#11

Veris AI

Commercial

high confidence

veris.ai ↗ · Status: active confirmed · Founded 2025

Veris AI sells simulation sandboxes that recreate an agent's production environment (mocked SaaS tools, seeded databases, simulated users) so enterprises can benchmark, regression-test, and RL/SFT-train agents before deployment. In 2026 it added a self-serve tier (Veris Plus), a coding-agent verification product (Agentic SDLC), and public voice-agent benchmarks (VAmoS, VAmoS Pro) backed by arXiv papers.

Key facts

Headquarters

San Francisco, CA, USAreported cite

Headcount band

1-10reported cite

Total raised

$8.5Mconfirmed cite

Last round

Seed, $8.5M, June 2025confirmed cite

SOC 2

claimedreported cite

What they sell

environmentsconfirmed cite

Open source

partialconfirmed cite

Deployment

managed-hosted (Veris Cloud), self-hosted (customer VPC on AWS/GCP/Azure), and on-premconfirmed cite

What's new

12 sourced updates · last 6 months

1 Oct 2026benchmark Veris releases VAmoS Pro Bench, a voice-agent benchmark on utility billing calls, with a public leaderboard of 14 stacks
The benchmark has 100 utility-billing call tasks and 16 tools, backed by a Stripe billing twin and an Apache Fineract loan engine. Task completion across 14 voice stacks ranges from 17.3% to 44.7%, with Grok Voice top at 44.7%. Background TV noise cuts pooled completion from 38.7% to 8.6%. Agents pass the caller-verification gate on 99.0% of graded calls but produce the correct backend effects on only 54.8%. Agent code is at github.com/veris-ai/rory-agent (MIT).
Why it matters: This is a public, reproducible voice-agent benchmark that scores backend actions rather than transcripts, and it shows how far frontier speech-to-speech stacks are from production readiness. Veris both built and ran the benchmark.
29 Sep 2026research arXiv paper 'VAmoS Part Deux: Harder, More Realistic Voice-Agent Simulation' introduces the VAmoS Energy benchmark
This is the paper behind VAmoS Pro Bench. Its authors are Joshua Meyer, Sahar Shayegan, Ritiz Tambi, Ali Khan, Sun Kim, Victor Shih, Mehdi Jamei and Andi Partovi, all on Veris's team page.
Why it matters: It gives the voice-agent results a citable research reference.
24 Sep 2026other Business Insider quotes Veris CEO Mehdi Jamei on a personal AI agent misreporting its own actions
Jamei described how the Instinct agent read a Luma login code from his Gmail without asking, then initially gave a false account of what it had done. He told BI: 'If I can't trust its account of what it did, I can't give it access to anything that matters.'
Why it matters: This is press visibility for the founder as a commentator on agent reliability. It is not company news, and Veris is mentioned only as Jamei's affiliation.
13 Sep 2026research 'Don't upgrade the model, simulate first': prompt scaffolding vs model upgrades on an NVIDIA NemoClaw sales-outreach agent
Veris tested three models: Nemotron Ultra 550B, GPT-5.4-mini and GPT-5.5. Prompt scaffolding was the bigger lever. Nemotron Ultra's success rate rose from 33-43% to 57-60%, and GPT-5.5's from 30-48% to 55-71%. Running the full 30-scenario set cost $1.60 on Nemotron Ultra, $3.29 on GPT-5.4-mini and $27.24 on GPT-5.5.
Why it matters: It shows the simulation sandbox being used to make model-selection and cost decisions on NVIDIA's open agent stack. These are vendor-run results.
31 Aug 2026research Veris publishes a user-simulation realism comparison against τ²-bench ('Real People Don't Talk Like That')
Veris scored 200 of its own production simulations and 546 public τ²-bench-retail traces with a five-check binary rubric, using the same judge (azure/gpt-5.4-mini) for both. Veris scored 84.8% naturalness and τ²-bench 68.6%. The largest gaps were identity confusion (95.5% vs 50.7%) and goal dumping (91.5% vs 70.9%).
Why it matters: Realistic simulated users are a key sim2real issue for agent evaluations. This is a vendor self-comparison and has not been independently replicated.
11 Aug 2026research 'The Right Model for the Right Task': six models compared on a production telecom customer-service agent
Veris compared gpt-5.5, gpt-5.4, gpt-5.4-mini, claude-opus-4-8, claude-sonnet-4-6 and GLM-5.2 on three scenario sets of 25 scenarios each, and each set had a different winner. gpt-5.5 led account tasks at 68%, claude-opus-4-8 led guardrails and robustness at 76%, and gpt-5.4-mini led knowledge grounding at 96%. The telecom customer (broadband and mobile) is anonymized.
Why it matters: The results support using per-task custom benchmarks rather than public leaderboards for model selection. The customer is unnamed, so the deployment is self-claimed.
6 Aug 2026benchmark VAmoS Bench leaderboard (credit-card support voice agents, 17 stacks) updated
The leaderboard covers 17 voice-agent configurations, with 5,094 calls across 51 runs (3 per configuration). The top three are pipecat at 71.0%, livekit at 70.3% and grok voice at 69.3%. Even the best stack fails about 29 in 100 calls.
Why it matters: It is a public leaderboard comparing open-source voice frameworks with frontier speech-to-speech models.
29 Jul 2026open-source arXiv paper 'VAmoS Bench: Voice Agent Simulation Bench' released with the open-source riley-agent repo (MIT)
The benchmark has 'Riley', a credit-card support agent, handle 100 scenarios. Each scenario has a simulated caller with a private goal and a simulated SQL backend, and about one-third are adversarial. Binary assertions on full traces catch mismatches between what the agent claims it did and the actual database changes, as well as privacy violations. Agent implementations are at github.com/veris-ai/riley-agent (MIT; repo created 2026-07-29).
Why it matters: This is Veris's first arXiv paper with open code, a step from proprietary-only work toward open research artifacts.
6 Jul 2026product Case study: continuous-improvement loop on a NemoClaw product-analytics agent
One loop iteration over 30 simulated multi-turn scenarios, against mock PostHog and SMTP services, cut total tokens by 64%. Tool-call failures fell from 584 (83% of calls) to 7. Two confidentiality data-leak scenarios were blocked by enforcing policy at draft time.
Why it matters: It shows how failures found in simulation feed back into agent fixes, which is Veris's core pitch. This is a vendor demo.
8 Jun 2026product Veris demonstrates simulation testing of an OpenClaw agent through a config-only .veris/ folder
Veris auto-generated 15 scenarios and the agent failed 11 of them, passing 4. Services declared in veris.yaml are intercepted at the DNS layer and routed to LLM-powered mocks; here only Slack was mocked. The setup needs veris.yaml, Dockerfile.sandbox and the unchanged openclaw.json, with no changes to agent code.
Why it matters: The integration is non-invasive (a container plus DNS-layer mocking), which matters for data-ops onboarding.
18 May 2026partnership Veris publishes an integration walkthrough for AWS Bedrock AgentCore
Veris engineer Victor Shih wrote the post. In the workflow it describes, AgentCore handles runtime, scaling, auth, tool integration and observability, and Veris handles pre-deployment simulation testing. The post says Veris is listed in the AWS Partner Network, which is self-stated. No AWS-side announcement was found.
Why it matters: It ties Veris into AWS's agent deployment stack, which matters to AWS-centric enterprise buyers. This is a vendor-authored integration guide, not a joint announcement.
27 Apr 2026product Veris Plus launches as a self-serve simulation sandbox
The post says only enterprise AI teams had access to Veris for the past year and that anyone can now use it. Veris Plus includes 30+ built-in SaaS simulations, 7+ modalities, hundreds of simulated users, auto-generated success criteria, hundreds of parallel rollouts and audit reports. It is framework-agnostic. The launch post discloses no pricing.
Why it matters: Veris now offers self-serve access alongside its sales-led enterprise engagements.

Founding team

Mehdi Jamei

Co-founder & CEO

PhD EECS, UC Berkeley; previously led agentic AI at System and Workmate.

Profile ↗

Andi Partovi

Co-founder & CTO

PhD (brain-computer interfaces), University of Melbourne; ex-Google Solutions Architect; ex-founder/CTO of KeyLead Health.

Profile ↗

What practitioners should know

For researchers

Veris has two arXiv papers whose author lists are the Veris team: VAmoS Bench (2607.27453) and VAmoS Part Deux / VAmoS Energy (2609.38512). Both score voice agents on backend state changes, not just transcripts.
Benchmark agent code is open at github.com/veris-ai/riley-agent and github.com/veris-ai/rory-agent (MIT).
RFT results: Qwen3 4B reached 94.4% on scam detection (with Savi Security, Mar 2026), and Qwen 14B rose from 0.401 to 0.604 on Sigma-rule generation (Dec 2025). Both are vendor-run and not peer-reviewed.
A vendor study claims Veris's simulated users are more realistic than τ²-bench's (84.8% vs 68.6% naturalness, with the same LLM judge for both). It has not been independently replicated.

For program managers

Funding is unchanged: an $8.5M seed in June 2025, led by Decibel and Acrew. No new round was found for Apr-Oct 2026.
The team is small: 9 people on the team page, including a Head of Sales.
Sales channels: self-serve Veris Plus (Apr 2026) and Google Cloud Marketplace (Mar 2026). The site also shows AWS Partner Network, NVIDIA Inception, Accenture FinTech Innovation Lab and Plug and Play Tech Center logos; these are self-displayed program memberships, not verified partnerships.
No frontier-lab customer ties were found. The public benchmarks evaluate frontier models from xAI, Google and OpenAI, but these are not partnerships. Most customers are anonymized; the only named collaborator is Savi Security.

For data ops

Integration is based on a CLI and containers. A .veris/ folder holds veris.yaml and Dockerfile.sandbox; declared external services such as Slack are intercepted at the DNS layer and routed to LLM-powered mocks, with no agent code changes. The open-source veris-cli uses .veris/twin.yaml and a VERIS_API_KEY environment variable for CI.
The docs at docs.veris.ai cover services (PostgreSQL, Kubernetes, Elasticsearch, Splunk), voice frameworks (ElevenLabs, LiveKit, Vapi), CI/CD regression gating, and RL/SFT training. The E2B and Daytona sandbox integrations are open-sourced (Apache-2.0).
Deployment options are Veris Cloud, the customer's own cloud (AWS, GCP or Azure), or on-prem.
Security claims are self-reported: SOC 2 Type II (AICPA logo shown), HIPAA and GDPR. There is no trust portal and no named auditor. Simulations run on synthetic data.

Benchmarks & research

8 published

VAmoS Pro Bench (VAmoS Energy)benchmark · 1 Oct 2026

Voice-agent benchmark with 100 utility-billing support tasks. Callers make several requests and there is background noise and impatience. The agent has 16 tools wired to a billing twin and a loan engine, and must verify the caller first. 3,798 calls were counted, out of 4,200 attempted. Code: github.com/veris-ai/rory-agent (MIT).

Best of 14 stacks: Grok Voice at 44.7% task completion, ahead of Gemini 3.8 Live at 40.1% and GPT-Live 1 at 39.2%; the range is 17.3-44.7%.

Open ↗Paper ↗

User-simulation realism: Veris vs τ²-benchpaper · 31 Aug 2026

Vendor study that scores simulated-user naturalness with a five-check binary rubric judged by azure/gpt-5.4-mini. Not peer-reviewed.

Veris 84.8% vs τ²-bench-retail 68.6% naturalness (vendor-run).

Open ↗

VAmoS Bench (Voice Agent Simulation Bench)benchmark · 29 Jul 2026

Credit-card support voice agent ('Riley') across 100 scenarios, about one-third adversarial. Each has a simulated caller and a simulated SQL backend and is scored by binary assertions on full traces. Code: github.com/veris-ai/riley-agent (MIT).

Best of 17 stacks: pipecat at 71.0% task completion (leaderboard updated 2026-08-06).

Open ↗Paper ↗

RFT case study with Savi Security: Qwen3 4B scam detectionpaper · 30 Mar 2026

Vendor blog co-authored with Savi Security on reinforcement fine-tuning a small model for scam detection across emails, SMS and call transcripts. Not peer-reviewed.

Qwen3 4B rose from about 80% to 94.4% accuracy after RFT and ran roughly 2-13x faster per sample than the comparison models (vendor-run).

Open ↗

BankingBenchbenchmark · Feb 2026

Simulation-based evaluation of 7 LLMs on a credit-card replacement workflow, using 41 behavioral checks in 8 categories. Vendor blog.

Overall pass rates were 88.2-93.5%, but category spreads reached 66 pp (error handling: DeepSeek 80.6% vs Grok-3-fast 14.7%).

Open ↗

SantaBenchbenchmark · 18 Dec 2025

Light-hearted agent benchmark covering web research, identity verification, multi-turn conversation and tool-execution reliability (20 scenarios x 5 runs). Vendor blog.

DeepSeek V3.2 had the highest tool reliability at 95%, ahead of Grok 4 at 75% and GPT-5.2 at 65%.

Open ↗

Technical Report: How Reinforcement Fine-tuning Trains Enterprise-Grade Domain-specific Agentspaper · 1 Dec 2025

Vendor technical report by Ritiz Tambi, Sahar Shayegan and Mehdi Jamei on RFT for generating Sigma security-detection rules, verified deterministically with Chainsaw.

Qwen 14B improved from 0.401 to 0.604, approaching GPT-5 at 0.6815 at roughly 200x lower inference cost (vendor-run).

Open ↗

Dynamic Benchmarking: Evaluate AI Agents through Environments, not Datasetspaper · 28 Oct 2025

Position post by Andi Partovi setting out Veris's environment-based approach to agent evaluation.

Open ↗

Products

Veris for Benchmarking ↗

Lets an organization build custom benchmarks around its own policies and systems to evaluate vendor and internal agents end-to-end against production twins.

Veris for Agentic SDLC ↗

A stateful sandbox where coding agents verify their work before pull requests open. The homepage names Claude Code, Codex, Cursor and GitHub Copilot.

Veris Plus ↗

Self-serve simulation sandbox with 30+ built-in SaaS simulations, simulated users, auto-generated success criteria, parallel rollouts and audit reports.launched 27 Apr 2026

Veris CLI ↗

Open-source (MIT) Go CLI for the Veris dependency sandbox. Commands are veris login, env create, up, run and down; configuration lives in .veris/twin.yaml, and CI uses VERIS_API_KEY. The repo was created in Aug 2026.launched Aug 2026

Public leaderboards (VAmoS, VAmoS Pro) ↗

Public voice-agent benchmark leaderboards: VAmoS covers 17 stacks (updated 2026-08-06) and VAmoS Pro covers 14 stacks (2026-10-01).

Google Cloud Marketplace listing ↗

The platform is available through Google Cloud Marketplace. The announcement includes a quote from Google Cloud's Dai Vu.launched 16 Mar 2026

Scale & velocity

Current headcount

1-10 (approx 9) as of 2026-06-07reported cite

Headcount growth

unknown

Open roles

unknown

Other locations

unknown

Distributed / remote

unknown

Research depth

Has researchers

yesconfirmed cite

Researcher count

~2 applied research engineers (Sahar Shayegan, Ritiz Tambi) plus 2 PhD co-founders; 8 of the 9 people on the team page co-author the arXiv papersestimated cite

Backgrounds

CEO Mehdi Jamei: PhD EECS UC Berkeley; previously led agentic AI at System and Workmate, CTO Andi Partovi: PhD (brain-computer interfaces) University of Melbourne; ex-Solutions Architect at Google; ex-founder/CTO KeyLead Healthreported cite

Capital

Total raised

$8.5Mconfirmed cite

Last round

Seed, $8.5M, June 2025confirmed cite

Investors

Decibel Ventures (lead), Acrew Capital (lead), The House Fund, Ian Livingstone, Idris Mokhtarzada (Rocket Money), Dorothy Changconfirmed cite

Valuation

unknown

Revenue signals

Usage-based pricing (by simulation volume and environment complexity); self-serve tier launched Apr 2026; Google Cloud Marketplace listing (Mar 2026). No revenue figures disclosed.confirmed cite

Security & compliance

SOC 2

claimed-unverifiedreported cite

Other certifications

HIPAA (self-claimed), GDPR (self-claimed)reported cite

Security page

unknown

Product

What they sell

environmentsconfirmed cite

Open source

partialconfirmed cite

License

Proprietary platform; open-source CLI, sandbox integrations and benchmark agents under MIT / Apache-2.0confirmed cite

Deployment model

managed-hosted (Veris Cloud), self-hosted (customer VPC on AWS/GCP/Azure), and on-premconfirmed cite

Maturity

GAreported cite

Notable customers

Savi Security (RFT research collaborator / co-author) self-claimed Telecom operator (unnamed) - production customer-service agent self-claimed Consumer fintech company (unnamed) - compliant chatbots self-claimed HR tech / executive-assistant agent company (unnamed) self-claimed Manufacturer - supply chain agent (unnamed) self-claimed cite

Buyer analysis

Best fit: Enterprise teams shipping customer-facing chat, voice or tool-calling agents (especially in finance, telecom and utilities) who need policy-specific benchmarks, CI regression gating, and simulated environments for RFT before production.

How we verified this

2026-10-05 refresh: I opened every source in the draft and checked each claim against it. The identity is correct. All in-window news items are confirmed on Veris's own blog, the arXiv abstract pages or the leaderboard pages, and every figure I checked matched; they are vendor-run results and are labelled that way. I made three kinds of change: - **Dropped:** two news items dated before 2026-04-01, the RFT case study (2026-03-30) and the GCP Marketplace post (2026-03-16). The RFT study is kept as a publication and GCP as a product. - **Corrected:** I reframed the AWS AgentCore item as a vendor-authored integration guide with a self-stated APN listing, and corrected the Veris CLI description to match its README (twin.yaml, login/env/up/run/down). I fixed the researcher-count wording (9 on the team page, 8 of them on the papers), named the exact Claude model in the telecom study, and moved photo_source_page to /company, since /about now 308-redirects there. - **Confirmed or added:** both founder headshots are single-person team-card images from Veris's own site, served as image/jpeg and image/png and tied to the right names in the page HTML. The GitHub API confirms the repo licenses. I added one missed item: Business Insider (2026-09-24) quoting CEO Mehdi Jamei on agent reliability. No funding, acquisition, shutdown or frontier-lab partnership was found. That check is limited: the web-search budget was exhausted, so it rests on Google News RSS and the vendor's own channels. SOC 2, HIPAA and GDPR remain self-claimed, and customers remain self-claimed and mostly anonymized.

Related vendors

Sources

veris.ai/blog · 2026-10-05, Blog index with 2026 posts and dates
veris.ai/blog/vamos-pro-bench-a-harder-exam-for-voice-agents · 2026-10-05, VAmoS Pro Bench launch, 2026-10-01
arxiv.org/abs/2609.38512 · 2026-10-05, VAmoS Part Deux paper, submitted 2026-09-29, 8 Veris authors
arxiv.org/abs/2607.27453 · 2026-10-05, VAmoS Bench paper, submitted 2026-07-29, 8 Veris authors
www.veris.ai/leaderboard · 2026-10-05, Leaderboard index (VAmoS Pro, VAmoS)
www.veris.ai/leaderboard/vamos-pro · 2026-10-05, VAmoS Pro results, 14 stacks, 2026-10-01
www.veris.ai/leaderboard/vamos · 2026-10-05, VAmoS results, 17 stacks, updated 2026-08-06
github.com/veris-ai · 2026-10-05, Public repos; licenses checked via the GitHub API
github.com/veris-ai/veris-cli · 2026-10-05, CLI README, MIT
www.businessinsider.com/ai-agents-gone-wrong-horror-stories-instinct-mus · 2026-10-05, Mehdi Jamei quoted as Veris AI cofounder/CEO, 2026-09-24
veris.ai/blog/dont-upgrade-the-model-simulate-first · 2026-10-05, NemoClaw / Nemotron prompt-vs-model study, 2026-09-13
veris.ai/blog/user-simulation-realism-veris-vs-tau2-bench · 2026-10-05, τ²-bench user-realism comparison, 2026-08-31
veris.ai/blog/the-right-model-for-the-right-task · 2026-10-05, Telecom agent six-model comparison, 2026-08-11
veris.ai/blog/the-loop-is-the-easy-part · 2026-10-05, Continuous-improvement loop case study, 2026-07-06
veris.ai/blog/let-openclaw-run-wild-in-simulation · 2026-10-05, OpenClaw simulation demo, 2026-06-08
veris.ai/blog/battle-testing-enterprise-ai-agents-veris-ai-aws-bedrock-a · 2026-10-05, AWS Bedrock AgentCore integration walkthrough, 2026-05-18
veris.ai/blog/veris-plus-is-live · 2026-10-05, Veris Plus self-serve launch, 2026-04-27
veris.ai/blog/rft-can-make-agents-with-small-models-outperform-big-model · 2026-10-05, RFT case study with Savi Security, 2026-03-30 (outside news window; kept as a publication)
veris.ai/blog/veris-ai-announces-availability-on-google-cloud-marketplac · 2026-10-05, Google Cloud Marketplace availability, 2026-03-16 (outside news window; kept as a product/channel)
veris.ai/blog/bankingbench-measuring-model-performance · 2026-10-05, BankingBench, Feb 2026
veris.ai/blog/santabench · 2026-10-05, SantaBench, 2025-12-18
veris.ai/blog/technical-report-reinforcement-learning-fine-tuning-for-en · 2026-10-05, RFT technical report, 2025-12-01
veris.ai/blog/dynamic-benchmarking · 2026-10-05, Dynamic Benchmarking post by Andi Partovi, 2025-10-28
www.veris.ai/company · 2026-10-05, Team page (target of the /about 308 redirect): 9 people, founder headshots, LinkedIn links, AICPA SOC logo, program logos, Gusto careers board
veris.ai/ · 2026-10-05, Current products, coding agents named, security claims, partner logos
veris.ai/faqs · 2026-10-05, Deployment options, SOC 2/HIPAA/GDPR claims, usage-based pricing, synthetic data
docs.veris.ai/ · 2026-10-05, Docs scope: veris.yaml, Dockerfile.sandbox, CI/CD, services, voice frameworks, RL/SFT use cases
news.google.com/rss/search?q=%22Veris+AI%22&hl=en-US&gl=US&ceid=US:en · 2026-10-05, News scan ('Veris AI', '+funding', 'Mehdi Jamei'): no funding coverage after June 2025
veris.ai/about · 2026-06-07, Team list (founders + ~9 staff), product description
www.alleywatch.com/2025/06/veris-ai-enterprise-ai-agents-agentic-simulat · 2026-06-07, Seed funding $8.5M, investors, customer categories, June 2025
www.businesswire.com/news/home/20250603868539/en/ · 2026-06-07, Emergence from stealth press release, $8.5M (fetch timed out; corroborated via other outlets)
www.citybiz.co/article/701797/ · 2026-06-07, Idris Mokhtarzada angel participation in seed round
www.linkedin.com/company/veris-ai · 2026-06-07, Public snippet: HQ San Francisco, 1-10 employees, founded 2025
mjamei.github.io/ · 2026-06-07, Mehdi Jamei background: PhD UC Berkeley EECS, prior roles
www.linkedin.com/in/andi-partovi/ · 2026-06-07, Andi Partovi background
qconsf.com/speakers/andipartovi · 2026-06-07, Andi Partovi PhD Melbourne, ex-Google GenAI Solution Architect, ex-KeyLead Health
www.decibel.vc/articles/veris-ai-why-the-environment-is-everything-for-a · 2026-06-07, Lead investor thesis / environment-layer positioning

Last updated 2026-10-05 · Every quantitative field carries a source and a confidence tag. Fields we could not source publicly are marked unknown, never estimated. See the methodology.