Braintrust
Evaluation and observability platform for AI agents, tracing them in production and scoring them against datasets.
Product
Selected offerings — the AI products recorded here, not the vendor's full catalogue.
-
Stores production agent traces in its own datastore, turns the patterns it finds there into evaluation datasets, and scores every release against them.
Closest alternatives 2
Similar products 18
Closest alternatives are pairs a vendor page itself compares. Similar products are matched from what each product does; nothing in that group is asserted as a rivalry.
Sources
- Total funding
-
Company disclosure · 17 Feb 2026
$125M is the sum of two figures Braintrust states itself, and the company has published no cumulative total since the Series A. Its Series A post, 2024-10-08: "we've raised $36 million to advance the future of AI software engineering, bringing our total funding to $45 million." Its Series B post, 2026-02-17: "Braintrust has raised $80M to become the observability layer for production AI", led by ICONIQ with Andreessen Horowitz, Greylock, Elad Gil and basecase returning -- that post states no running total. $45M + $80M is arithmetic on the company's own two numbers, not an estimate,.
- Description
-
Company disclosure · 18 Sep 2026
Own homepage, read 2026-09-18: "Ship quality agents at scale -- Discover patterns in production, turn them into evals, and improve quality with every release." Its named surfaces are Observe, Evaluate, Discover, the Loop agent, pattern automations and Brainstore. Delivery test: the platform stores and scores the customer's own production agent traces.
Open Braintrust in the directory
Something wrong here? Send a correction — quote this company id: braintrust.