Bespoke Labs A Verified
RL environment company · Coding
- Domains
- Coding Long-Horizon
- On X
- @bespokelabsai ↗
- Funding
- $40M raised · rounds and investors
- Tier
- A why
- Snapshot
What Bespoke Labs does
Bespoke Labs builds company-scale RL environments and infrastructure, plus agent evaluation and GEPA-based optimization, for frontier labs and enterprises training long-horizon agents.
- Sells
- RL environments
- Leads with
- Coding
- Based in
- Mountain View, USA
- Team
- 11-25
- Website
- bespokelabs.ai ↗
What Bespoke Labs sells
Read from Bespoke Labs's own website, checked October 11, 2026: the line that puts it in each category.
RL environments
“Bespoke Labs builds company-scale RL environments and infrastructure to let frontier labs and enterprises train long-horizon agents for production.”
bespokelabs.ai/ ↗“Evaluate agents in environments that mirror your systems and processes.”
bespokelabs.ai/ ↗
Also
“Enterprises rely on us to make AI agents dependable.”
bespokelabs.ai/ ↗
Domains Bespoke Labs covers
Coding leads with
“Company-scale simulations with real codebases and microservices, allowing agents to master the complex, long-horizon workflows required for production.”
bespokelabs.ai/ ↗“OpenThoughts is one of the most impactful open data curation projects of the past year.”
bespokelabs.ai/blog/bespoke-labs-raises-40m-to-build-environ… ↗
Benchmarks Bespoke Labs built or runs
AutoResearchExam built it
“To address this gap, we introduce AutoResearchExam, a benchmark of open ended ML research tasks”
benchmarks.bespokelabs.ai/autoresearchexam/ ↗
Bespoke Labs competitors and alternatives
The companies that sell the most of the same things in the same domains, and what they share with Bespoke Labs.
- Abundant Also sells RL environments and evals · also in coding
- Datacurve Also sells RL environments and evals · also in coding
- Emulated Also sells RL environments and evals · also in coding
- General Reasoning Also sells RL environments and evals · also in coding
- Idler Also sells RL environments and evals · also in coding
Tier A
Scaling: 51 to 250 people, or $20M+ raised.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- team 11-50
- raised $40M
- investors: Wing VC, 8VC, Mayfield
- in curated RL directories (5 pts)
On X · well regarded, moderate buzz, from 14 posts about Bespoke Labs in the last month
Discussion centers on its Nimble decision model and an NVIDIA-partnered post on training Nemotron for autonomous ML research, with some praise and a Berkeley/Stanford paper.
How we got to tier A
- Adoption: team 11-50; raised $40M; investors: Wing VC, 8VC, Mayfield. Tier A.
- On X: well regarded, moderate buzz. “Discussion centers on its Nimble decision model and an NVIDIA-partnered post on training Nemotron for autonomous ML research, with some praise and a Berkeley/Stanford paper.” No move.
- In curated RL directories: 5 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Bespoke Labs funding
- Raised
- $40Mstated total
- Latest round
- Series A2026-07 · led by Wing VC
Backed by8VCWing VCMayfieldThe House Fund
Rounds
- Series A · 2026-07 · led by Wing VC
Our Series A round was led by Wing VC, with participation from Mayfield, The House Fund, dbt Labs CEO Tristan Handy, and angels from Anthropic, OpenAI, and Meta, and others.
- Read: “Our Series A round was led by Wing VC, with participation from Mayfield, The House Fund, dbt Labs CEO Tristan Handy, and angels from Anthropic, OpenAI, and Meta, and others.”
- Found word for word on its own site: bespokelabs.ai/blog/bespoke-labs-raises-40m-to-build-environments-that-enable-reliable-agents
- The quote names who led it; the amount isn't in it
- No other page or directory names it yet
- Seed · $8.25M · led by 8VC
Our $8.25 million seed round was led by 8VC, with participation from Jeff Dean, Resolve AI CEO Spiros Xanthos, DevRev CEO Dheeraj Pandey, and others.
- Read: “Our $8.25 million seed round was led by 8VC, with participation from Jeff Dean, Resolve AI CEO Spiros Xanthos, DevRev CEO Dheeraj Pandey, and others.”
- Found word for word on its own site: bespokelabs.ai/blog/bespoke-labs-raises-40m-to-build-environments-that-enable-reliable-agents
- The quote states the amount and who led it
- No other page or directory names it yet
Funds 4
- 8VC led a round
Named in the round quoted above.
- Wing VC led a round
Named in the round quoted above.
- Mayfield
Named in the round quoted above.
- The House Fund
Named in the round quoted above.
Angels 4
- Dheeraj Pandey
Named in the round quoted above.
- Jeff Dean
Named in the round quoted above.
- Spiros Xanthos
Named in the round quoted above.
- Tristan Handy
Named in the round quoted above.
Every figure is quoted from its own site, its accelerator or a funding announcement; a round's amount and lead appear only when its quote states them. Startup databases are never used as evidence. Checked 2026-10-11. How funding is checked.
Training methods
Methods Bespoke Labs uses, offers or builds for, with public evidence: its own website says so, or two independent sites do.
- GRPO Group Relative Policy Optimization On its own website
“We are excited to share some recent findings which show that RL can improve multi-step tool use capabilities, a first milestone. Using GRPO, the core algorithm behind DeepSeek-R1, we improved Qwen2.5-7B-Instruct’s tool use performance by 23% on a subset of the BFCL benchmark using only 100 training samples. The tasks in this benchmark require an agent to or…”
bespokelabs.ai“We use supervised fine-tuning (SFT) with trajectories coming from a strong teacher model, and reinforcement learning (GRPO) on the fontTools specialized environments that we curate. SFT gives a 52pp improvement in performance on the held-out fontTools evaluation set. Further RL training lifts the total improvement to 57pp compared to the ba…”
bespokelabs.ai - SFT Supervised Fine-Tuning On its own website
“Can an open coding model be post-trained to work better on a specific repository? How do we use SFT and RL to improve performance? To answer these questions, we curate coding tasks specialized for a repository and post-train Inkling using SFT and RL. Here, we focus on the fontTools open-source repository, but our meth…”
bespokelabs.ai“The pipeline combines synthetic data with engineered distributions, supervised fine-tuning of Llama 3.1 8B with LoRA, and GEPA prompt optimization. Teacher-generated explanations undergo rejection sampling before training. Evaluations then check product accuracy, legal and partner compliance, and product requ…”
bespokelabs.ai
Where Bespoke Labs sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Latest from Bespoke Labs on X
@bespokelabsai ↗Next: browse all environments. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.