintrust eval/CI gates deeper
CI prompt test	Promptfoo	YAML/red-team OSS; Braintrust production-trace feedback loop
Runtime guardrails	Galileo, Guardrails	Galileo runtime safety; Braintrust release-control + evals
APM legacy	Datadog LLM Obs, Fiddler	General APM; Braintrust AI-trace-native
In-list overlap	Exa, Cody, JB AI, Continue, Aider, Cline, Mintlify, Q Dev(sunset), Phind(shutdown)	Dev lane adjacent (eval vs coding/docs)